https://arxiv.org/api/LYIDkQC1qqh9wzAK0OAInjUlszk 2026-09-28T16:40:31Z 60 67 0 http://arxiv.org/abs/2609.15032v1 2026-09-14T04:50:52Z

Live free-viewpoint visualization of real humans is critical for immersive communication and interactive digital experiences. Existing methods either rely on computationally expensive optimization or require calibrated cameras and low-resolution inputs, making real-time high-resolution deployment impractical. In this work, we present Tele360, the first real-time feed-forward system for dynamic human reconstruction and live free-viewpoint visualization from sparse, unposed RGB streams. Our system jointly estimates camera poses and reconstructs a dynamic 3D Gaussian representation for each time instance in a single forward pass. To achieve this, we start by designing a lightweight sparsity-aware multi-view transformer backbone that tokenizes foreground human regions while preserving global context through a shared scene token. We then employ a fully transformer-based Gaussian decoder to mitigate convolution-induced over-smoothing while keeping decoding sparse and efficient. In addition, we introduce a hybrid feature pyramid that injects multi-scale appearance cues into geometry prediction. We further introduce a lightweight differentiable Levenberg-Marquardt camera refinement layer to enhance multi-view consistency and geometric alignment. Moreover, to stabilize learning under sparse, unposed inputs, we transfer multi-view geometry priors from a large visual-geometry foundation model via teacher-student distillation. Finally, the predicted Gaussian maps are streamed with video codecs to remote devices for interactive free-viewpoint rendering. Extensive experiments show that Tele360 achieves state-of-the-art visual quality on studio benchmarks while supporting real-time 2K input-to-rendering at over 25 FPS on a single consumer GPU. Additional captured sequences illustrate its performance across varied subjects, clothing, and motions under our multi-camera setup.

2026-09-14T04:50:52Z Hanzhang Tu Zhanfeng Liao Wei Min Jiajun Zhang Yebin Liu http://arxiv.org/abs/2608.19556v1 2026-08-20T01:54:26Z

Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion. Recent bidirectional approaches address this problem using rewards signals built upon 3D Gaussian-Splatting reconstruction. However, a single rigid 3d reconstruction cannot model a dynamic scene, so this critic penalizes genuine object motion as reconstruction error and is maximized by freezing the video. This shortcut is especially detrimental in the AR setting, where each chunk can propagate an already-static configuration. In this work, we propose Stream4D, which replaces the static critic with a feed-forward 4D reconstruction reward that explicitly models scene dynamics, allowing coherent motion to receive high consistency rewards. To further guide motion magnitude and quality, we add a motion prior that rewards natural scene-flow magnitude while penalizing jitter and non-rigid artifacts. Our final recipe combines these two terms with a lightweight perceptual anchor. Across various autoregressive video backbones and various generation horizons, Stream4D improves 4D reconstruction quality, preserves motion more effectively, and achieves higher human-aligned preference. Project page: https://banyuanhao.github.io/Stream4D/

2026-08-20T01:54:26Z Yuanhao Ban Jiaqi Feng Hengguang Zhou Xiaohuan Pei Justin Cui Cho-Jui Hsieh http://arxiv.org/abs/2607.29106v1 2026-07-31T07:35:52Z

Reconstructing animatable 3D human avatars from a single image remains particularly challenging for loose garments, whose geometry and motion cannot be adequately represented by body-aligned topology and skinning. We present Forwardrobe, a feed-forward framework for reconstructing garment-aware Gaussian avatars from a single image. Forwardrobe explicitly separates clothing from the body in canonical Gaussian space and equips the garment layer with continuity-aware geometry and skinning initialization, pose-conditioned non-rigid deformation, and appearance adaptation. These designs improve garment reconstruction and visual quality during animation, particularly for skirts and dresses. The separated garment layer additionally forms an independently controllable 3D asset, enabling garment editing, transfer, and 3D virtual try-on. Experiments demonstrate improved garment reconstruction quality and greater flexibility in garment manipulation compared with existing single-image avatar reconstruction methods.

2026-07-31T07:35:52Z Daisheng Jin Shuyun Wang Ying He http://arxiv.org/abs/2607.12206v1 2026-07-13T23:16:29Z

We present RegHead, a framework for constructing semantic blendshape sets for animatable non-humanoid head avatars. With a fixed expression vocabulary, semantic blendshapes provide a low-dimensional and interpretable animation interface and support cross-identity retargeting. Building such blendshape sets remains expensive because (i) expression-consistent supervision is scarce, (ii) generated 4D assets typically lack correspondence, and (iii) facial motion is highly localized. We propose (1) a large-scale dataset of non-humanoid identities paired with a shared expression vocabulary, obtained by expanding a small artist-rigged library via fine-tuned image editing; (2) a dense stochastic anchor motion representation tailored to localized facial deformations; and (3) a fast feed-forward registration model that converts unregistered expression meshes into a corresponded blendshape basis by predicting anchor-based deformations from the neutral shape. Experiments show that our approach produces higher-fidelity expression meshes than baselines, while running orders of magnitude faster than optimization. We further demonstrate real-time retargeting from human face tracking signals to non-humanoid characters, capturing both head pose and localized facial motions. Our project page is available at https://snap-research.github.io/RegHead/.

2026-07-13T23:16:29Z Jiahao Luo Hao Zhang Jianqi Chen Yijie He Jiaxu Zou Michael Vasilkovsky Sergei Korolev Sergey Tulyakov Chaoyang Wang Peter Wonka James Davis Jian Wang http://arxiv.org/abs/2607.05243v1 2026-07-06T15:53:09Z

Reconstructing dynamic human-scene environments from monocular videos is a challenging problem that requires jointly modeling scene geometry, camera motion, and non-rigid human dynamics while enabling photorealistic rendering. Recent feed-forward methods can efficiently predict geometry, but they are often limited to non-photorealistic representations such as point clouds and meshes, or they fail to handle non-rigid objects, particularly dynamic humans. To fill this gap, we present GUSH3R (Gaussian-Unified Scene Human 3D Reconstruction), a feed-forward framework for online dynamic human-scene reconstruction. From a monocular human-scene video, our method reconstructs dynamic humans (everyone) and static scenes (everywhere) in a single forward pass (all at once) as 3D Gaussian Splatting (3DGS) primitives (as gaussians), which are geometrically consistent and capable of novel view synthesis. Experiments on monocular human-scene datasets demonstrate that our approach achieves competitive novel view synthesis quality while significantly improving inference efficiency compared to optimization-based methods.

2026-07-06T15:53:09Z Project page: https://abkeito.github.io/gush3r-page/ Keito Abe Kaede Shiohara Takashi Otonari Toshihiko Yamasaki http://arxiv.org/abs/2606.32036v1 2026-06-30T17:59:05Z

Producing 3D human representations from input views on the fly is essential for immersive live streaming systems, where representation compactness is as critical as high fidelity given limited computational power and transmission bandwidth. Although recent feed-forward reconstruction methods achieve impressive quality through the view-centric prediction of 3D representations, they repeatedly encode the same subject content across multiple views, leading to significant inter-view redundancy. Our key insight is to perform predictions directly in 3D space, enabling the network to learn and produce a highly compact representation. To this end, we propose PointSplat, a novel human-centric approach that directly infers Gaussian primitives from an input point set. The proposed method first estimates a coarse geometric proxy and performs ray casting to prune redundant points and establish explicit 2D--3D correspondences. Subsequently, it employs a Point-Image Transformer to fuse appearance and geometry features, predicting Gaussian attributes in a single forward pass. This design restricts predictions to foreground regions of interest, substantially reducing the total number of Gaussians while improving novel-view rendering quality. Extensive experiments demonstrate that PointSplat achieves higher efficiency and quality while exhibiting strong robustness to variations in view count and image resolution across multiple datasets.

2026-06-30T17:59:05Z Project Page: https://zju3dv.github.io/pointsplat Yujie Guo Yudong Jin Lingteng Qiu Zehong Shen Zhen Xu Jing Zhang Xianchao Shen Hujun Bao Sida Peng Xiaowei Zhou http://arxiv.org/abs/2606.29333v1 2026-06-28T11:01:36Z

Uncalibrated volumetric video streaming for human reconstruction is essential for holographic communication and AR/VR, yet remains challenging due to the need for temporal consistency and computational efficiency from sparse-view inputs. Existing methods rely on per-scene optimization or calibrated cameras, while recent feed-forward models are limited to low-resolution (0.5K) single-frame synthesis. We present HiReFF, a feed-forward method for 2K-resolution 360° human video reconstruction from uncalibrated sparse-view videos. Our framework decomposes the problem into two key tasks: foreground 3D Gaussian reconstruction from sparse-view videos (four views separated by 90°) and computationally efficient high-resolution synthesis. To enable the former, we propose Scale-synchronized Camera Calibration to resolve scale ambiguity for multi-view supervision, and Gaussian-wise Foreground Masking to reconstruct clean foregrounds by modulating Gaussian parameters. For efficient high-resolution synthesis, our High-resolution Side-tuning achieves 2K rendering by augmenting the Gaussian head with supplementary features while keeping the backbone at 0.5K, drastically reducing computational overhead. Experiments demonstrate that HiReFF significantly outperforms existing methods in high-resolution streaming volumetric video reconstruction. https://iridescentjiang.github.io/HiReFF

2026-06-28T11:01:36Z Yiming Jiang Hanzhang Tu Wenfeng Song Siyou Lin Liang An Shuai Li Aimin Hao Yebin Liu http://arxiv.org/abs/2606.24232v2 2026-08-29T15:15:07Z

We introduce FiCA, a Feed-forward, instant Gaussian Codec Avatar generation pipeline that creates lifelike avatars from a single portrait image. Generating a photorealistic and drivable avatar from just a single image is significantly challenging due to the limited visual information available to accurately infer the 3D appearance and geometry of human heads. To address this, we develop a novel system that combines human-centric vision foundation models with a diffusion model. This system is designed to fully exploit partial visual observations to generate lifelike human avatars. Our proposed diffusion model learns a generative mapping from these partial observations to complete and authentic 3D mesh reconstruction. Additionally, we introduce a feed-forward mesh refinement network that enhances the fidelity and identity preservation of the generated avatars, eliminating the need for person-specific test-time optimization. By leveraging a universal prior model that decodes a generated mesh into a set of 3D Gaussians, we generate a photorealistic 3D Gaussian avatar, capable of being driven with novel expressions in real-time. Our experiments demonstrate that the avatars generated by our feed-forward approach faithfully represent diverse identities and surpass the visual quality of avatars produced by recent competing methods.

