https://arxiv.org/api/NAdNEekSDHwwXjvTSuDUX6Oxw/0 2026-09-27T19:43:10Z 40 104 0 http://arxiv.org/abs/2609.23509v1 2026-09-20T09:52:43Z

Novel view synthesis is a key task for dynamic scene reconstruction, where high rendering speed is essential for applications such as virtual reality. Existing deformable Gaussian Splatting methods achieve high-fidelity dynamic scene modeling, but still face limitations in memory usage and rendering efficiency due to the large number of redundant Gaussians. To address these challenges, we propose Geometry-Aware Redundancy Optimization (GARO), a unified redundancy measurement framework in the adaptive density control stage of the traditional dynamic scene reconstruction pipeline. This framework first selects low-gradient candidates using an optimization activity assessment strategy, and then evaluates geometric complexity through low curvature analysis to further filter and prune redundant points, resulting in a compact and expressive Gaussian representation. Extensive experiments on synthetic and real-world datasets demonstrate that GARO achieves robust trade-offs between quality and speed, with PSNR remaining stable and rendering speed improved by 2x, validating the efficiency and effectiveness of GARO.

2026-09-20T09:52:43Z 8 pages. Accepted to IEEE ICRA 2026 Huiwen Xue School of Software, Northwestern Polytechnical University Kaixing Zhao School of Software, Northwestern Polytechnical University Zuheng Ming L2TI, Université Sorbonne Paris Nord, EmboMind Research Tingcheng Li School of Electronic Information and Engineering, Suzhou University of Science and Technology http://arxiv.org/abs/2608.13143v1 2026-08-13T12:16:37Z

This paper presents ProbSplat, a Compute-in-Memory (CIM)-inspired architecture based on programmable and energy efficient floating-gate inverter columns for probabilistic computing. Improving upon our prior work, ProbSplat programs and stores both means and variances of Gaussian mixture components, and evaluates log-likelihood for gaussian splatting during scene reconstruction with high energy efficiency, suitable for robotics and augmented/virtual reality (AR/VR) at the edge. Our proposed scheme enables independent control of both mean and variance via deterministic adjustment of floating-gate MOSFET threshold voltages, increasing the fidelity of hardware to program probability distributions. The design is simulated in 180nm CMOS on 1.8 V at 50 MHz and achieves mean-variance independence with <2.4% deviation during 3-D Gaussian mixture modeling. Compared to conventional digital implementations, ProbSplat significantly reduces compute complexity, memory footprint, and power consumption. The scalable framework consumes 18pJ energy per log-likelihood inference with 4-bit precision while operating for 500 mixture functions in a 3-D GMM. Scene reconstruction with ProbSplat's characteristics gave satisfactory fidelity of 21.99 PSNR (dB) at 8-bit precision.

2026-08-13T12:16:37Z Accepted for publication in the 2026 IEEE Computer Society Annual Symposium on VLSI (ISVLSI) Siddarth Gottumukkula M P Samartha Vedant Pahariya Priyanshi Jain Amit Ranjan Trivedi Priyesh Shukla http://arxiv.org/abs/2608.04475v1 2026-08-05T05:58:30Z

Despite the promise of virtual reality (VR) for intuitive spatial interaction, volume visualization (VolVis) in VR remains constrained by high rendering costs and motion discomfort. Recent advances have shown that representing volumetric scenes with 3D Gaussian splatting enables high-performance rendering, making this representation well-suited for VR. However, existing Gaussian-based scene editing workflows remain limited by slow offline segmentation and fatigue-inducing manual selection. To address these challenges, we present Super-Gaussian, a novel VolVis framework that enhances scene editing and interaction in VR through intuitive 3D Gaussian selection and natural language interaction (NLI). Our approach groups Gaussian primitives into higher-level units via feature-aware clustering, enabling efficient selection of complex volumetric regions, such as tumors in medical images or filaments in cosmological data, without point-by-point interaction. Building on this, we introduce a hierarchical select-and-refine workflow that combines random-walk-based region propagation, cluster selection, and point refinement, allowing users to progressively specify regions of interest with reduced effort. We further support on-the-fly text labeling of selected regions using NLI, allowing users to semantically query, interpret, and manipulate content within a visualization-perception-action loop. By integrating multimodal interaction, including speech, visual feedback, and spatial manipulation in VR, our framework supports intuitive exploration, editing, and scientific analysis of volumetric data. We demonstrate the effectiveness of Super-Gaussian through four case studies, quantitative selection benchmarks against existing Gaussian-based techniques, and system-level evaluations. Implementation details and experiments can be found on the project page: https://smin0136.github.io/super-gaussian-project/

