https://arxiv.org/api/yv1+pSuVrcJz9tyjt1ydX51iL30 2026-09-06T21:17:59Z 30 78 0 http://arxiv.org/abs/2607.23840v1 2026-07-26T20:53:41Z

Facial movement and expression are central to face-to-face communication, conveying turn-taking, attention, agreement, and engagement alongside speech. While speech-driven facial animation has made strong progress in lip synchronization and audio-conditioned motion generation, most methods treat conversational behavior as an emergent byproduct of audio, or expose only coarse sequence-level affect control. As a result, key non-verbal channels such as gaze contact and aversion, rhythmic head motion, and emotion remain difficult to explicitly control. We present STEER, a controllable 3D dyadic motion prior for reactive conversational head avatars. STEER factorizes conversational behavior into explicit controls for gaze, head rhythm, and emotion, allowing users to steer how an avatar listens, reacts, and engages with a conversation partner. Since temporally aligned annotations for these behaviors are not available in public dyadic corpora, we introduce a tracking and annotation pipeline that recovers behavioral pseudo-labels from in-the-wild dyadic video. A causal flow-matching transformer then learns partner-aware target motion conditioned on audio, partner motion, emotion and the proposed behavioral controls. We further embed STEER in a photorealistic avatar pipeline by extending a Universal Gaussian Head-Avatar Prior with a learned mapping from tracked parametric motion into its avatar-driving space. This enables controllable animation of high-fidelity Gaussian head avatars without re-training the underlying avatar model. STEER outperforms recent dyadic motion baselines on motion quality, dynamics, and diversity, remains competitive on partner coupling, and enables gaze, head-rhythm, and emotion edits together with an interactive live deployment. We make our code and dataset annotations available at our webpage.

2026-07-26T20:53:41Z Project page: https://kartik-teotia.github.io/STEER/ Kartik Teotia Helge Rhodin Hyeongwoo Kim Marc Habermann Christian Theobalt http://arxiv.org/abs/2607.04341v1 2026-07-05T14:51:43Z

This state-of-the-art report provides an overview of controllable 3D human avatar creation. We describe current 3D avatar systems, which typically consist of three stages: (i) learning priors of human appearance and motion, (ii) creating a personalized avatar, and (iii) animating the avatar. To limit the scope, we focus on the prior learning and avatar creation stages. We define current avatar representations and introduce a taxonomy that categorizes existing work along multiple axes, including body regions and employed priors. We review methods for full-body and head avatars, as well as layered representations that decompose the body into components such as hands, hair, and garments. Finally, we outline common underlying principles, reference key literature for newcomers, and discuss open challenges and future research directions.

2026-07-05T14:51:43Z Eurographics 2026 State-of-the-Art Report (STAR). Project page: https://wojciechzielonka.com/how-to-build-digital-humans/ Wojciech Zielonka Tobias Kirschstein Timo Bolkart Simon Giebenhain Vanessa Sklyarova Xiang Deng Donglai Xiang Shunsuke Saito Yebin Liu Matthias Niessner Justus Thies 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/2604.27871v1 2026-04-30T13:53:03Z

We present D-Rex, a person-specific framework for photorealistic, relightable, expressive, and animatable full-body human avatars with free-viewpoint rendering. Existing methods for relightable full-body avatars rely on explicit 3D intrinsic decomposition with analytic reflectance models, which require accurate geometry registration and careful optimization to capture realistic light transport effects. This tight coupling of relighting with avatar modeling has hindered expressiveness: to our knowledge, no existing method demonstrates strong facial animation alongside relighting, limiting applicability in telepresence, gaming, and virtual production. We propose to decouple relighting entirely from avatar modeling by treating it as an image-space post-process: a learned translation from flat-lit, albedo-like renderings to a target HDR illumination. To this end, we leverage the strong generative prior of a pre-trained video diffusion relighting model, fine-tuned via LoRA on paired flat-lit and relit frames captured in a light stage. The flat-lit driving frames are produced by an independent expressive full-body avatar framework trained under white-light conditions, requiring no modification to support relighting, making D-Rex directly applicable to any white-light avatar system. We demonstrate that D-Rex enables view- and temporally consistent relighting while faithfully preserving expressive motion and fine-grained facial detail, outperforming physically-based relightable avatar baselines. Project page is https://vcai.mpi-inf.mpg.de/projects/DRex/

2026-04-30T13:53:03Z Timo Teufel Xilong Zhou Umar Iqbal Jan Kautz Marc Habermann Vladislav Golyanik Christian Theobalt http://arxiv.org/abs/2604.25466v1 2026-04-28T10:12:28Z

Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined structural representations to accurately position 3D Gaussians. Although these approaches have shown the remarkable progress in this field, they still suffer from inconsistent feature representations across multi-view inputs due to complex articulations of the human body and limited overlaps between different views. To address this problem, we propose a novel method to accurately localize 3D Gaussians and ultimately improve the quality of human rendering. The key idea is to unproject latent embeddings encoded from each viewpoint into a shared 3D space through predicted depth maps and recalibrate them belonging to the same body part based on cross-view attention. This helps the model resolve the spatial ambiguity occurring in highly textured regions as well as occluded body parts, thus leading to the accurate localization of 3D Gaussians. Experimental results on benchmark datasets show that the proposed method efficiently improves the performance of generalizable human Gaussian splatting from sparse-view inputs.