2026-06-23T07:22:17Z Project page: https://kim-youwang.github.io/FiCA Kim Youwang Zhengyu Yang Liuhao Ge Yu Rong Timur Bagautdinov Su Zhaoen Nir Sopher Jovan Popović Teng Deng Tae-Hyun Oh Chen Cao http://arxiv.org/abs/2606.22718v2 2026-07-30T13:03:09Z

We present Generative Relightable Avatars (GRA), a person-specific method for photorealistic free-view rendering and environment-map relighting of full-body humans. We postulate that modeling fine-grained appearance details is inherently a one-to-many problem that can benefit from a generative formulation. In contrast to fully regressive relightable avatar methods, GRA follows a hybrid approach that combines controllable, physics-grounded relighting with probabilistic refinement. Starting from a tracked animated mesh, we optimize material parameters in UV-space and render a coarse relit appearance under a target HDR environment map. Next, we refine the textures with a feed-forward model to capture pose-dependent texture dynamics and illumination effects beyond simplified reflectance assumptions. Finally, a fine-tuned video-to-video diffusion model transforms the physically grounded renderings into temporally coherent, high-detail videos while preserving 3D control, with an error-recycling strategy for generating long videos. Experimental evaluations demonstrate our method's improved perceptual quality over prior relightable avatar baselines. Project Page: https://vcai.mpi-inf.mpg.de/projects/GRA/

2026-06-21T23:36:00Z Project Page: https://vcai.mpi-inf.mpg.de/projects/GRA/ Kunwar Maheep Singh Christian Theobalt Rishabh Dabral http://arxiv.org/abs/2606.19156v1 2026-06-17T14:58:37Z

Dynamic 3D hand reconstruction from egocentric videos is essential for next-generation computing platforms such as AR/VR and AI glasses. Despite its importance, most prior works focus either on multi-view 3D hand reconstruction or on 4D human body reconstruction. Egocentric 4D hand reconstruction remains challenging due to fast head motion, rapid hand dynamics, severe occlusions, and inherent ambiguity from single-view observations. To address these challenges, we introduce Hand-4DGS, the first feed-forward framework for reconstructing dynamic 4D hands directly from egocentric videos, enabling both fast (~60 FPS) inference and strong generalization. Our approach incorporates a mesh-guided representation for structural priors and temporal convolutions to model dynamic motion. We evaluate our framework on two challenging egocentric datasets, H2O and ARCTIC, and demonstrate significant improvements over baselines. Our method benefits from the generalization capability of feed-forward networks and effective 2D image supervision through Gaussian splatting, without requiring expensive 3D hand pose ground-truth annotations.

2026-06-17T14:58:37Z Project page: https://jeongminb.github.io/hand-4dgs/ Jeongmin Bae Seoha Kim Marc Pollefeys Mahdi Rad Youngjung Uh Taein Kwon http://arxiv.org/abs/2606.15659v1 2026-06-14T07:55:57Z

High-quality 4D head avatars from one or a few source portraits are central to telepresence, AR/VR, and digital-human interaction. 3D Gaussian Splatting (3DGS) has emerged as the dominant representation, with two complementary regimes (generalizable feed-forward predictors and per-subject refiners) maturing in parallel. However, existing feed-forward predictors are trained on a single dataset family with a hard-coded source count, inheriting the corresponding domain bias. Per-subject refiners require 300K--600K iterations and rely on adaptive densification that destroys upstream Gaussian layouts, preventing the two regimes from sharing a representation end-to-end. To bridge both regimes we propose SpatialAvatar-0 on a shared FLAME-mesh-bound Gaussian representation: a feed-forward generator with a parameter-free K-source mean-pool and a monocular-temporal to multi-view-spatial two-phase schedule that anchors against identity-prior collapse onto the smaller multi-view set. We further introduce a 10K-iter layout-preserving per-subject refinement loop that freezes the FLAME-binding and Gaussian count and replaces densification with a three-component anti-spike regularization. On VFHQ/HDTF cross-domain zero-shot we surpass the in-domain leader GAGAvatar by +1.5 dB PSNR despite never training on either test domain, and on the SplattingAvatar monocular benchmark we lead every reported metric, surpassing the 300K-iter GeoAvatar by +1.3 dB PSNR at up to 60x shorter per-subject schedule than common SOTA baselines. Website: https://spatialwalk.github.io/SpatialAvatar-0.

2026-06-14T07:55:57Z Yiran Wang Zeyu Zhang Yuanming Li Ziming Wang Yang Zhao http://arxiv.org/abs/2606.02573v1 2026-06-01T17:58:11Z

In this paper, we present HumanNOVA, a photorealistic, universal, and rapid model for generating 3D human avatars from a single RGB image. Achieving both photorealism and generalization is challenging due to the scarcity of diverse, high-quality 3D human data. To address this, we build a scalable data generation pipeline that follows two strategies. The first one is to leverage existing rigged assets and animate them with extensive poses from daily life. The second strategy is to utilize existing multi-camera captures of humans and employ fitting to generate more diverse views for training. These two strategies enable us to scale up to 100k assets, significantly enhancing both the quantity and the diversity of data for robust model training. In terms of the architecture, HumanNOVA adopts a feed-forward, token-conditioned avatar modeling framework that allows fast inference in less than one second and requires no test-time optimization. Given an input image and an estimated simplified human mesh (SMPL) without detailed geometry or appearance, the model first encodes both inputs into compact token representations. These tokens then act as conditioning signals and are fused through cross-attention to construct a triplane-based 3D avatar representation. Extensive experiments on multiple benchmarks demonstrate the superiority of our approach, both quantitatively and qualitatively, as well as its robustness under diverse input image conditions. Project page at https://HumanNOVA.github.io .

2026-06-01T17:58:11Z CVPR 2026 Highlight Hezhen Hu Wangbo Zhao Lanqing Guo Hanwen Jiang Jonathan C. Liu Zhiwen Fan Kai Wang Zhangyang Wang Georgios Pavlakos http://arxiv.org/abs/2605.20752v2 2026-05-28T12:25:46Z

Vision-language-action (VLA) policies have advanced language-conditioned robotic manipulation by transferring semantic priors from pretrained vision-language models to action generation. However, standard action-imitation learning often lacks sufficient modeling of explicit 3D spatial information, dense geometric supervision, and future environment evolution, all critical for precise robotic interaction. To address this, we propose \textbf{GaussianDream}, a feed-forward 3D Gaussian world-model plug-in. Specifically, we introduce learnable GaussianDream Queries in the encoder, enabling the model to capture current-frame 3D spatial structure and short-horizon future evolution. During training, the latent GaussianDream prefix is processed by a static reconstruction head and a future prediction head to produce current 3D Gaussian scene states and future Gaussian evolution states. The current branch is supervised by RGB rendering and depth, while the future branch uses future RGB, depth, and pseudo 3D scene-flow signals. During inference, GaussianDream discards all auxiliary heads and retains only the learned prefix to condition action generation, without test-time Gaussian reconstruction or future prediction. Experimental results demonstrate that GaussianDream achieves state-of-the-art performance across multiple robotic manipulation benchmarks, reaching \textbf{98.4\%} on LIBERO, \textbf{54.8\%} on RoboCasa Human-50, and \textbf{50.0\%} on real-robot tasks. Compared with existing 3D-enhanced VLA methods, GaussianDream achieves strong accuracy while providing higher inference efficiency than video-based world-model approaches.

2026-05-20T05:51:30Z 19 pages, 9 figures Zijian Zhang Yuqing Jiang Qian Cheng Xiaofan Li Si Liu Ding Zhao Ping Luo Weitao Zhou Haibao Yu http://arxiv.org/abs/2605.04035v3 2026-07-01T09:13:55Z

We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method employs an efficient encoder-decoder architecture that compresses input views into a compact latent representation. This latent representation is then decoded into a set of UV-parameterized 3D Gaussians anchored to a neutral head template. This UV representation decouples the number of 3D Gaussians from the number and resolution of input images, enabling training with many high-resolution input views. We train and evaluate our model on an internal dataset with more than 10,000 subjects, which is an order of magnitude larger than existing multi-view human head datasets. HeadsUp achieves state-of-the-art reconstruction quality and generalizes to novel identities without test-time optimization. We extensively analyze the scaling behavior of our model across identities, views, and model capacity, revealing practical insights for quality-compute trade-offs. Finally, we highlight the strength of our latent space by showcasing two downstream applications: generating novel 3D identities and animating the 3D heads with expression blendshapes.

2026-05-05T17:55:01Z Accepted to ECCV 2026. Project website: https://apple.github.io/ml-headsup/ Evangelos Ntavelis Sean Wu Mohamad Shahbazi Fabio Maninchedda Dmitry Kostiaev Artem Sevastopolsky Vittorio Megaro Trevor Phillips Alejandro Blumentals Shridhar Ravikumar Mehak Gupta Reinhard Knothe Jeronimo Bayer Matthias Vestner Simon Schaefer Thomas Etterlin Christian Zimmermann Alexey Artemov Mathias Deschler Peter Kaufmann Stefan Brugger Sebastian Martin Brian Amberg Tom Runia http://arxiv.org/abs/2604.25330v1 2026-04-28T07:46:50Z

Real-time immersive video communications, particularly high-fidelity 3D telepresence, necessitates a synergistic balance between instantaneous dynamic scene reconstruction and high-efficiency data transmission. While recent advancements in feed-forward 3D Gaussian Splatting (3DGS) have enabled real-time rendering, performing multi-view video coding and 3D reconstruction in a decoupled manner leads to suboptimal compression efficiency and high computational complexity. To address this, we propose GS-SCNet, the first unified end-to-end framework that seamlessly integrates generalizable 3DGS reconstruction with a dedicated deep Semantic Coding pipeline. Our architecture is underpinned by two core technical contributions: (i) we introduce a Disparity-Guided Parallel Semantic Codec that exploits epipolar geometric priors to facilitate cross-view contextual interaction via disparity compensation and semantic fusion, thereby enabling real-time parallel processing of stereo streams while significantly enhancing rate-distortion performance, and (ii) we develop a Lightweight Gaussian Parameter Predictor which directly projects decoded semantic latents into 3DGS attributes, obviating the need for intermediate pixel-domain reconstruction. By coupling the codec with the task-specific predictor, our framework extracts geometric correlations only once, effectively eliminating the redundant computational bottleneck inherent in conventional decoupled paradigms. Extensive evaluations on both synthetic and real-world human datasets demonstrate that GS-SCNet achieves a superior trade-off across compression efficiency, rendering quality, and real-time performance. Notably, our framework exhibits strong cross-domain generalization and robustness against compression artifacts when applied to out-of-domain real-world data, significantly outperforming conventional decoupled transmission paradigms.