2026-08-05T05:58:30Z IEEE VIS 2026 accepted Suemin Jeon Kaiyuan Tang Chaoli Wang Won-Ki Jeong http://arxiv.org/abs/2608.01969v1 2026-08-03T09:35:16Z

Digital Twins (DTs) are increasingly used for immersive experiences in virtual tourism. Virtual Reality (VR) enables remote visits to replicated locations for promotional purposes or access to fragile and rural cultural heritage sites. However, developing high-fidelity DTs of tourist destinations is costly, due to the manual creation of 3D environments. Novel 3D rendering techniques, such as 3D Gaussian splatting (3DGS), pose a promising approach to creating immersive experiences. This study investigates the user experience (UX) of a 3D-mesh-based scene and a 3DGS-based scene within a VR tourism application. In a laboratory study, 20 participants engaged with both versions and rated UX, cybersickness, presence and affect through standardized questionnaires. A custom questionnaire was created to measure the perception of the DTs. The collected data suggests that both versions were enjoyed and induced positive affect, with the Mesh version receiving good UX ratings. While the 3DGS version scored higher in terms of experienced realism, it showed clear weaknesses in pragmatic quality. Further, the results suggest that the feeling of presence could be enhanced and cybersickness reduced in both versions. Overall, the study contributes to the understanding of UX in VR tourism applications by implementing mesh-based and 3DGS-based DTs and raising important questions about the perception of realism.

2026-08-03T09:35:16Z Accepted to the 1st Workshop on Hyperrealism in XR at ISMAR 2026 Maximilian Warsinke Francesco Vona Abm Tariqul Islam Tanja Kojić Jan-Niklas Voigt-Antons Sebastian Möller http://arxiv.org/abs/2607.28164v1 2026-07-30T13:04:03Z

We propose S-Avatar, a novel method for generating photorealistic 3D head avatars from a single image using a diffusion-guided 3D model generation module and strategies for animating 3D Gaussian Splatting (3DGS). While single-image head avatar reconstruction is crucial for lifelike Virtual Reality (VR) applications, existing approaches often struggle to preserve 3D consistency under unseen viewpoints. S-Avatar addresses this limitation through a three-stage pipeline. First, a high-resolution 3DGS is synthesized directly from a single image using a diffusion-based Gaussian splat generation module. Next, the parametric head model FLAME is aligned with the generated 3DGS by optimizing its parameters and spatial transformations. Finally, to adapt the 3DGS to FLAME variations, we construct a binding template that encodes the spatial relationship between the initial splats and FLAME. The dynamic 3D head avatar can then be rendered in real time by deforming the 3DGS with the binding template. By combining diffusion-guided canonical 3DGS generation with FLAME-based control, our method achieves efficient and accurate reconstruction with enhanced 3D consistency. Evaluations on public datasets demonstrate that S-Avatar outperforms state-of-the-art methods in novel-view and expression generation, achieving superior realism and consistency. Consequently, our approach represents a significant advance in accessible avatar creation, applicable to a wide range of VR/AR applications. The project page is available at https://github.com/hailsong/savatar.

2026-07-30T13:04:03Z 15 pages, 12 figures Hail Song Seokhwan Yang Jiwon Yang Woojin Cho Woontack Woo http://arxiv.org/abs/2607.12641v1 2026-07-14T11:19:16Z

Wireless aerial virtual reality (VR) aims to provide immersive access to large-scale scenes, but high-resolution view generation and delivery are jointly constrained by limited bandwidth, latency, and power. 3D Gaussian Splatting (3DGS) can reduce the payload by rendering views from compact pose information, yet its geometry errors may cause severe VR quality degradation. Existing channel-aware or pixel-level resource allocation schemes fail to capture such geometry-sensitive distortion. To address this issue, this paper proposes GeoFovea-GS as a geometry-aware cross-layer framework for communication-efficient wireless aerial VR. A foveated geometry-aware distortion metric is developed to characterize photometric rendering error, geometric inconsistency, and view-dependent perceptual importance in a unified form. Based on this metric, the joint selection of pose-only 3DGS rendering and image/tile correction transmission is formulated as a cross-layer optimization problem under wireless constraints. A lightweight value-of-information scheduler is further developed to allocate communication resources to regions that are both geometry-critical and perceptually important. Experiments on real-world 3DGS scenes demonstrate that GeoFovea-GS achieves superior immersive rendering quality with substantially reduced transmission cost.