2026-04-28T10:12:28Z 10 pages, 8 figures, CVPR 2026 Findings Jingi Kim Wonjun Kim http://arxiv.org/abs/2604.25178v1 2026-04-28T03:37:24Z

Achieving a desirable balance between rendering quality and real-time performance is a long-standing challenge in modern game and rendering engines, particularly on resource-constrained mobile devices such as laptops, tablets, and smartphones. Existing approaches to automatic rendering parameter optimization either depend on exhaustive per-scene pre-computation that spans several days, suffer from the prohibitive inference overhead of neural networks that prevents per-frame adaptation, or lack generalizability across heterogeneous hardware and diverse scenes. In this paper, we propose \textbf{LUT-Opt}, a lightweight, general-purpose framework for adaptive per-frame rendering parameter optimization. Our method decomposes the joint optimization of rendering time and image quality into a tractable two-stage pipeline. In the offline stage, we train a pair of XGBoost regressors to predict rendering time and image quality from rendering parameters, hardware state, and scene complexity descriptors. The trained ensemble models are then distilled into compact lookup tables (LUTs) through systematic discretization and a two-phase linear search that first constrains rendering time and subsequently maximizes structural similarity (SSIM). During runtime, the pre-computed LUT is queried every frame in sub-millisecond time, enabling truly adaptive parameter selection with negligible computational overhead. We validate LUT-Opt on two representative rendering techniques -- subsurface scattering (SSS) and hybrid-pipeline ambient occlusion (AO) -- implemented within Unreal Engine 5. Extensive experiments across multiple scenes and GPU configurations demonstrate that LUT-Opt reduces subsurface scattering rendering time by approximately 40\% and ambient occlusion rendering time by roughly 70\%, while incurring only about 2\% increase in image quality error, with per-frame inference latency below 0.1\ ms.

2026-04-28T03:37:24Z Baijun Tan Francesco Moretti http://arxiv.org/abs/2603.29591v2 2026-06-24T15:07:02Z

Every day, many people die under violent circumstances, whether from crimes, war, migration, or climate disasters. Medico-legal and law enforcement institutions document many portraits of the deceased for evidence, but cannot immediately carry out identification on them. While traditional image editing tools can process these photos for public release, the workflow is lengthy and produces suboptimal results. In this work, we leverage advances in image generation models, which can now produce photorealistic human portraits, to introduce FlowID, an identity-preserving facial reconstruction method. Our approach combines single-image fine-tuning, which adapts the generative model to out-of-distribution injured faces, with attention-based masking that localizes edits to damaged regions while preserving identity-critical features. Together, these components enable the removal of artifacts from violent death while retaining sufficient identity information to support identification. To evaluate our method, we introduce InjuredFaces, a novel benchmark for identity-preserving facial reconstruction under severe facial damage. Beyond serving as an evaluation tool for this work, InjuredFaces provides a standardized resource for the community to study and compare methods addressing facial reconstruction in extreme conditions. Experimental results show that FlowID outperforms state-of-the-art open-source methods while maintaining low memory requirements, making it suitable for local deployment without compromising data privacy.

2026-03-31T11:12:01Z Jules Ripoll David Bertoin Alasdair Newson Charles Dossal Jose Pablo Baraybar http://arxiv.org/abs/2603.28763v2 2026-09-03T17:59:22Z

Acquiring labeled datasets for 3D human mesh estimation is challenging due to depth ambiguities and the inherent difficulty of annotating 3D geometry from monocular images. Existing datasets are either real, with manually annotated 3D geometry and limited scale, or synthetic, rendered from 3D engines that provide precise labels but suffer from limited photorealism, low diversity, and high production costs. In this work, we explore a third path: generated data. We introduce PoseDreamer, a novel pipeline that leverages diffusion models to generate large-scale synthetic datasets with 3D mesh annotations. Our approach combines controllable image generation with Direct Preference Optimization for control alignment, curriculum-based hard sample mining, and multi-stage quality filtering. Together, these components naturally maintain correspondence between 3D labels and generated images, while prioritizing challenging samples to maximize dataset utility. Using PoseDreamer, we generate more than 500,000 high-quality synthetic samples, achieving a 76% improvement in image-quality metrics compared to rendering-based datasets. Models trained on PoseDreamer achieve performance comparable to or superior to those trained on real-world and traditional synthetic datasets. In addition, combining PoseDreamer with synthetic datasets results in better performance than combining real-world and synthetic datasets, demonstrating the complementary nature of our dataset. We will release the full dataset and generation code.