2026-04-28T07:46:50Z Under review Dingxi Yang Wenqi Guo Yue Liu Jungong Han Zhijin Qin http://arxiv.org/abs/2604.13476v2 2026-04-26T03:48:21Z

Surround-view perception is increasingly important for robotic navigation and loco-manipulation, especially in human-in-the-loop settings such as teleoperation, data collection, and emergency takeover. However, current robotic visual interfaces are often limited to narrow forward-facing views, or, when multiple on-board cameras are available, require cumbersome manual switching that interrupts the operator's workflow. Both configurations suffer from motion-induced jitter that causes simulator sickness in head-mounted displays. We introduce a surround-view robotic vision system that combines six cameras with LiDAR to provide full 360$^\circ$ visual coverage, while meeting the geometric and real-time constraints of embodied deployment. We further present \textsc{RobotPan}, a feed-forward framework that predicts \emph{metric-scaled} and \emph{compact} 3D Gaussians from calibrated sparse-view inputs for real-time rendering, reconstruction, and streaming. \textsc{RobotPan} lifts multi-view features into a unified spherical coordinate representation and decodes Gaussians using hierarchical spherical voxel priors, allocating fine resolution near the robot and coarser resolution at larger radii to reduce computational redundancy without sacrificing fidelity. To support long sequences, our online fusion updates dynamic content while preventing unbounded growth in static regions by selectively updating appearance. Finally, we release a multi-sensor dataset tailored to 360$^\circ$ novel view synthesis and metric 3D reconstruction for robotics, covering navigation, manipulation, and locomotion on real platforms. Experiments show that \textsc{RobotPan} achieves competitive quality against prior feed-forward reconstruction and view-synthesis methods while producing substantially fewer Gaussians, enabling practical real-time embodied deployment.

2026-04-15T04:58:23Z Project website: https://robotpan.github.io/ Jiahao Ma Qiang Zhang Peiran Liu Zeran Su Pihai Sun Gang Han Wen Zhao Wei Cui Zhang Zhang Zhiyuan Xu Renjing Xu Jian Tang Miaomiao Liu Yijie Guo http://arxiv.org/abs/2604.10259v2 2026-07-23T17:36:45Z

We present HumanGS, a generalizable feed-forward Gaussian splatting framework for human 3D reconstruction and real-time animation from sparse multi-view RGB images and their associated SMPL-X poses. Unlike prior methods that rely on depth supervision, fixed input views, UV maps, repeated feed-forward inference for each target pose or view, or computationally expensive vertex-to-image cross-attention, HumanGS employs a simple transformer architecture that explicitly associates SMPL-X vertices with multi-scale image features through geometric back-projection. This eliminates the need for large pre-trained human representation models while naturally aggregating complementary information from multiple views. The aggregated vertex features are mapped by a lightweight MLP decoder to a canonical set of 3D Gaussian primitives aligned with SMPL-X vertices. One Gaussian is regularized to remain close to the SMPL-X surface, providing a strong geometric prior and stable correspondence to the parametric body model, while a small set of unconstrained Gaussians per vertex captures geometric details beyond the body surface, such as clothing and hair. The resulting canonical representation is animated efficiently using linear blend skinning and Gaussian rasterization without further network inference. Trained entirely from scratch on only 10K frames from THuman2.1, HumanGS achieves reconstruction quality comparable to or better than state-of-the-art methods while reducing reconstruction time by over 15 times compared to recent transformer-based approaches, enabling real-time animation and interactive applications. Code and pre-trained models are available at https://github.com/Devdoot57/HumanGS .

2026-04-11T15:52:58Z Devdoot Chatterjee Zakaria Laskar C. V. Jawahar http://arxiv.org/abs/2604.02320v2 2026-04-07T17:25:24Z

High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. On the one hand, multi-view studio data enables high-fidelity modeling of humans with precise control over expressions and poses, but it struggles to generalize to real-world data due to limited scale and the domain gap between the studio environment and the real world. On the other hand, recent large-scale avatar models trained on millions of in-the-wild samples show promise for generalization across a wide range of identities, yet the resulting avatars are often of low-quality due to inherent 3D ambiguities. To address this, we present Large-Scale Codec Avatars (LCA), a high-fidelity, full-body 3D avatar model that generalizes to world-scale populations in a feedforward manner, enabling efficient inference. Inspired by the success of large language models and vision foundation models, we present, for the first time, a pre/post-training paradigm for 3D avatar modeling at scale: we pretrain on 1M in-the-wild videos to learn broad priors over appearance and geometry, then post-train on high-quality curated data to enhance expressivity and fidelity. LCA generalizes across hair styles, clothing, and demographics while providing precise, fine-grained facial expressions and finger-level articulation control, with strong identity preservation. Notably, we observe emergent generalization to relightability and loose garment support to unconstrained inputs, and zero-shot robustness to stylized imagery, despite the absence of direct supervision.

2026-04-02T17:58:40Z Accepted in CVPR2026. Website: https://junxuan-li.github.io/lca Junxuan Li Rawal Khirodkar Chengan He Zhongshi Jiang Giljoo Nam Lingchen Yang Jihyun Lee Egor Zakharov Zhaoen Su Rinat Abdrashitov Yuan Dong Julieta Martinez Kai Li Qingyang Tan Takaaki Shiratori Matthew Hu Peihong Guo Xuhua Huang Ariyan Zarei Marco Pesavento Yichen Xu He Wen Teng Deng Wyatt Borsos Anjali Thakrar Jean-Charles Bazin Carsten Stoll Ginés Hidalgo James Booth Lucy Wang Xiaowen Ma Yu Rong Sairanjith Thalanki Chen Cao Christian Häne Abhishek Kar Sofien Bouaziz Jason Saragih Yaser Sheikh Shunsuke Saito http://arxiv.org/abs/2603.14772v1 2026-03-16T03:12:27Z

Existing single-image 3D human avatar methods primarily rely on rigid joint transformations, limiting their ability to model realistic cloth dynamics. We present DynaAvatar, a zero-shot framework that reconstructs animatable 3D human avatars with motion-dependent cloth dynamics from a single image. Trained on large-scale multi-person motion datasets, DynaAvatar employs a Transformer-based feed-forward architecture that directly predicts dynamic 3D Gaussian deformations without subject-specific optimization. To overcome the scarcity of dynamic captures, we introduce a static-to-dynamic knowledge transfer strategy: a Transformer pretrained on large-scale static captures provides strong geometric and appearance priors, which are efficiently adapted to motion-dependent deformations through lightweight LoRA fine-tuning on dynamic captures. We further propose the DynaFlow loss, an optical flow-guided objective that provides reliable motion-direction geometric cues for cloth dynamics in rendered space. Finally, we reannotate the missing or noisy SMPL-X fittings in existing dynamic capture datasets, as most public dynamic capture datasets contain incomplete or unreliable fittings that are unsuitable for training high-quality 3D avatar reconstruction models. Experiments demonstrate that DynaAvatar produces visually rich and generalizable animations, outperforming prior methods.

2026-03-16T03:12:27Z Accepted to CVPR 2026 Joohyun Kwon Geonhee Sim Gyeongsik Moon http://arxiv.org/abs/2603.07660v1 2026-03-08T14:49:20Z

The pursuit of spatial intelligence fundamentally relies on access to large-scale, fine-grained 3D data. However, existing approaches predominantly construct spatial understanding benchmarks by generating question-answer (QA) pairs from a limited number of manually annotated datasets, rather than systematically annotating new large-scale 3D scenes from raw web data. As a result, their scalability is severely constrained, and model performance is further hindered by domain gaps inherent in these narrowly curated datasets. In this work, we propose Holi-Spatial, the first fully automated, large-scale, spatially-aware multimodal dataset, constructed from raw video inputs without human intervention, using the proposed data curation pipeline. Holi-Spatial supports multi-level spatial supervision, ranging from geometrically accurate 3D Gaussian Splatting (3DGS) reconstructions with rendered depth maps to object-level and relational semantic annotations, together with corresponding spatial Question-Answer (QA) pairs. Following a principled and systematic pipeline, we further construct Holi-Spatial-4M, the first large-scale, high-quality 3D semantic dataset, containing 12K optimized 3DGS scenes, 1.3M 2D masks, 320K 3D bounding boxes, 320K instance captions, 1.2M 3D grounding instances, and 1.2M spatial QA pairs spanning diverse geometric, relational, and semantic reasoning tasks. Holi-Spatial demonstrates exceptional performance in data curation quality, significantly outperforming existing feed-forward and per-scene optimized methods on datasets such as ScanNet, ScanNet++, and DL3DV. Furthermore, fine-tuning Vision-Language Models (VLMs) on spatial reasoning tasks using this dataset has also led to substantial improvements in model performance.

2026-03-08T14:49:20Z project page: https://visionary-laboratory.github.io/holi-spatial/ Yuanyuan Gao Hao Li Yifei Liu Xinhao Ji Yuning Gong Yuanjun Liao Fangfu Liu Manyuan Zhang Yuchen Yang Dan Xu Xue Yang Huaxi Huang Hongjie Zhang Ziwei Liu Xiao Sun Dingwen Zhang Zhihang Zhong http://arxiv.org/abs/2601.18851v1 2026-01-26T14:26:16Z

Head avatar reenactment focuses on creating animatable personal avatars from monocular videos, serving as a foundational element for applications like social signal understanding, gaming, human-machine interaction, and computer vision. Recent advances in 3D Morphable Model (3DMM)-based facial reconstruction methods have achieved remarkable high-fidelity face estimation. However, on the one hand, they struggle to capture the entire head, including non-facial regions and background details in real time, which is an essential aspect for producing realistic, high-fidelity head avatars. On the other hand, recent approaches leveraging generative adversarial networks (GANs) for head avatar generation from videos can achieve high-quality reenactments but encounter limitations in reproducing fine-grained head details, such as wrinkles and hair textures. In addition, existing methods generally rely on a large amount of training data, and rarely focus on using only a simple selfie video to achieve avatar reenactment. To address these challenges, this study introduces a method for detailed head avatar reenactment using a selfie video. The approach combines 3DMMs with a StyleGAN-based generator. A detailed reconstruction model is proposed, incorporating mixed loss functions for foreground reconstruction and avatar image generation during adversarial training to recover high-frequency details. Qualitative and quantitative evaluations on self-reenactment and cross-reenactment tasks demonstrate that the proposed method achieves superior head avatar reconstruction with rich and intricate textures compared to existing approaches.

2026-01-26T14:26:16Z Wei Liang Hui Yu Derui Ding Rachael E. Jack Philippe G. Schyns http://arxiv.org/abs/2601.07603v3 2026-05-21T11:50:40Z

We present UIKA, a feed-forward animatable Gaussian head model from an arbitrary number of pose-free inputs, including a single image, multi-view captures, and smartphone-captured videos. Unlike the traditional avatar method, which requires a studio-level multi-view capture system and reconstructs a human-specific model through a long-time optimization process, we rethink the task through the lenses of model representation, network design, and data preparation. First, we introduce a UV-guided avatar modeling strategy, in which each input image is associated with a pixel-wise facial correspondence estimation. Such correspondence estimation allows us to reproject each valid pixel color from screen space to UV space, which is independent of camera pose and character expression. Furthermore, we design learnable UV tokens on which the attention mechanism can be applied at both the screen and UV levels. The learned UV tokens can be decoded into canonical Gaussian attributes using aggregated UV information from all input views. To train our large avatar model, we additionally prepare a large-scale, identity-rich synthetic training dataset. Our method significantly outperforms existing approaches in both monocular and multi-view settings.