2026-03-30T17:59:18Z Lorenza Prospero Orest Kupyn Ostap Viniavskyi João F. Henriques Christian Rupprecht http://arxiv.org/abs/2603.26934v1 2026-03-27T19:17:16Z

Recent advances in photorealistic avatar generation have enabled highly realistic talking-head avatars, raising security concerns regarding identity impersonation in AI-mediated communication. To advance in this challenging problem, the task of avatar fingerprinting aims to determine whether two avatar videos are driven by the same human operator or not. However, current public databases in the literature are scarce and based solely on old-fashioned talking-head avatar generators, not representing realistic scenarios for the current task of avatar fingerprinting. To overcome this situation, the present article introduces AVAPrintDB, a new publicly available multi-generator talking-head avatar database for avatar fingerprinting. AVAPrintDB is constructed from two audiovisual corpora and three state-of-the-art avatar generators (GAGAvatar, LivePortrait, HunyuanPortrait), representing different synthesis paradigms, and includes both self- and cross-reenactments to simulate legitimate usage and impersonation scenarios. Building on this database, we also define a standardized and reproducible benchmark for avatar fingerprinting, considering public state-of-the-art avatar fingerprinting systems and exploring novel methods based on Foundation Models (DINOv2 and CLIP). Also, we conduct a comprehensive analysis under generator and dataset shift. Our results show that, while identity-related motion cues persist across synthetic avatars, current avatar fingerprinting systems remain highly sensitive to changes in the synthesis pipeline and source domain. The AVAPrintDB, benchmark protocols, and avatar fingerprinting systems are publicly available to facilitate reproducible research.

2026-03-27T19:17:16Z Laura Pedrouzo-Rodriguez Luis F. Gomez Ruben Tolosana Ruben Vera-Rodriguez Roberto Daza Aythami Morales Julian Fierrez http://arxiv.org/abs/2603.22036v1 2026-03-23T14:38:18Z

Reconstructing translucent objects from multi-view images is a difficult problem. Previously, researchers have used differentiable path tracing and the neural implicit field, which require relatively large computational costs. Recently, many works have achieved good reconstruction results for opaque objects based on a 3DGS pipeline with much higher efficiency. However, such methods have difficulty dealing with translucent objects, because they do not consider the optical properties of translucent objects. In this paper, we propose a novel 3DGS-based pipeline (GTSR) to reconstruct the surface geometry of translucent objects. GTSR combines two sets of Gaussians, surface and interior Gaussians, which are used to model the surface and scattering color when lights pass translucent objects. To render the appearance of translucent objects, we introduce a method that uses the Fresnel term to blend two sets of Gaussians. Furthermore, to improve the reconstructed details of non-contour areas, we introduce the Disney BSDF model with deferred rendering to enhance constraints of the normal and depth. Experimental results demonstrate that our method outperforms baseline reconstruction methods on the NeuralTO Syn dataset while showing great real-time rendering performance. We also extend the dataset with new translucent objects of varying material properties and demonstrate our method can adapt to different translucent materials.

2026-03-23T14:38:18Z Youwen Yuan Xi Zhao http://arxiv.org/abs/2603.15433v1 2026-03-16T15:39:48Z

Photorealistic human novel view synthesis from a single image is crucial for democratizing immersive 3D telepresence, eliminating the need for complex multi-camera setups. However, current rendering-centric methods prioritize visual fidelity over explicit geometric understanding and struggle with intricate regions like faces and hands, leading to temporal instability. Meanwhile, human-centric frameworks suffer from memory bottlenecks since they typically rely on an auxiliary model to provide informative structural priors for geometric modeling, which limits real-time performance. To address these challenges, we propose PrismMirror, a geometry-guided framework for instant frontal view synthesis from a single image. By avoiding external geometric modeling and focusing on frontal view synthesis, our model optimizes visual integrity for telepresence. Specifically, PrismMirror introduces a novel cascade learning strategy that enables coarse-to-fine geometric feature learning. It first directly learns coarse geometric features, such as SMPL-X meshes and point clouds, and then refines textures through rendering supervision. To achieve real-time efficiency, we distill this unified framework into a lightweight linear attention model. Notably, PrismMirror is the first monocular human frontal view synthesis model that achieves real-time inference at 24 FPS, significantly outperforming previous methods in both visual authenticity and structural accuracy.

2026-03-16T15:39:48Z Fangyu Lin Yingdong Hu Lunjie Zhu Zhening Liu Yushi Huang Zehong Lin Jun Zhang http://arxiv.org/abs/2603.06057v1 2026-03-06T09:09:01Z

Diffusion models have recently advanced photorealistic human synthesis, although practical talking-head generation (THG) remains constrained by high inference latency, temporal instability such as flicker and identity drift, and imperfect audio-visual alignment under challenging speech conditions. This paper introduces TempoSyncDiff, a reference-conditioned latent diffusion framework that explores few-step inference for efficient audio-driven talking-head generation. The approach adopts a teacher-student distillation formulation in which a diffusion teacher trained with a standard noise prediction objective guides a lightweight student denoiser capable of operating with significantly fewer inference steps to improve generation stability. The framework incorporates identity anchoring and temporal regularization designed to mitigate identity drift and frame-to-frame flicker during synthesis, while viseme-based audio conditioning provides coarse lip motion control. Experiments on the LRS3 dataset report denoising-stage component-level metrics relative to VAE reconstructions and preliminary latency characterization, including CPU-only and edge computing measurements and feasibility estimates for edge deployment. The results suggest that distilled diffusion models can retain much of the reconstruction behaviour of a stronger teacher while enabling substantially lower latency inference. The study is positioned as an initial step toward practical diffusion-based talking-head generation under constrained computational settings. GitHub: https://mazumdarsoumya.github.io/TempoSyncDiff

2026-03-06T09:09:01Z Soumya Mazumdar Vineet Kumar Rakesh http://arxiv.org/abs/2603.04290v2 2026-03-05T15:37:00Z

We introduce Gaussian Wardrobe, a novel framework to digitalize compositional 3D neural avatars from multi-view videos. Existing methods for 3D neural avatars typically treat the human body and clothing as an inseparable entity. However, this paradigm fails to capture the dynamics of complex free-form garments and limits the reuse of clothing across different individuals. To overcome these problems, we develop a novel, compositional 3D Gaussian representation to build avatars from multiple layers of free-form garments. The core of our method is decomposing neural avatars into bodies and layers of shape-agnostic neural garments. To achieve this, our framework learns to disentangle each garment layer from multi-view videos and canonicalizes it into a shape-independent space. In experiments, our method models photorealistic avatars with high-fidelity dynamics, achieving new state-of-the-art performance on novel pose synthesis benchmarks. In addition, we demonstrate that the learned compositional garments contribute to a versatile digital wardrobe, enabling a practical virtual try-on application where clothing can be freely transferred to new subjects. Project page: https://ait.ethz.ch/gaussianwardrobe

2026-03-04T17:06:50Z 3DV 2026, 16 pages, 12 figures Zhiyi Chen Hsuan-I Ho Tianjian Jiang Jie Song Manuel Kaufmann Chen Guo http://arxiv.org/abs/2602.19350v1 2026-02-22T21:50:24Z

Digitizing humans and synthesizing photorealistic avatars with explicit 3D pose and camera controls are central to VR, telepresence, and entertainment. Existing skinning-based workflows require laborious manual rigging or template-based fittings, while neural volumetric methods rely on canonical templates and re-optimization for each unseen pose. We present PoseCraft, a diffusion framework built around tokenized 3D interface: instead of relying only on rasterized geometry as 2D control images, we encode sparse 3D landmarks and camera extrinsics as discrete conditioning tokens and inject them into diffusion via cross-attention. Our approach preserves 3D semantics by avoiding 2D re-projection ambiguity under large pose and viewpoint changes, and produces photorealistic imagery that faithfully captures identity and appearance. To train and evaluate at scale, we also implement GenHumanRF, a data generation workflow that renders diverse supervision from volumetric reconstructions. Our experiments show that PoseCraft achieves significant perceptual quality improvement over diffusion-centric methods, and attains better or comparable metrics to latest volumetric rendering SOTA while better preserving fabric and hair details.

2026-02-22T21:50:24Z Zhilin Guo Jing Yang Kyle Fogarty Jingyi Wan Boqiao Zhang Tianhao Wu Weihao Xia Chenliang Zhou Sakar Khattar Fangcheng Zhong Cristina Nader Vasconcelos Cengiz Oztireli http://arxiv.org/abs/2602.11575v3 2026-06-24T02:18:51Z

Visual navigation models often struggle in real-world dynamic environments due to limited robustness to the sim-to-real gap and the difficulty of training policies tailored to target deployment environments (e.g., households, restaurants, and factories). Although real-to-sim navigation simulation using 3D Gaussian Splatting (GS) can mitigate these challenges, prior GS-based works have considered only static scenes or non-photorealistic human obstacles built from simulator assets, despite the importance of safe navigation in dynamic environments. To address these issues, we propose ReaDy-Go, a novel real-to-sim simulation pipeline that synthesizes photorealistic dynamic scenarios in target environments by augmenting a reconstructed static GS scene with dynamic human GS obstacles, and trains navigation policies using the generated datasets. The pipeline provides three key contributions: (1) a dynamic GS simulator that integrates static scene GS with a human animation module, enabling the insertion of animatable human GS avatars and the synthesis of plausible human motions from 2D trajectories, (2) a navigation dataset generation framework that leverages the simulator along with a robot expert planner designed for dynamic GS representations and a human planner, and (3) robust navigation policies to both the sim-to-real gap and moving obstacles. The proposed simulator generates thousands of photorealistic navigation scenarios with animatable human GS avatars from arbitrary viewpoints. ReaDy-Go outperforms baselines across target environments in both simulation and real-world experiments, demonstrating improved navigation performance even after sim-to-real transfer and in the presence of moving obstacles. Moreover, zero-shot sim-to-real deployment in an unseen environment indicates its generalization potential. Project page: https://syeon-yoo.github.io/ready-go-site/.