2026-01-12T14:53:56Z CVPR 2026 Highlight. Code: https://github.com/ant-research/UIKA Zijian Wu Boyao Zhou Liangxiao Hu Hongyu Liu Yuan Sun Xuan Wang Xun Cao Yujun Shen Hao Zhu http://arxiv.org/abs/2601.06378v1 2026-01-10T01:26:28Z

Despite significant progress in 4D generation, rig and motion, the core structural and dynamic components of animation are typically modeled as separate problems. Existing pipelines rely on ground-truth skeletons and skinning weights for motion generation and treat auto-rigging as an independent process, undermining scalability and interpretability. We present RigMo, a unified generative framework that jointly learns rig and motion directly from raw mesh sequences, without any human-provided rig annotations. RigMo encodes per-vertex deformations into two compact latent spaces: a rig latent that decodes into explicit Gaussian bones and skinning weights, and a motion latent that produces time-varying SE(3) transformations. Together, these outputs define an animatable mesh with explicit structure and coherent motion, enabling feed-forward rig and motion inference for deformable objects. Beyond unified rig-motion discovery, we introduce a Motion-DiT model operating in RigMo's latent space and demonstrate that these structure-aware latents can naturally support downstream motion generation tasks. Experiments on DeformingThings4D, Objaverse-XL, and TrueBones demonstrate that RigMo learns smooth, interpretable, and physically plausible rigs, while achieving superior reconstruction and category-level generalization compared to existing auto-rigging and deformation baselines. RigMo establishes a new paradigm for unified, structure-aware, and scalable dynamic 3D modeling.

2026-01-10T01:26:28Z Project Page: https://RigMo-Page.github.io Hao Zhang Jiahao Luo Bohui Wan Yizhou Zhao Zongrui Li Michael Vasilkovsky Chaoyang Wang Jian Wang Narendra Ahuja Bing Zhou http://arxiv.org/abs/2512.01444v1 2025-12-01T09:28:50Z

3D human avatar animation aims at transforming a human avatar from an arbitrary initial pose to a specified target pose using deformation algorithms. Existing approaches typically divide this task into two stages: canonical template construction and target pose deformation. However, current template construction methods demand extensive skeletal rigging and often produce artifacts for specific poses. Moreover, target pose deformation suffers from structural distortions caused by Linear Blend Skinning (LBS), which significantly undermines animation realism. To address these problems, we propose a unified learning-based framework to address both challenges in two phases. For the former phase, to overcome the inefficiencies and artifacts during template construction, we leverage a U-Net architecture that decouples texture and pose information in a feed-forward process, enabling fast generation of a human template. For the latter phase, we propose a data-driven refinement technique that enhances structural integrity. Extensive experiments show that our model delivers consistent performance across diverse poses with an optimal balance between efficiency and quality,surpassing state-of-the-art (SOTA) methods.

2025-12-01T09:28:50Z 9 pages,4 figures Jian Shu Nanjie Yao Gangjian Zhang Junlong Ren Yu Feng Hao Wang http://arxiv.org/abs/2512.00255v2 2026-03-30T13:16:23Z

We present Relightable Holoported Characters (RHC), a novel person-specific method for free-view rendering and relighting of full-body and highly dynamic humans solely observed from sparse-view RGB videos at inference. In contrast to classical one-light-at-a-time (OLAT)-based human relighting, our transformer-based RelightNet predicts relit appearance within a single network pass, avoiding costly OLAT-basis capture and generation. For training such a model, we introduce a new capture strategy and dataset recorded in a multi-view lightstage, where we alternate frames lit by random environment maps with uniformly lit tracking frames, simultaneously enabling accurate motion tracking and diverse illumination as well as dynamics coverage. Inspired by the rendering equation, we derive physics-informed features that encode geometry, albedo, shading, and the virtual camera view from a coarse human mesh proxy and the input views. Our RelightNet then takes these features as input and cross-attends them with a novel lighting condition, and regresses the relit appearance in the form of texel-aligned 3D Gaussian splats attached to the coarse mesh proxy. Consequently, our RelightNet implicitly learns to efficiently compute the rendering equation for novel lighting conditions within a single feed-forward pass. Experiments demonstrate our method's superior visual fidelity and lighting reproduction compared to state-of-the-art approaches. Project page: https://vcai.mpi-inf.mpg.de/projects/RHC/

2025-11-29T00:17:34Z Kunwar Maheep Singh Jianchun Chen Vladislav Golyanik Stephan J. Garbin Thabo Beeler Rishabh Dabral Marc Habermann Christian Theobalt http://arxiv.org/abs/2511.22704v1 2025-11-27T18:58:54Z

We present Splat-SAP, a feed-forward approach to render novel views of human-centered scenes from binocular cameras with large sparsity. Gaussian Splatting has shown its promising potential in rendering tasks, but it typically necessitates per-scene optimization with dense input views. Although some recent approaches achieve feed-forward Gaussian Splatting rendering through geometry priors obtained by multi-view stereo, such approaches still require largely overlapped input views to establish the geometry prior. To bridge this gap, we leverage pixel-wise point map reconstruction to represent geometry which is robust to large sparsity for its independent view modeling. In general, we propose a two-stage learning strategy. In stage 1, we transform the point map into real space via an iterative affinity learning process, which facilitates camera control in the following. In stage 2, we project point maps of two input views onto the target view plane and refine such geometry via stereo matching. Furthermore, we anchor Gaussian primitives on this refined plane in order to render high-quality images. As a metric representation, the scale-aware point map in stage 1 is trained in a self-supervised manner without 3D supervision and stage 2 is supervised with photo-metric loss. We collect multi-view human-centered data and demonstrate that our method improves both the stability of point map reconstruction and the visual quality of free-viewpoint rendering.

2025-11-27T18:58:54Z Accepted by AAAI 2026. Project page: https://yaourtb.github.io/Splat-SAP Boyao Zhou Shunyuan Zheng Zhanfeng Liao Zihan Ma Hanzhang Tu Boning Liu Yebin Liu http://arxiv.org/abs/2510.23929v1 2025-10-27T23:28:11Z

We introduce TurboPortrait3D: a method for low-latency novel-view synthesis of human portraits. Our approach builds on the observation that existing image-to-3D models for portrait generation, while capable of producing renderable 3D representations, are prone to visual artifacts, often lack of detail, and tend to fail at fully preserving the identity of the subject. On the other hand, image diffusion models excel at generating high-quality images, but besides being computationally expensive, are not grounded in 3D and thus are not directly capable of producing multi-view consistent outputs. In this work, we demonstrate that image-space diffusion models can be used to significantly enhance the quality of existing image-to-avatar methods, while maintaining 3D-awareness and running with low-latency. Our method takes a single frontal image of a subject as input, and applies a feedforward image-to-avatar generation pipeline to obtain an initial 3D representation and corresponding noisy renders. These noisy renders are then fed to a single-step diffusion model which is conditioned on input image(s), and is specifically trained to refine the renders in a multi-view consistent way. Moreover, we introduce a novel effective training strategy that includes pre-training on a large corpus of synthetic multi-view data, followed by fine-tuning on high-quality real images. We demonstrate that our approach both qualitatively and quantitatively outperforms current state-of-the-art for portrait novel-view synthesis, while being efficient in time.

2025-10-27T23:28:11Z Emily Kim Julieta Martinez Timur Bagautdinov Jessica Hodgins http://arxiv.org/abs/2510.13454v2 2026-03-05T09:57:15Z

The rapid progress of large, pretrained models for both visual content generation and 3D reconstruction opens up new possibilities for text-to-3D generation. Intuitively, one could obtain a formidable 3D scene generator if one were able to combine the power of a modern latent text-to-video model as "generator" with the geometric abilities of a recent (feedforward) 3D reconstruction system as "decoder". We introduce VIST3A, a general framework that does just that, addressing two main challenges. First, the two components must be joined in a way that preserves the rich knowledge encoded in their weights. We revisit model stitching, i.e., we identify the layer in the 3D decoder that best matches the latent representation produced by the text-to-video generator and stitch the two parts together. That operation requires only a small dataset and no labels. Second, the text-to-video generator must be aligned with the stitched 3D decoder, to ensure that the generated latents are decodable into consistent, perceptually convincing 3D scene geometry. To that end, we adapt direct reward finetuning, a popular technique for human preference alignment. We evaluate the proposed VIST3A approach with different video generators and 3D reconstruction models. All tested pairings markedly improve over prior text-to-3D models that output Gaussian splats. Moreover, by choosing a suitable 3D base model, VIST3A also enables high-quality text-to-pointmap generation.

2025-10-15T11:55:08Z ICLR 2026 (Oral), Project page: https://gohyojun15.github.io/VIST3A/ Hyojun Go Dominik Narnhofer Goutam Bhat Prune Truong Federico Tombari Konrad Schindler http://arxiv.org/abs/2509.26621v1 2025-09-30T17:56:02Z

We introduce HART, a unified framework for sparse-view human reconstruction. Given a small set of uncalibrated RGB images of a person as input, it outputs a watertight clothed mesh, the aligned SMPL-X body mesh, and a Gaussian-splat representation for photorealistic novel-view rendering. Prior methods for clothed human reconstruction either optimize parametric templates, which overlook loose garments and human-object interactions, or train implicit functions under simplified camera assumptions, limiting applicability in real scenes. In contrast, HART predicts per-pixel 3D point maps, normals, and body correspondences, and employs an occlusion-aware Poisson reconstruction to recover complete geometry, even in self-occluded regions. These predictions also align with a parametric SMPL-X body model, ensuring that reconstructed geometry remains consistent with human structure while capturing loose clothing and interactions. These human-aligned meshes initialize Gaussian splats to further enable sparse-view rendering. While trained on only 2.3K synthetic scans, HART achieves state-of-the-art results: Chamfer Distance improves by 18-23 percent for clothed-mesh reconstruction, PA-V2V drops by 6-27 percent for SMPL-X estimation, LPIPS decreases by 15-27 percent for novel-view synthesis on a wide range of datasets. These results suggest that feed-forward transformers can serve as a scalable model for robust human reconstruction in real-world settings. Code and models will be released.

2025-09-30T17:56:02Z Project page: https://xiyichen.github.io/hart Xiyi Chen Shaofei Wang Marko Mihajlovic Taewon Kang Sergey Prokudin Ming Lin http://arxiv.org/abs/2509.25603v1 2025-09-29T23:58:49Z

We perceive our surroundings with an active focus, paying more attention to regions of interest, such as the shelf labels in a grocery store. When it comes to scene reconstruction, this human perception trait calls for spatially varying degrees of detail ready for closer inspection in critical regions, preferably reconstructed on demand. While recent works in 3D Gaussian Splatting (3DGS) achieve fast, generalizable reconstruction from sparse views, their uniform resolution output leads to high computational costs unscalable to high-resolution training. As a result, they cannot leverage available images at their original high resolution to reconstruct details. Per-scene optimization methods reconstruct finer details with adaptive density control, yet require dense observations and lengthy offline optimization. To bridge the gap between the prohibitive cost of high-resolution holistic reconstructions and the user needs for localized fine details, we propose the problem of localized high-resolution reconstruction via on-demand Gaussian densification. Given a low-resolution 3DGS reconstruction, the goal is to learn a generalizable network that densifies the initial 3DGS to capture fine details in a user-specified local region of interest (RoI), based on sparse high-resolution observations of the RoI. This formulation avoids the high cost and redundancy of uniformly high-resolution reconstructions and fully leverages high-resolution captures in critical regions. We propose GaussianLens, a feed-forward densification framework that fuses multi-modal information from the initial 3DGS and multi-view images. We further design a pixel-guided densification mechanism that effectively captures details under large resolution increases. Experiments demonstrate our method's superior performance in local fine detail reconstruction and strong scalability to images of up to $1024\times1024$ resolution.