2026-02-12T04:48:18Z Accepted by IEEE Robotics and Automation Letters (RA-L). Project page: https://syeon-yoo.github.io/ready-go-site/ Seungyeon Yoo Youngseok Jang Dabin Kim Youngsoo Han Seungwoo Jung H. Jin Kim 10.1109/LRA.2026.3707355 http://arxiv.org/abs/2602.01748v1 2026-02-02T07:34:15Z

We propose OFERA, a novel framework for real-time expression control of photorealistic Gaussian head avatars for VR headset users. Existing approaches attempt to recover occluded facial expressions using additional sensors or internal cameras, but sensor-based methods increase device weight and discomfort, while camera-based methods raise privacy concerns and suffer from limited access to raw data. To overcome these limitations, we leverage the blendshape signals provided by commercial VR headsets as expression inputs. Our framework consists of three key components: (1) Blendshape Distribution Alignment (BDA), which applies linear regression to align the headset-provided blendshape distribution to a canonical input space; (2) an Expression Parameter Mapper (EPM) that maps the aligned blendshape signals into an expression parameter space for controlling Gaussian head avatars; and (3) a Mapper-integrated Avatar (MiA) that incorporates EPM into the avatar learning process to ensure distributional consistency. Furthermore, OFERA establishes an end-to-end pipeline that senses and maps expressions, updates Gaussian avatars, and renders them in real-time within VR environments. We show that EPM outperforms existing mapping methods on quantitative metrics, and we demonstrate through a user study that the full OFERA framework enhances expression fidelity while preserving avatar realism. By enabling real-time and photorealistic avatar expression control, OFERA significantly improves telepresence in VR communication. A project page is available at https://ysshwan147.github.io/projects/ofera/.

2026-02-02T07:34:15Z Accepted as an IEEE TVCG paper at IEEE VR 2026 (journal track) Seokhwan Yang Boram Yoon Seoyoung Kang Hail Song Woontack Woo http://arxiv.org/abs/2602.01729v1 2026-02-02T07:11:44Z

This study explores a streamlined facial data collection method for conversational contexts, addressing the limitations of existing approaches that often require extensive datasets and prioritize technical metrics over user perception and experience. We systematically investigate which facial expression data are essential for reconstructing photorealistic avatars and how they can be captured efficiently. Our research employs a two-phase methodology to identify efficient facial data collection strategies and evaluate their effectiveness. In the first phase, we conduct facial data acquisition and evaluate reconstruction performance using utterance data and emotional data. In the second phase, we carry out a comprehensive user evaluation comparing three progressive conditions: utterance only, utterance and emotional data, and a control condition involving extensive data. Findings from 24 participants engaged in simulated face-to-face conversations reveal that targeted utterance and emotional data achieve comparable levels of perceived realism, naturalness, and telepresence, while reducing training time and data usage when compared to the extensive data collection approach. These results demonstrate that targeted data inputs can enable efficient avatar face reconstruction, offering practical guidelines for real-time applications such as AR/VR telepresence and highlighting the trade-off between data quantity and perceived quality.

2026-02-02T07:11:44Z Accepted as an IEEE TVCG paper at IEEE VR 2026 (journal track) Seoyoung Kang Seokhwan Yang Hail Song Boram Yoon Jinwook Kim Kangsoo Kim Woontack Woo http://arxiv.org/abs/2602.01661v2 2026-02-03T06:44:02Z

In this work, we focus on the challenge of temporally consistent human-centric dense prediction across video sequences. Existing models achieve strong per-frame accuracy but often flicker under motion, occlusion, and lighting changes, and they rarely have paired human video supervision for multiple dense tasks. We address this gap with a scalable synthetic data pipeline that generates photorealistic human frames and motion-aligned sequences with pixel-accurate depth, normals, and masks. Unlike prior static data synthetic pipelines, our pipeline provides both frame-level labels for spatial learning and sequence-level supervision for temporal learning. Building on this, we train a unified ViT-based dense predictor that (i) injects an explicit human geometric prior via CSE embeddings and (ii) improves geometry-feature reliability with a lightweight channel reweighting module after feature fusion. Our two-stage training strategy, combining static pretraining with dynamic sequence supervision, enables the model first to acquire robust spatial representations and then refine temporal consistency across motion-aligned sequences. Extensive experiments show that we achieve state-of-the-art performance on THuman2.1 and Hi4D and generalize effectively to in-the-wild videos.

2026-02-02T05:28:58Z Xingyu Miao Junting Dong Qin Zhao Yuhang Yang Junhao Chen Yang Long http://arxiv.org/abs/2601.04715v1 2026-01-08T08:33:22Z

The rapid advancement of AI-generated content (AIGC) has escalated the threat of deepfakes, from facial manipulations to the synthesis of entire photorealistic human bodies. However, existing detection methods remain fragmented, specializing either in facial-region forgeries or full-body synthetic images, and consequently fail to generalize across the full spectrum of human image manipulations. We introduce HuForDet, a holistic framework for human image forgery detection, which features a dual-branch architecture comprising: (1) a face forgery detection branch that employs heterogeneous experts operating in both RGB and frequency domains, including an adaptive Laplacian-of-Gaussian (LoG) module designed to capture artifacts ranging from fine-grained blending boundaries to coarse-scale texture irregularities; and (2) a contextualized forgery detection branch that leverages a Multi-Modal Large Language Model (MLLM) to analyze full-body semantic consistency, enhanced with a confidence estimation mechanism that dynamically weights its contribution during feature fusion. We curate a human image forgery (HuFor) dataset that unifies existing face forgery data with a new corpus of full-body synthetic humans. Extensive experiments show that our HuForDet achieves state-of-the-art forgery detection performance and superior robustness across diverse human image forgeries.

2026-01-08T08:33:22Z 6 figures, 5 tables Xiao Guo Jie Zhu Anil Jain Xiaoming Liu http://arxiv.org/abs/2601.02098v1 2026-01-05T13:26:02Z

Reconstructing complete and animatable 3D human avatars from monocular videos remains challenging, particularly under severe occlusions. While 3D Gaussian Splatting has enabled photorealistic human rendering, existing methods struggle with incomplete observations, often producing corrupted geometry and temporal inconsistencies. We present InpaintHuman, a novel method for generating high-fidelity, complete, and animatable avatars from occluded monocular videos. Our approach introduces two key innovations: (i) a multi-scale UV-parameterized representation with hierarchical coarse-to-fine feature interpolation, enabling robust reconstruction of occluded regions while preserving geometric details; and (ii) an identity-preserving diffusion inpainting module that integrates textual inversion with semantic-conditioned guidance for subject-specific, temporally coherent completion. Unlike SDS-based methods, our approach employs direct pixel-level supervision to ensure identity fidelity. Experiments on synthetic benchmarks (PeopleSnapshot, ZJU-MoCap) and real-world scenarios (OcMotion) demonstrate competitive performance with consistent improvements in reconstruction quality across diverse poses and viewpoints.

2026-01-05T13:26:02Z Jinlong Fan Shanshan Zhao Liang Zheng Jing Zhang Yuxiang Yang Mingming Gong http://arxiv.org/abs/2512.06106v1 2025-12-05T19:24:18Z

What if users could meet their future selves today? AI-generated future selves simulate meaningful encounters with a digital twin decades in the future. As AI systems advance, combining cloned voices, age-progressed facial rendering, and autobiographical narratives, a central question emerges: Does the modality of these future selves alter their psychological and affective impact? How might a text-based chatbot, a voice-only system, or a photorealistic avatar shape present-day decisions and our feeling of connection to the future? We report a randomized controlled study (N=92) evaluating three modalities of AI-generated future selves (text, voice, avatar) against a neutral control condition. We also report a systematic model evaluation between Claude 4 and three other Large Language Models (LLMs), assessing Claude 4 across psychological and interaction dimensions and establishing conversational AI quality as a critical determinant of intervention effectiveness. All personalized modalities strengthened Future Self-Continuity (FSC), emotional well-being, and motivation compared to control, with avatar producing the largest vividness gains, yet with no significant differences between formats. Interaction quality metrics, particularly persuasiveness, realism, and user engagement, emerged as robust predictors of psychological and affective outcomes, indicating that how compelling the interaction feels matters more than the form it takes. Content analysis found thematic patterns: text emphasized career planning, while voice and avatar facilitated personal reflection. Claude 4 outperformed ChatGPT 3.5, Llama 4, and Qwen 3 in enhancing psychological, affective, and FSC outcomes.

2025-12-05T19:24:18Z Constanze Albrecht Chayapatr Archiwaranguprok Rachel Poonsiriwong Awu Chen Peggy Yin Monchai Lertsutthiwong Kavin Winson Hal Hershfield Pattie Maes Pat Pataranutaporn http://arxiv.org/abs/2512.04313v1 2025-12-03T23:02:27Z

Current expressive avatar systems rely heavily on visual cues, failing when faces are occluded or when emotions remain internal. We present Mind-to-Face, the first framework that decodes non-invasive electroencephalogram (EEG) signals directly into high-fidelity facial expressions. We build a dual-modality recording setup to obtain synchronized EEG and multi-view facial video during emotion-eliciting stimuli, enabling precise supervision for neural-to-visual learning. Our model uses a CNN-Transformer encoder to map EEG signals into dense 3D position maps, capable of sampling over 65k vertices, capturing fine-scale geometry and subtle emotional dynamics, and renders them through a modified 3D Gaussian Splatting pipeline for photorealistic, view-consistent results. Through extensive evaluation, we show that EEG alone can reliably predict dynamic, subject-specific facial expressions, including subtle emotional responses, demonstrating that neural signals contain far richer affective and geometric information than previously assumed. Mind-to-Face establishes a new paradigm for neural-driven avatars, enabling personalized, emotion-aware telepresence and cognitive interaction in immersive environments.

2025-12-03T23:02:27Z 16 pages, 11 figures Haolin Xiong Tianwen Fu Pratusha Bhuvana Prasad Yunxuan Cai Haiwei Chen Wenbin Teng Hanyuan Xiao Yajie Zhao http://arxiv.org/abs/2511.08079v1 2025-11-11T10:29:40Z

Reconstructing human avatars using generative priors is essential for achieving versatile and realistic avatar models. Traditional approaches often rely on volumetric representations guided by generative models, but these methods require extensive volumetric rendering queries, leading to slow training. Alternatively, surface-based representations offer faster optimization through differentiable rasterization, yet they are typically limited by vertex count, restricting mesh resolution and scalability when combined with generative priors. Moreover, integrating generative priors into physically based human avatar modeling remains largely unexplored. To address these challenges, we introduce DIS (Deep Inverse Shading), a unified framework for high-fidelity, relightable avatar reconstruction that incorporates generative priors into a coherent surface representation. DIS centers on a mesh-based model that serves as the target for optimizing both surface and material details. The framework fuses multi-view 2D generative surface normal predictions, rich in detail but often inconsistent, into the central mesh using a normal conversion module. This module converts generative normal outputs into per-triangle surface offsets via differentiable rasterization, enabling the capture of fine geometric details beyond sparse vertex limitations. Additionally, DIS integrates a de-shading module to recover accurate material properties. This module refines albedo predictions by removing baked-in shading and back-propagates reconstruction errors to optimize the geometry. Through joint optimization of geometry and material appearance, DIS achieves physically consistent, high-quality reconstructions suitable for accurate relighting. Our experiments show that DIS delivers SOTA relighting quality, enhanced rendering efficiency, lower memory consumption, and detailed surface reconstruction.