2025-09-29T23:58:49Z Yijia Weng Zhicheng Wang Songyou Peng Saining Xie Howard Zhou Leonidas J. Guibas http://arxiv.org/abs/2509.24209v2 2026-08-26T07:59:05Z

Instant reconstruction of dynamic 3D humans from uncalibrated sparse-view videos is critical for numerous downstream applications. Existing methods, however, are either limited by the slow reconstruction speeds or incapable of generating novel-time representations. To address these challenges, we propose Forge4D, a feed-forward 4D human reconstruction and interpolation model that efficiently reconstructs temporally aligned representations from uncalibrated sparse-view videos, enabling both novel view and novel time synthesis. Our model simplifies the 4D reconstruction and interpolation problem as a joint task of streaming 3D Gaussian reconstruction and dense motion prediction. For the task of streaming 3D Gaussian reconstruction, we first reconstruct static 3D Gaussians from uncalibrated sparse-view images and then introduce learnable state tokens to enforce temporal consistency in a memory-friendly manner by interactively updating shared information across different timestamps. For novel time synthesis, we design a novel motion prediction module to predict dense motions for each 3D Gaussian between two adjacent frames, coupled with an occlusion-aware Gaussian fusion process to interpolate 3D Gaussians at arbitrary timestamps. To overcome the lack of the ground truth for dense motion supervision, we formulate dense motion prediction as a dense point matching task and introduce a self-supervised retargeting loss to optimize this module. An additional occlusion-aware optical flow loss is introduced to ensure motion consistency with plausible human movement, providing stronger regularization. Extensive experiments demonstrate the effectiveness of our model on both in-domain and out-of-domain datasets. Project page and code at: https://zhenliuzju.github.io/huyingdong/Forge4D.

2025-09-29T02:47:14Z Yingdong Hu Yisheng He Jinnan Chen Weihao Yuan Kejie Qiu Zehong Lin Siyu Zhu Zilong Dong Steven Hoi Jun Zhang http://arxiv.org/abs/2509.02466v1 2025-09-02T16:20:20Z

In this paper, we rethink text-to-avatar generative models by proposing TeRA, a more efficient and effective framework than the previous SDS-based models and general large 3D generative models. Our approach employs a two-stage training strategy for learning a native 3D avatar generative model. Initially, we distill a decoder to derive a structured latent space from a large human reconstruction model. Subsequently, a text-controlled latent diffusion model is trained to generate photorealistic 3D human avatars within this latent space. TeRA enhances the model performance by eliminating slow iterative optimization and enables text-based partial customization through a structured 3D human representation. Experiments have proven our approach's superiority over previous text-to-avatar generative models in subjective and objective evaluation.

2025-09-02T16:20:20Z Accepted by ICCV2025 Yanwen Wang Yiyu Zhuang Jiawei Zhang Li Wang Yifei Zeng Xun Cao Xinxin Zuo Hao Zhu http://arxiv.org/abs/2508.19688v1 2025-08-27T08:52:35Z

Monocular texture 3D human reconstruction aims to create a complete 3D digital avatar from just a single front-view human RGB image. However, the geometric ambiguity inherent in a single 2D image and the scarcity of 3D human training data are the main obstacles limiting progress in this field. To address these issues, current methods employ prior geometric estimation networks to derive various human geometric forms, such as the SMPL model and normal maps. However, they struggle to integrate these modalities effectively, leading to view inconsistencies, such as facial distortions. To this end, we propose a two-process 3D human reconstruction framework, SAT, which seamlessly learns various prior geometries in a unified manner and reconstructs high-quality textured 3D avatars as the final output. To further facilitate geometry learning, we introduce a Supervisor Feature Regularization module. By employing a multi-view network with the same structure to provide intermediate features as training supervision, these varied geometric priors can be better fused. To tackle data scarcity and further improve reconstruction quality, we also propose an Online Animation Augmentation module. By building a one-feed-forward animation network, we augment a massive number of samples from the original 3D human data online for model training. Extensive experiments on two benchmarks show the superiority of our approach compared to state-of-the-art methods.

2025-08-27T08:52:35Z 10 pages, 8 figures Gangjian Zhang Jian Shu Nanjie Yao Hao Wang http://arxiv.org/abs/2508.17437v2 2025-08-26T16:57:07Z

Inferring the physical properties of 3D scenes from visual information is a critical yet challenging task for creating interactive and realistic virtual worlds. While humans intuitively grasp material characteristics such as elasticity or stiffness, existing methods often rely on slow, per-scene optimization, limiting their generalizability and application. To address this problem, we introduce PIXIE, a novel method that trains a generalizable neural network to predict physical properties across multiple scenes from 3D visual features purely using supervised losses. Once trained, our feed-forward network can perform fast inference of plausible material fields, which coupled with a learned static scene representation like Gaussian Splatting enables realistic physics simulation under external forces. To facilitate this research, we also collected PIXIEVERSE, one of the largest known datasets of paired 3D assets and physic material annotations. Extensive evaluations demonstrate that PIXIE is about 1.46-4.39x better and orders of magnitude faster than test-time optimization methods. By leveraging pretrained visual features like CLIP, our method can also zero-shot generalize to real-world scenes despite only ever been trained on synthetic data. https://pixie-3d.github.io/

2025-08-20T19:24:04Z Website: https://pixie-3d.github.io/ Long Le Ryan Lucas Chen Wang Chuhao Chen Dinesh Jayaraman Eric Eaton Lingjie Liu http://arxiv.org/abs/2508.14892v1 2025-08-20T17:59:11Z

Reconstructing 3D human bodies from sparse views has been an appealing topic, which is crucial to broader the related applications. In this paper, we propose a quite challenging but valuable task to reconstruct the human body from only two images, i.e., the front and back view, which can largely lower the barrier for users to create their own 3D digital humans. The main challenges lie in the difficulty of building 3D consistency and recovering missing information from the highly sparse input. We redesign a geometry reconstruction model based on foundation reconstruction models to predict consistent point clouds even input images have scarce overlaps with extensive human data training. Furthermore, an enhancement algorithm is applied to supplement the missing color information, and then the complete human point clouds with colors can be obtained, which are directly transformed into 3D Gaussians for better rendering quality. Experiments show that our method can reconstruct the entire human in 190 ms on a single NVIDIA RTX 4090, with two images at a resolution of 1024x1024, demonstrating state-of-the-art performance on the THuman2.0 and cross-domain datasets. Additionally, our method can complete human reconstruction even with images captured by low-cost mobile devices, reducing the requirements for data collection. Demos and code are available at https://hustvl.github.io/Snap-Snap/.

2025-08-20T17:59:11Z Project page: https://hustvl.github.io/Snap-Snap/ Jia Lu Taoran Yi Jiemin Fang Chen Yang Chuiyun Wu Wei Shen Wenyu Liu Qi Tian Xinggang Wang http://arxiv.org/abs/2508.09876v1 2025-08-13T15:18:21Z

Exoskeletons have been shown to effectively assist humans during steady locomotion. However, their effects on non-steady locomotion, characterized by nonlinear phase progression within a gait cycle, remain insufficiently explored, particularly across diverse activities. This work presents a shank angle-based control system that enables the exoskeleton to maintain real-time coordination with human gait, even under phase perturbations, while dynamically shaping assistance profiles to match the biological ankle moment patterns across walking, running, stair negotiation tasks. The control system consists of an assistance profile online generation method and a model-based feedforward control method. The assistance profile is formulated as a dual-Gaussian model with the shank angle as the independent variable. Leveraging only IMU measurements, the model parameters are updated online each stride to adapt to inter- and intra-individual biomechanical variability. The profile tracking control employs a human-exoskeleton kinematics and stiffness model as a feedforward component, reducing reliance on historical control data due to the lack of clear and consistent periodicity in non-steady locomotion. Three experiments were conducted using a lightweight soft exoskeleton with multiple subjects. The results validated the effectiveness of each individual method, demonstrated the robustness of the control system against gait perturbations across various activities, and revealed positive biomechanical and physiological responses of human users to the exoskeleton's mechanical assistance.

2025-08-13T15:18:21Z 49 pages, 20 figures, 4 tables IEEE Transactions on Automation Science and Engineering, 2026 Xiaowei Tan Weizhong Jiang Bi Zhang Wanxin Chen Yiwen Zhao Ning Li Lianqing Liu Xingang Zhao 10.1109/TASE.2026.3710825 http://arxiv.org/abs/2507.18758v1 2025-07-24T19:18:59Z

Modeling animatable human avatars from videos is a long-standing and challenging problem. While conventional methods require per-instance optimization, recent feed-forward methods have been proposed to generate 3D Gaussians with a learnable network. However, these methods predict Gaussians for each frame independently, without fully capturing the relations of Gaussians from different timestamps. To address this, we propose Human Gaussian Graph to model the connection between predicted Gaussians and human SMPL mesh, so that we can leverage information from all frames to recover an animatable human representation. Specifically, the Human Gaussian Graph contains dual layers where Gaussians are the first layer nodes and mesh vertices serve as the second layer nodes. Based on this structure, we further propose the intra-node operation to aggregate various Gaussians connected to one mesh vertex, and inter-node operation to support message passing among mesh node neighbors. Experimental results on novel view synthesis and novel pose animation demonstrate the efficiency and generalization of our method.

2025-07-24T19:18:59Z Yifan Liu Shengjun Zhang Chensheng Dai Yang Chen Hao Liu Chen Li Yueqi Duan http://arxiv.org/abs/2507.14501v5 2025-12-21T13:54:53Z

3D reconstruction and view synthesis are foundational problems in computer vision, graphics, and immersive technologies such as augmented reality (AR), virtual reality (VR), and digital twins. Traditional methods rely on computationally intensive iterative optimization in a complex chain, limiting their applicability in real-world scenarios. Recent advances in feed-forward approaches, driven by deep learning, have revolutionized this field by enabling fast and generalizable 3D reconstruction and view synthesis. This survey offers a comprehensive review of feed-forward techniques for 3D reconstruction and view synthesis, with a taxonomy according to the underlying representation architectures including point cloud, 3D Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), etc. We examine key tasks such as pose-free reconstruction, dynamic 3D reconstruction, and 3D-aware image and video synthesis, highlighting their applications in digital humans, SLAM, robotics, and beyond. In addition, we review commonly used datasets with detailed statistics, along with evaluation protocols for various downstream tasks. We conclude by discussing open research challenges and promising directions for future work, emphasizing the potential of feed-forward approaches to advance the state of the art in 3D vision.

2025-07-19T06:13:25Z A project page associated with this survey is available at https://fnzhan.com/projects/Feed-Forward-3D Jiahui Zhang Yuelei Li Anpei Chen Muyu Xu Kunhao Liu Jianyuan Wang Xiao-Xiao Long Hanxue Liang Zexiang Xu Hao Su Christian Theobalt Christian Rupprecht Andrea Vedaldi Kaichen Zhou Hanspeter Pfister Paul Pu Liang Shijian Lu Fangneng Zhan http://arxiv.org/abs/2506.13766v2 2026-03-16T17:28:33Z

Reconstructing animatable 3D humans from casually captured images of articulated subjects without camera or pose information is highly practical but remains challenging due to view misalignment, occlusions, and the absence of structural priors. In this work, we present LHM++, an efficient large-scale human reconstruction model that generates high-quality, animatable 3D avatars within seconds from one or multiple pose-free images. At its core is an Encoder-Decoder Point-Image Transformer architecture that progressively encodes and decodes 3D geometric point features to improve efficiency, while fusing hierarchical 3D point features with image features through multimodal attention. The fused features are decoded into 3D Gaussian splats to recover detailed geometry and appearance. To further enhance visual fidelity, we introduce a lightweight 3D-aware neural animation renderer that refines the rendering quality of reconstructed avatars in real time. Extensive experiments show that our method produces high-fidelity, animatable 3D humans without requiring camera or pose annotations. Our code and project page are available at https://lingtengqiu.github.io/LHM++/

2025-06-16T17:59:56Z HomePage: https://lingtengqiu.github.io/LHM++/ Online Demo: https://huggingface.co/spaces/Lingteng/LHMPP Lingteng Qiu Peihao Li Heyuan Li Qi Zuo Xiaodong Gu Yuan Dong Weihao Yuan Rui Peng Siyu Zhu Xiaoguang Han Guanying Chen Zilong Dong http://arxiv.org/abs/2506.12793v1 2025-06-15T09:49:15Z

Single-view textured human reconstruction aims to reconstruct a clothed 3D digital human by inputting a monocular 2D image. Existing approaches include feed-forward methods, limited by scarce 3D human data, and diffusion-based methods, prone to erroneous 2D hallucinations. To address these issues, we propose a novel SMPL normal map Equipped 3D Human Reconstruction (SEHR) framework, integrating a pretrained large 3D reconstruction model with human geometry prior. SEHR performs single-view human reconstruction without using a preset diffusion model in one forward propagation. Concretely, SEHR consists of two key components: SMPL Normal Map Guidance (SNMG) and SMPL Normal Map Constraint (SNMC). SNMG incorporates SMPL normal maps into an auxiliary network to provide improved body shape guidance. SNMC enhances invisible body parts by constraining the model to predict an extra SMPL normal Gaussians. Extensive experiments on two benchmark datasets demonstrate that SEHR outperforms existing state-of-the-art methods.

2025-06-15T09:49:15Z Accepted to ICME 2025 (Oral) Wenhao Shen Gangjian Zhang Jianfeng Zhang Yu Feng Nanjie Yao Xuanmeng Zhang Hao Wang http://arxiv.org/abs/2506.05011v1 2025-06-05T13:21:09Z

Despite significant advancements in dynamic neural rendering, existing methods fail to address the unique challenges posed by UAV-captured scenarios, particularly those involving monocular camera setups, top-down perspective, and multiple small, moving humans, which are not adequately represented in existing datasets. In this work, we introduce UAV4D, a framework for enabling photorealistic rendering for dynamic real-world scenes captured by UAVs. Specifically, we address the challenge of reconstructing dynamic scenes with multiple moving pedestrians from monocular video data without the need for additional sensors. We use a combination of a 3D foundation model and a human mesh reconstruction model to reconstruct both the scene background and humans. We propose a novel approach to resolve the scene scale ambiguity and place both humans and the scene in world coordinates by identifying human-scene contact points. Additionally, we exploit the SMPL model and background mesh to initialize Gaussian splats, enabling holistic scene rendering. We evaluated our method on three complex UAV-captured datasets: VisDrone, Manipal-UAV, and Okutama-Action, each with distinct characteristics and 10~50 humans. Our results demonstrate the benefits of our approach over existing methods in novel view synthesis, achieving a 1.5 dB PSNR improvement and superior visual sharpness.

2025-06-05T13:21:09Z Jaehoon Choi Dongki Jung Christopher Maxey Yonghan Lee Sungmin Eum Dinesh Manocha Heesung Kwon http://arxiv.org/abs/2505.21502v2 2025-11-21T06:23:38Z

We propose GRGS, a generalizable and relightable 3D Gaussian framework for high-fidelity human novel view synthesis under diverse lighting conditions. Unlike existing methods that rely on per-character optimization or ignore physical constraints, GRGS adopts a feed-forward, fully supervised strategy projecting geometry, material, and illumination cues from multi-view 2D observations into 3D Gaussian representations. To recover accurate geometry under diverse lighting conditions, we introduce a Lighting-robust Geometry Refinement (LGR) module trained on synthetically relit data to predict precise depth and surface normals. Based on the high-quality geometry, a Physically Grounded Neural Rendering (PGNR) module is further proposed to integrate neural prediction with physics-based shading, supporting editable relighting with shadows and indirect illumination. Moreover, we design a 2D-to-3D projection training scheme leveraging differentiable supervision from ambient occlusion, direct, and indirect lighting maps, alleviating the computational cost of ray tracing. Extensive experiments demonstrate that GRGS achieves superior visual quality, geometric consistency, and generalization across characters and lighting conditions.

2025-05-27T17:59:47Z Project Webpage: https://sypj-98.github.io/grgs/ Yipengjing Sun Shengping Zhang Chenyang Wang Shunyuan Zheng Zonglin Li Xiangyang Ji http://arxiv.org/abs/2504.06982v1 2025-04-09T15:38:18Z

3D human digitization has long been a highly pursued yet challenging task. Existing methods aim to generate high-quality 3D digital humans from single or multiple views, but remain primarily constrained by current paradigms and the scarcity of 3D human assets. Specifically, recent approaches fall into several paradigms: optimization-based and feed-forward (both single-view regression and multi-view generation with reconstruction). However, they are limited by slow speed, low quality, cascade reasoning, and ambiguity in mapping low-dimensional planes to high-dimensional space due to occlusion and invisibility, respectively. Furthermore, existing 3D human assets remain small-scale, insufficient for large-scale training. To address these challenges, we propose a latent space generation paradigm for 3D human digitization, which involves compressing multi-view images into Gaussians via a UV-structured VAE, along with DiT-based conditional generation, we transform the ill-posed low-to-high-dimensional mapping problem into a learnable distribution shift, which also supports end-to-end inference. In addition, we employ the multi-view optimization approach combined with synthetic data to construct the HGS-1M dataset, which contains $1$ million 3D Gaussian assets to support the large-scale training. Experimental results demonstrate that our paradigm, powered by large-scale training, produces high-quality 3D human Gaussians with intricate textures, facial details, and loose clothing deformation.

2025-04-09T15:38:18Z project page:https://yyvhang.github.io/SIGMAN_3D/ Yuhang Yang Fengqi Liu Yixing Lu Qin Zhao Pingyu Wu Wei Zhai Ran Yi Yang Cao Lizhuang Ma Zheng-Jun Zha Junting Dong http://arxiv.org/abs/2504.03536v2 2025-11-12T12:58:15Z

Single-image human reconstruction is vital for digital human modeling applications but remains an extremely challenging task. Current approaches rely on generative models to synthesize multi-view images for subsequent 3D reconstruction and animation. However, directly generating multiple views from a single human image suffers from geometric inconsistencies, resulting in issues like fragmented or blurred limbs in the reconstructed models. To tackle these limitations, we introduce \textbf{HumanDreamer-X}, a novel framework that integrates multi-view human generation and reconstruction into a unified pipeline, which significantly enhances the geometric consistency and visual fidelity of the reconstructed 3D models. In this framework, 3D Gaussian Splatting serves as an explicit 3D representation to provide initial geometry and appearance priority. Building upon this foundation, \textbf{HumanFixer} is trained to restore 3DGS renderings, which guarantee photorealistic results. Furthermore, we delve into the inherent challenges associated with attention mechanisms in multi-view human generation, and propose an attention modulation strategy that effectively enhances geometric details identity consistency across multi-view. Experimental results demonstrate that our approach markedly improves generation and reconstruction PSNR quality metrics by 16.45% and 12.65%, respectively, achieving a PSNR of up to 25.62 dB, while also showing generalization capabilities on in-the-wild data and applicability to various human reconstruction backbone models.

2025-04-04T15:35:14Z Project Page: https://humandreamer-x.github.io/ Boyuan Wang Runqi Ouyang Xiaofeng Wang Zheng Zhu Guosheng Zhao Chaojun Ni Xiaopei Zhang Guan Huang Yijie Ren Lihong Liu Xingang Wang http://arxiv.org/abs/2503.19207v2 2025-04-04T08:17:08Z

We present a novel method for reconstructing personalized 3D human avatars with realistic animation from only a few images. Due to the large variations in body shapes, poses, and cloth types, existing methods mostly require hours of per-subject optimization during inference, which limits their practical applications. In contrast, we learn a universal prior from over a thousand clothed humans to achieve instant feedforward generation and zero-shot generalization. Specifically, instead of rigging the avatar with shared skinning weights, we jointly infer personalized avatar shape, skinning weights, and pose-dependent deformations, which effectively improves overall geometric fidelity and reduces deformation artifacts. Moreover, to normalize pose variations and resolve coupled ambiguity between canonical shapes and skinning weights, we design a 3D canonicalization process to produce pixel-aligned initial conditions, which helps to reconstruct fine-grained geometric details. We then propose a multi-frame feature aggregation to robustly reduce artifacts introduced in canonicalization and fuse a plausible avatar preserving person-specific identities. Finally, we train the model in an end-to-end framework on a large-scale capture dataset, which contains diverse human subjects paired with high-quality 3D scans. Extensive experiments show that our method generates more authentic reconstruction and animation than state-of-the-arts, and can be directly generalized to inputs from casually taken phone photos. Project page and code is available at https://github.com/rongakowang/FRESA.