2025-11-11T10:29:40Z AAAI2026 Jiacheng Wu Ruiqi Zhang Jie Chen http://arxiv.org/abs/2510.16833v1 2025-10-19T13:42:03Z

Mannequin-based clothing displays offer a cost-effective alternative to real-model showcases for online fashion presentation, but lack realism and expressive detail. To overcome this limitation, we introduce a new task called mannequin-to-human (M2H) video generation, which aims to synthesize identity-controllable, photorealistic human videos from footage of mannequins. We propose M2HVideo, a pose-aware and identity-preserving video generation framework that addresses two key challenges: the misalignment between head and body motion, and identity drift caused by temporal modeling. In particular, M2HVideo incorporates a dynamic pose-aware head encoder that fuses facial semantics with body pose to produce consistent identity embeddings across frames. To address the loss of fine facial details due to latent space compression, we introduce a mirror loss applied in pixel space through a denoising diffusion implicit model (DDIM)-based one-step denoising. Additionally, we design a distribution-aware adapter that aligns statistical distributions of identity and clothing features to enhance temporal coherence. Extensive experiments on the UBC fashion dataset, our self-constructed ASOS dataset, and the newly collected MannequinVideos dataset captured on-site demonstrate that M2HVideo achieves superior performance in terms of clothing consistency, identity preservation, and video fidelity in comparison to state-of-the-art methods.

2025-10-19T13:42:03Z Xiangyu Mu Dongliang Zhou Jie Hou Haijun Zhang Weili Guan http://arxiv.org/abs/2510.12785v1 2025-10-14T17:56:14Z

Digital human avatars aim to simulate the dynamic appearance of humans in virtual environments, enabling immersive experiences across gaming, film, virtual reality, and more. However, the conventional process for creating and animating photorealistic human avatars is expensive and time-consuming, requiring large camera capture rigs and significant manual effort from professional 3D artists. With the advent of capable image and video generation models, recent methods enable automatic rendering of realistic animated avatars from a single casually captured reference image of a target subject. While these techniques significantly lower barriers to avatar creation and offer compelling realism, they lack constraints provided by multi-view information or an explicit 3D representation. So, image quality and realism degrade when rendered from viewpoints that deviate strongly from the reference image. Here, we build a video model that generates animatable multi-view videos of digital humans based on a single reference image and target expressions. Our model, MVP4D, is based on a state-of-the-art pre-trained video diffusion model and generates hundreds of frames simultaneously from viewpoints varying by up to 360 degrees around a target subject. We show how to distill the outputs of this model into a 4D avatar that can be rendered in real-time. Our approach significantly improves the realism, temporal consistency, and 3D consistency of generated avatars compared to previous methods.

2025-10-14T17:56:14Z 18 pages, 12 figures Felix Taubner Ruihang Zhang Mathieu Tuli Sherwin Bahmani David B. Lindell http://arxiv.org/abs/2509.18924v1 2025-09-23T12:46:43Z

We introduce the first method for audio-driven universal photorealistic avatar synthesis, combining a person-agnostic speech model with our novel Universal Head Avatar Prior (UHAP). UHAP is trained on cross-identity multi-view videos. In particular, our UHAP is supervised with neutral scan data, enabling it to capture the identity-specific details at high fidelity. In contrast to previous approaches, which predominantly map audio features to geometric deformations only while ignoring audio-dependent appearance variations, our universal speech model directly maps raw audio inputs into the UHAP latent expression space. This expression space inherently encodes, both, geometric and appearance variations. For efficient personalization to new subjects, we employ a monocular encoder, which enables lightweight regression of dynamic expression variations across video frames. By accounting for these expression-dependent changes, it enables the subsequent model fine-tuning stage to focus exclusively on capturing the subject's global appearance and geometry. Decoding these audio-driven expression codes via UHAP generates highly realistic avatars with precise lip synchronization and nuanced expressive details, such as eyebrow movement, gaze shifts, and realistic mouth interior appearance as well as motion. Extensive evaluations demonstrate that our method is not only the first generalizable audio-driven avatar model that can account for detailed appearance modeling and rendering, but it also outperforms competing (geometry-only) methods across metrics measuring lip-sync accuracy, quantitative image quality, and perceptual realism.