2025-03-24T23:20:47Z Published in CVPR 2025 Rong Wang Fabian Prada Ziyan Wang Zhongshi Jiang Chengxiang Yin Junxuan Li Shunsuke Saito Igor Santesteban Javier Romero Rohan Joshi Hongdong Li Jason Saragih Yaser Sheikh http://arxiv.org/abs/2503.15671v2 2025-10-17T06:30:11Z

Reconstructing clothed humans from a single image is a fundamental task in computer vision with wide-ranging applications. Although existing monocular clothed human reconstruction solutions have shown promising results, they often rely on the assumption that the human subject is in an occlusion-free environment. Thus, when encountering in-the-wild occluded images, these algorithms produce multiview inconsistent and fragmented reconstructions. Additionally, most algorithms for monocular 3D human reconstruction leverage geometric priors such as SMPL annotations for training and inference, which are extremely challenging to acquire in real-world applications. To address these limitations, we propose CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-ConsistEncy from a Single Image, a novel pipeline designed to reconstruct occlusion-resilient 3D humans with multiview consistency from a single occluded image, without requiring either ground-truth geometric prior annotations or 3D supervision. Specifically, CHROME leverages a multiview diffusion model to first synthesize occlusion-free human images from the occluded input, compatible with off-the-shelf pose control to explicitly enforce cross-view consistency during synthesis. A 3D reconstruction model is then trained to predict a set of 3D Gaussians conditioned on both the occluded input and synthesized views, aligning cross-view details to produce a cohesive and accurate 3D representation. CHROME achieves significant improvements in terms of both novel view synthesis (upto 3 db PSNR) and geometric reconstruction under challenging conditions.

2025-03-19T19:56:18Z Accepted at ICCV 2025 Arindam Dutta Meng Zheng Zhongpai Gao Benjamin Planche Anwesha Choudhuri Terrence Chen Amit K. Roy-Chowdhury Ziyan Wu http://arxiv.org/abs/2503.15297v1 2025-03-19T15:18:05Z

With the emergence of new application areas such as cyber-physical systems and human-in-the-loop applications ensuring a specific level of end-to-end network latency with high reliability (e.g., 99.9%) is becoming increasingly critical. To align wireless links with these reliability requirements, it is essential to analyze and control network latency in terms of its full probability distribution. However, in a wireless link, the distribution may vary over time, making this task particularly challenging. We propose predicting the latency distribution using state-of-the-art data-driven techniques that leverage historical network information. Our approach tokenizes network state information and processes it using temporal deep-learning architectures-namely LSTM and Transformer models-to capture both short- and long-term delay dependencies. These models output parameters for a chosen parametric density via a mixture density network with Gaussian mixtures, yielding multi-step probabilistic forecasts of future delays. To validate our proposed approach, we implemented and tested these methods using a time-synchronized, SDR-based OpenAirInterface 5G testbed to collect and preprocess network-delay data. Our experiments show that the Transformer model achieves lower negative log-likelihood and mean absolute error than both LSTM and feed-forward baselines in challenging scenarios, while also providing insights into model complexity and training/inference overhead. This framework enables more informed decision-making for adaptive scheduling and resource allocation, paving the way toward enhanced QoS in evolving 5G and 6G networks.

2025-03-19T15:18:05Z Samie Mostafavi Gourav Prateek Sharma Ahmad Traboulsi James Gross http://arxiv.org/abs/2503.10625v1 2025-03-13T17:59:21Z

Animatable 3D human reconstruction from a single image is a challenging problem due to the ambiguity in decoupling geometry, appearance, and deformation. Recent advances in 3D human reconstruction mainly focus on static human modeling, and the reliance of using synthetic 3D scans for training limits their generalization ability. Conversely, optimization-based video methods achieve higher fidelity but demand controlled capture conditions and computationally intensive refinement processes. Motivated by the emergence of large reconstruction models for efficient static reconstruction, we propose LHM (Large Animatable Human Reconstruction Model) to infer high-fidelity avatars represented as 3D Gaussian splatting in a feed-forward pass. Our model leverages a multimodal transformer architecture to effectively encode the human body positional features and image features with attention mechanism, enabling detailed preservation of clothing geometry and texture. To further boost the face identity preservation and fine detail recovery, we propose a head feature pyramid encoding scheme to aggregate multi-scale features of the head regions. Extensive experiments demonstrate that our LHM generates plausible animatable human in seconds without post-processing for face and hands, outperforming existing methods in both reconstruction accuracy and generalization ability.

2025-03-13T17:59:21Z Project Page: https://lingtengqiu.github.io/LHM/ Lingteng Qiu Xiaodong Gu Peihao Li Qi Zuo Weichao Shen Junfei Zhang Kejie Qiu Weihao Yuan Guanying Chen Zilong Dong Liefeng Bo http://arxiv.org/abs/2502.20220v2 2025-09-15T15:25:04Z

Traditionally, creating photo-realistic 3D head avatars requires a studio-level multi-view capture setup and expensive optimization during test-time, limiting the use of digital human doubles to the VFX industry or offline renderings. To address this shortcoming, we present Avat3r, which regresses a high-quality and animatable 3D head avatar from just a few input images, vastly reducing compute requirements during inference. More specifically, we make Large Reconstruction Models animatable and learn a powerful prior over 3D human heads from a large multi-view video dataset. For better 3D head reconstructions, we employ position maps from DUSt3R and generalized feature maps from the human foundation model Sapiens. To animate the 3D head, our key discovery is that simple cross-attention to an expression code is already sufficient. Finally, we increase robustness by feeding input images with different expressions to our model during training, enabling the reconstruction of 3D head avatars from inconsistent inputs, e.g., an imperfect phone capture with accidental movement, or frames from a monocular video. We compare Avat3r with current state-of-the-art methods for few-input and single-input scenarios, and find that our method has a competitive advantage in both tasks. Finally, we demonstrate the wide applicability of our proposed model, creating 3D head avatars from images of different sources, smartphone captures, single images, and even out-of-domain inputs like antique busts. Project website: https://tobias-kirschstein.github.io/avat3r/

2025-02-27T16:00:11Z Project website: https://tobias-kirschstein.github.io/avat3r/, Video: https://youtu.be/P3zNVx15gYs Tobias Kirschstein Javier Romero Artem Sevastopolsky Matthias Nießner Shunsuke Saito http://arxiv.org/abs/2502.19441v1 2025-02-24T06:53:37Z

Recent advancements in Gaussian-based human body reconstruction have achieved notable success in creating animatable avatars. However, there are ongoing challenges to fully exploit the SMPL model's prior knowledge and enhance the visual fidelity of these models to achieve more refined avatar reconstructions. In this paper, we introduce AniGaussian which addresses the above issues with two insights. First, we propose an innovative pose guided deformation strategy that effectively constrains the dynamic Gaussian avatar with SMPL pose guidance, ensuring that the reconstructed model not only captures the detailed surface nuances but also maintains anatomical correctness across a wide range of motions. Second, we tackle the expressiveness limitations of Gaussian models in representing dynamic human bodies. We incorporate rigid-based priors from previous works to enhance the dynamic transform capabilities of the Gaussian model. Furthermore, we introduce a split-with-scale strategy that significantly improves geometry quality. The ablative study experiment demonstrates the effectiveness of our innovative model design. Through extensive comparisons with existing methods, AniGaussian demonstrates superior performance in both qualitative result and quantitative metrics.

2025-02-24T06:53:37Z 13pages, 14 figures. arXiv admin note: text overlap with arXiv:2401.09720 Mengtian Li Shengxiang Yao Chen Kai Zhifeng Xie Keyu Chen Yu-Gang Jiang http://arxiv.org/abs/2501.04631v2 2025-09-04T17:13:32Z

Clothed avatar generation has wide applications in virtual and augmented reality, filmmaking, and more. Previous methods have achieved success in generating diverse digital avatars, however, generating avatars with disentangled components (\eg, body, hair, and clothes) has long been a challenge. In this paper, we propose LayerAvatar, the first feed-forward diffusion-based method for generating component-disentangled clothed avatars. To achieve this, we first propose a layered UV feature plane representation, where components are distributed in different layers of the Gaussian-based UV feature plane with corresponding semantic labels. This representation supports high-resolution and real-time rendering, as well as expressive animation including controllable gestures and facial expressions. Based on the well-designed representation, we train a single-stage diffusion model and introduce constrain terms to address the severe occlusion problem of the innermost human body layer. Extensive experiments demonstrate the impressive performances of our method in generating disentangled clothed avatars, and we further explore its applications in component transfer. The project page is available at: https://olivia23333.github.io/LayerAvatar/

2025-01-08T17:27:27Z ICCV 2025 highlight, project page: https://olivia23333.github.io/LayerAvatar/ Weitian Zhang Yichao Yan Sijing Wu Manwen Liao Xiaokang Yang http://arxiv.org/abs/2412.14963v2 2025-03-25T03:48:17Z

Creating a high-fidelity, animatable 3D full-body avatar from a single image is a challenging task due to the diverse appearance and poses of humans and the limited availability of high-quality training data. To achieve fast and high-quality human reconstruction, this work rethinks the task from the perspectives of dataset, model, and representation. First, we introduce a large-scale HUman-centric GEnerated dataset, HuGe100K, consisting of 100K diverse, photorealistic sets of human images. Each set contains 24-view frames in specific human poses, generated using a pose-controllable image-to-multi-view model. Next, leveraging the diversity in views, poses, and appearances within HuGe100K, we develop a scalable feed-forward transformer model to predict a 3D human Gaussian representation in a uniform space from a given human image. This model is trained to disentangle human pose, body shape, clothing geometry, and texture. The estimated Gaussians can be animated without post-processing. We conduct comprehensive experiments to validate the effectiveness of the proposed dataset and method. Our model demonstrates the ability to efficiently reconstruct photorealistic humans at 1K resolution from a single input image using a single GPU instantly. Additionally, it seamlessly supports various applications, as well as shape and texture editing tasks. Project page: https://yiyuzhuang.github.io/IDOL/.

2024-12-19T15:43:05Z 22 pages, 16 figures, includes main content, supplementary materials, and references CVPR 2025 Yiyu Zhuang Jiaxi Lv Hao Wen Qing Shuai Ailing Zeng Hao Zhu Shifeng Chen Yujiu Yang Xun Cao Wei Liu http://arxiv.org/abs/2412.03103v1 2024-12-04T08:06:06Z

This paper investigates the research task of reconstructing the 3D clothed human body from a monocular image. Due to the inherent ambiguity of single-view input, existing approaches leverage pre-trained SMPL(-X) estimation models or generative models to provide auxiliary information for human reconstruction. However, these methods capture only the general human body geometry and overlook specific geometric details, leading to inaccurate skeleton reconstruction, incorrect joint positions, and unclear cloth wrinkles. In response to these issues, we propose a multi-level geometry learning framework. Technically, we design three key components: skeleton-level enhancement, joint-level augmentation, and wrinkle-level refinement modules. Specifically, we effectively integrate the projected 3D Fourier features into a Gaussian reconstruction model, introduce perturbations to improve joint depth estimation during training, and refine the human coarse wrinkles by resembling the de-noising process of diffusion model. Extensive quantitative and qualitative experiments on two out-of-distribution test sets show the superior performance of our approach compared to state-of-the-art (SOTA) methods.