2025-09-23T12:46:43Z (SIGGRAPH Asia 2025) Project page: https://kartik-teotia.github.io/UniGAHA/ Kartik Teotia Helge Rhodin Mohit Mendiratta Hyeongwoo Kim Marc Habermann Christian Theobalt http://arxiv.org/abs/2507.22153v1 2025-07-29T18:37:24Z

Photorealistic 3D avatar generation has rapidly improved in recent years, and realistic avatars that match a user's true appearance are more feasible in Mixed Reality (MR) than ever before. Yet, there are known risks to sharing one's likeness online, and photorealistic MR avatars could exacerbate these risks. If user likenesses were to be shared broadly, there are risks for cyber abuse or targeted fraud based on user appearances. We propose an alternate avatar rendering scheme for broader social MR -- synthesizing realistic avatars that preserve a user's demographic identity while being distinct enough from the individual user to protect facial biometric information. We introduce a methodology for privatizing appearance by isolating identity within the feature space of identity-encoding generative models. We develop two algorithms that then obfuscate identity: \epsmethod{} provides differential privacy guarantees and \thetamethod{} provides fine-grained control for the level of identity offset. These methods are shown to successfully generate de-identified virtual avatars across multiple generative architectures in 2D and 3D. With these techniques, it is possible to protect user privacy while largely preserving attributes related to sense of self. Employing these techniques in public settings could enable the use of photorealistic avatars broadly in MR, maintaining high realism and immersion without privacy risk.

2025-07-29T18:37:24Z Ethan Wilson Vincent Bindschaedler Sophie Jörg Sean Sheikholeslam Kevin Butler Eakta Jain http://arxiv.org/abs/2507.05620v2 2025-10-12T03:31:42Z

Enabling photorealistic avatar animations in virtual and augmented reality (VR/AR) has been challenging because of the difficulty of obtaining ground truth state of faces. It is physically impossible to obtain synchronized images from head-mounted cameras (HMC) sensing input, which has partial observations in infrared (IR), and an array of outside-in dome cameras, which have full observations that match avatars' appearance. Prior works relying on analysis-by-synthesis methods could generate accurate ground truth, but suffer from imperfect disentanglement between expression and style in their personalized training. The reliance of extensive paired captures (HMC and dome) for the same subject makes it operationally expensive to collect large-scale datasets, which cannot be reused for different HMC viewpoints and lighting. In this work, we propose a novel generative approach, Generative HMC (GenHMC), that leverages large unpaired HMC captures, which are much easier to collect, to directly generate high-quality synthetic HMC images given any conditioning avatar state from dome captures. We show that our method is able to properly disentangle the input conditioning signal that specifies facial expression and viewpoint, from facial appearance, leading to more accurate ground truth. Furthermore, our method can generalize to unseen identities, removing the reliance on the paired captures. We demonstrate these breakthroughs by both evaluating synthetic HMC images and universal face encoders trained from these new HMC-avatar correspondences, which achieve better data efficiency and state-of-the-art accuracy.

2025-07-08T03:00:44Z SIGGRAPH Asia 2025 (ACM Transactions on Graphics (TOG)). Project page: https://shawn615.github.io/genhmc/ Shaojie Bai Seunghyeon Seo Yida Wang Chenghui Li Owen Wang Te-Li Wang Tianyang Ma Jason Saragih Shih-En Wei Nojun Kwak Hyung Jun Kim http://arxiv.org/abs/2506.16159v1 2025-06-19T09:14:50Z

With the advancement of conversational AI, research on bodily expressions, including gestures and facial expressions, has also progressed. However, many existing studies focus on photorealistic avatars, making them unsuitable for non-photorealistic characters, such as those found in anime. This study proposes methods for expressing emotions, including exaggerated expressions unique to non-photorealistic characters, by utilizing expression data extracted from comics and dialogue-specific semantic gestures. A user study demonstrated significant improvements across multiple aspects when compared to existing research.

2025-06-19T09:14:50Z Accepted to SIGGRAPH 2025 Poster Taisei Omine Sony Group Corporation Naoyuki Kawabata Sony Group Corporation Fuminori Homma Sony Group Corporation 10.1145/3721250.3742976 http://arxiv.org/abs/2506.06271v2 2025-11-14T17:10:57Z

We introduce BecomingLit, a novel method for reconstructing relightable, high-resolution head avatars that can be rendered from novel viewpoints at interactive rates. Therefore, we propose a new low-cost light stage capture setup, tailored specifically towards capturing faces. Using this setup, we collect a novel dataset consisting of diverse multi-view sequences of numerous subjects under varying illumination conditions and facial expressions. By leveraging our new dataset, we introduce a new relightable avatar representation based on 3D Gaussian primitives that we animate with a parametric head model and an expression-dependent dynamics module. We propose a new hybrid neural shading approach, combining a neural diffuse BRDF with an analytical specular term. Our method reconstructs disentangled materials from our dynamic light stage recordings and enables all-frequency relighting of our avatars with both point lights and environment maps. In addition, our avatars can easily be animated and controlled from monocular videos. We validate our approach in extensive experiments on our dataset, where we consistently outperform existing state-of-the-art methods in relighting and reenactment by a significant margin.

2025-06-06T17:53:58Z NeurIPS 2025, Project Page: see https://jonathsch.github.io/becominglit/ , YouTube Video: see https://youtu.be/xPyeIqKdszA Jonathan Schmidt Simon Giebenhain Matthias Niessner