2024-12-04T08:06:06Z Gangjian Zhang Nanjie Yao Shunsi Zhang Hanfeng Zhao Guoliang Pang Jian Shu Hao Wang http://arxiv.org/abs/2410.01425v2 2025-03-12T12:14:39Z

Feed-forward based 3D Gaussian Splatting methods have demonstrated exceptional capability in real-time novel view synthesis for human models. However, current approaches are confined to either dense viewpoint configurations or restricted image resolutions. These limitations hinder their flexibility in free-viewpoint rendering across a wide range of camera view angle discrepancies, and also restrict their ability to recover fine-grained human details in real time using commonly available GPUs. To address these challenges, we propose a novel pipeline named EVA-Gaussian for 3D human novel view synthesis across diverse multi-view camera settings. Specifically, we first design an Efficient Cross-View Attention (EVA) module to effectively fuse cross-view information under high resolution inputs and sparse view settings, while minimizing temporal and computational overhead. Additionally, we introduce a feature refinement mechianism to predict the attributes of the 3D Gaussians and assign a feature value to each Gaussian, enabling the correction of artifacts caused by geometric inaccuracies in position estimation and enhancing overall visual fidelity. Experimental results on the THuman2.0 and THumansit datasets showcase the superiority of EVA-Gaussian in rendering quality across diverse camera settings. Project page: https://zhenliuzju.github.io/huyingdong/EVA-Gaussian.

2024-10-02T11:23:08Z Yingdong Hu Zhening Liu Jiawei Shao Zehong Lin Jun Zhang http://arxiv.org/abs/2409.07984v1 2024-09-12T12:30:04Z

Feedforward monocular face capture methods seek to reconstruct posed faces from a single image of a person. Current state of the art approaches have the ability to regress parametric 3D face models in real-time across a wide range of identities, lighting conditions and poses by leveraging large image datasets of human faces. These methods however suffer from clear limitations in that the underlying parametric face model only provides a coarse estimation of the face shape, thereby limiting their practical applicability in tasks that require precise 3D reconstruction (aging, face swapping, digital make-up, ...). In this paper, we propose a method for high-precision 3D face capture taking advantage of a collection of unconstrained videos of a subject as prior information. Our proposal builds on a two stage approach. We start with the reconstruction of a detailed 3D face avatar of the person, capturing both precise geometry and appearance from a collection of videos. We then use the encoder from a pre-trained monocular face reconstruction method, substituting its decoder with our personalized model, and proceed with transfer learning on the video collection. Using our pre-estimated image formation model, we obtain a more precise self-supervision objective, enabling improved expression and pose alignment. This results in a trained encoder capable of efficiently regressing pose and expression parameters in real-time from previously unseen images, which combined with our personalized geometry model yields more accurate and high fidelity mesh inference. Through extensive qualitative and quantitative evaluation, we showcase the superiority of our final model as compared to state-of-the-art baselines, and demonstrate its generalization ability to unseen pose, expression and lighting.

2024-09-12T12:30:04Z SIGGRAPH Asia 2024 Conference Paper. Project page: https://kelianb.github.io/SPARK/ SIGGRAPH Asia 2024 Conference Papers (SA Conference Papers '24), December 3-6, 2024, Tokyo, Japan Kelian Baert Shrisha Bharadwaj Fabien Castan Benoit Maujean Marc Christie Victoria Abrevaya Adnane Boukhayma 10.1145/3680528.3687704 http://arxiv.org/abs/2407.12777v1 2024-07-17T17:56:30Z

Recent progress in neural rendering has brought forth pioneering methods, such as NeRF and Gaussian Splatting, which revolutionize view rendering across various domains like AR/VR, gaming, and content creation. While these methods excel at interpolating {\em within the training data}, the challenge of generalizing to new scenes and objects from very sparse views persists. Specifically, modeling 3D humans from sparse views presents formidable hurdles due to the inherent complexity of human geometry, resulting in inaccurate reconstructions of geometry and textures. To tackle this challenge, this paper leverages recent advancements in Gaussian Splatting and introduces a new method to learn generalizable human Gaussians that allows photorealistic and accurate view-rendering of a new human subject from a limited set of sparse views in a feed-forward manner. A pivotal innovation of our approach involves reformulating the learning of 3D Gaussian parameters into a regression process defined on the 2D UV space of a human template, which allows leveraging the strong geometry prior and the advantages of 2D convolutions. In addition, a multi-scaffold is proposed to effectively represent the offset details. Our method outperforms recent methods on both within-dataset generalization as well as cross-dataset generalization settings.

2024-07-17T17:56:30Z Youngjoong Kwon Baole Fang Yixing Lu Haoye Dong Cheng Zhang Francisco Vicente Carrasco Albert Mosella-Montoro Jianjin Xu Shingo Takagi Daeil Kim Aayush Prakash Fernando De la Torre http://arxiv.org/abs/2406.19811v2 2024-10-02T04:00:01Z

Human activities are inherently complex, often involving numerous object interactions. To better understand these activities, it is crucial to model their interactions with the environment captured through dynamic changes. The recent availability of affordable head-mounted cameras and egocentric data offers a more accessible and efficient means to understand human-object interactions in 3D environments. However, most existing methods for human activity modeling neglect the dynamic interactions with objects, resulting in only static representations. The few existing solutions often require inputs from multiple sources, including multi-camera setups, depth-sensing cameras, or kinesthetic sensors. To this end, we introduce EgoGaussian, the first method capable of simultaneously reconstructing 3D scenes and dynamically tracking 3D object motion from RGB egocentric input alone. We leverage the uniquely discrete nature of Gaussian Splatting and segment dynamic interactions from the background, with both having explicit representations. Our approach employs a clip-level online learning pipeline that leverages the dynamic nature of human activities, allowing us to reconstruct the temporal evolution of the scene in chronological order and track rigid object motion. EgoGaussian shows significant improvements in terms of both dynamic object and background reconstruction quality compared to the state-of-the-art. We also qualitatively demonstrate the high quality of the reconstructed models.

2024-06-28T10:39:36Z Daiwei Zhang Gengyan Li Jiajie Li Mickaël Bressieux Otmar Hilliges Marc Pollefeys Luc Van Gool Xi Wang http://arxiv.org/abs/2406.08475v2 2024-12-14T09:51:44Z

Creating realistic avatars from a single RGB image is an attractive yet challenging problem. Due to its ill-posed nature, recent works leverage powerful prior from 2D diffusion models pretrained on large datasets. Although 2D diffusion models demonstrate strong generalization capability, they cannot provide multi-view shape priors with guaranteed 3D consistency. We propose Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion. Our key insight is that 2D multi-view diffusion and 3D reconstruction models provide complementary information for each other, and by coupling them in a tight manner, we can fully leverage the potential of both models. We introduce a novel image-conditioned generative 3D Gaussian Splats reconstruction model that leverages the priors from 2D multi-view diffusion models, and provides an explicit 3D representation, which further guides the 2D reverse sampling process to have better 3D consistency. Experiments show that our proposed framework outperforms state-of-the-art methods and enables the creation of realistic avatars from a single RGB image, achieving high-fidelity in both geometry and appearance. Extensive ablations also validate the efficacy of our design, (1) multi-view 2D priors conditioning in generative 3D reconstruction and (2) consistency refinement of sampling trajectory via the explicit 3D representation. Our code and models will be released on https://yuxuan-xue.com/human-3diffusion.

2024-06-12T17:57:25Z Accepted to NeurIPS2024. Project Page: https://yuxuan-xue.com/human-3diffusion Yuxuan Xue Xianghui Xie Riccardo Marin Gerard Pons-Moll http://arxiv.org/abs/2406.06526v3 2025-02-27T05:39:54Z

3D city generation with NeRF-based methods shows promising generation results but is computationally inefficient. Recently 3D Gaussian Splatting (3D-GS) has emerged as a highly efficient alternative for object-level 3D generation. However, adapting 3D-GS from finite-scale 3D objects and humans to infinite-scale 3D cities is non-trivial. Unbounded 3D city generation entails significant storage overhead (out-of-memory issues), arising from the need to expand points to billions, often demanding hundreds of Gigabytes of VRAM for a city scene spanning 10km^2. In this paper, we propose GaussianCity, a generative Gaussian Splatting framework dedicated to efficiently synthesizing unbounded 3D cities with a single feed-forward pass. Our key insights are two-fold: 1) Compact 3D Scene Representation: We introduce BEV-Point as a highly compact intermediate representation, ensuring that the growth in VRAM usage for unbounded scenes remains constant, thus enabling unbounded city generation. 2) Spatial-aware Gaussian Attribute Decoder: We present spatial-aware BEV-Point decoder to produce 3D Gaussian attributes, which leverages Point Serializer to integrate the structural and contextual characteristics of BEV points. Extensive experiments demonstrate that GaussianCity achieves state-of-the-art results in both drone-view and street-view 3D city generation. Notably, compared to CityDreamer, GaussianCity exhibits superior performance with a speedup of 60 times (10.72 FPS v.s. 0.18 FPS).

2024-06-10T17:59:55Z CVPR 2025. Project Page: https://haozhexie.com/project/gaussian-city Haozhe Xie Zhaoxi Chen Fangzhou Hong Ziwei Liu http://arxiv.org/abs/2311.02191v1 2023-11-03T18:48:01Z

Accurate and reliable human motion reconstruction is crucial for creating natural interactions of full-body avatars in Virtual Reality (VR) and entertainment applications. As the Metaverse and social applications gain popularity, users are seeking cost-effective solutions to create full-body animations that are comparable in quality to those produced by commercial motion capture systems. In order to provide affordable solutions, though, it is important to minimize the number of sensors attached to the subject's body. Unfortunately, reconstructing the full-body pose from sparse data is a heavily under-determined problem. Some studies that use IMU sensors face challenges in reconstructing the pose due to positional drift and ambiguity of the poses. In recent years, some mainstream VR systems have released 6-degree-of-freedom (6-DoF) tracking devices providing positional and rotational information. Nevertheless, most solutions for reconstructing full-body poses rely on traditional inverse kinematics (IK) solutions, which often produce non-continuous and unnatural poses. In this article, we introduce SparsePoser, a novel deep learning-based solution for reconstructing a full-body pose from a reduced set of six tracking devices. Our system incorporates a convolutional-based autoencoder that synthesizes high-quality continuous human poses by learning the human motion manifold from motion capture data. Then, we employ a learned IK component, made of multiple lightweight feed-forward neural networks, to adjust the hands and feet toward the corresponding trackers. We extensively evaluate our method on publicly available motion capture datasets and with real-time live demos. We show that our method outperforms state-of-the-art techniques using IMU sensors or 6-DoF tracking devices, and can be used for users with different body dimensions and proportions.

2023-11-03T18:48:01Z Published in ACM TOG https://dl.acm.org/doi/10.1145/3625264 and presented in SIGGRAPH ASIA 2023 ACM Transactions on Graphics 2023 Jose Luis Ponton Haoran Yun Andreas Aristidou Carlos Andujar Nuria Pelechano 10.1145/3625264