2026-07-14T11:19:16Z 7 pages, 5 figures Zeyi Ren Wencheng Yan Jiawen Zhang Jintao Yan Sheng Zhou Zhisheng Niu http://arxiv.org/abs/2605.30863v1 2026-05-29T05:38:00Z

Dynamic scene reconstruction and novel view synthesis are fundamental to next-generation visual intelligence applications such as virtual reality, robotics, and digital twins. However, high-fidelity reconstruction of complex, time-varying scenes from arbitrary viewpoints remains a significant challenge. Existing dynamic 3DGS methods suffer from computational inefficiency, since they model all Gaussians as dynamic components. While recent decomposition-based approaches address this issue, they still struggle with degraded reconstruction quality and prolonged training time. To mitigate these limitations, we propose a novel dynamic reconstruction framework built upon an efficient static-dynamic decomposition strategy using a Feed-Forward Gaussian Splatting encoder and an optical flow model. By eliminating redundant computations on static regions, our method achieves state-of-the-art performance, outperforming existing baselines across rendering quality, training and rendering speed, and storage efficiency. Notably, on the Neural 3D dataset, our framework requires only 10 minutes for training and achieves a rendering speed of over 700 FPS on a single NVIDIA RTX 5090 GPU at resolution of 1352x1014. Furthermore, our decomposition strategy eliminates the need for COLMAP preprocessing and enables deterministic initialization, thereby enhancing both efficiency and reproducibility.

2026-05-29T05:38:00Z 23 pages, 9 figures, 7 tables Youngtae Han Sung-hwan Han Youngmin Yi http://arxiv.org/abs/2605.16065v1 2026-05-15T15:29:30Z

3D Gaussian Splatting (3D-GS) enables real-time 3D scene reconstruction but lacks robust segmentation for editing tasks such as object removal, extraction, and recoloring. Existing approaches that lift 2D segmentations to the 3D domain suffer from view inconsistencies and coarse masks. In this paper, we propose a novel framework that leverages the Segment Anything Model High Quality (SAM-HQ) to generate accurate 2D masks, addressing the limitations of the standard SAM in boundary fidelity and fine-structure preservation. To achieve robust 3D segmentation of any target object in a given scene, we introduce a prior-guided label reassignment method that assigns labels to 3D Gaussians by enforcing multiview consistency with learned priors. Our approach achieves state-of-the-art segmentation accuracy and enables interactive, real-time object editing while maintaining high visual fidelity. Qualitative results demonstrate superior boundary preservation and practical utility in Virtual Reality (VR) and robotics, advancing 3D scene editing.

2026-05-15T15:29:30Z Accepted at IEEE International Conference on Image Processing 2026, 6 pages Raushan Joshi Jean-Yves Guillemaut http://arxiv.org/abs/2605.02784v2 2026-05-21T16:22:38Z

Accurately recovering human pose and appearance from video is an essential component of scene reconstruction, with applications to motion capture, motion prediction, virtual reality, and digital twinning. Despite significant interest in building realistic human avatars from video, this paper demonstrates that existing methods do not accurately recover the 3D geometry of humans. ViT-based approaches are not consistently reliable and can overfit to 2D views, while NeRF- and Gaussian Splatting-based avatars treat pose and appearance separately, limiting rendering generalization to new poses. To resolve these shortcomings, this paper proposes HumanSplatHMR, a joint optimization framework that refines 3D human poses while simultaneously learning a high-fidelity avatar for novel-view and novel-pose synthesis. Our key insight is to close the loop between geometric pose estimation and differentiable rendering. Unlike prior human avatar methods that rely on accurate human pose obtained through motion capture systems or offline refinement, which are impractical in in-the-wild scenarios, our approach uses only human mesh estimates from a state-of-the-art human pose estimator to better reflect real-world conditions. Therefore, instead of using the human pose only as a deformation prior, HumanSplatHMR backpropagates photometric, segmentation, and depth losses through a differentiable renderer to the pose parameters and global position. This coupling refines the global 3D pose over time, improving accuracy and alignment while producing better renderings from novel views. Experiments show consistent improvements over pose recovery baselines that omit image-level refinement and avatar baselines that decouple pose estimation from avatar reconstruction.

2026-05-04T16:26:11Z Project page: https://scottyehengz.github.io/HumanSplat/ Yeheng Zong Pou-Chun Kung Yike Pan Seth Isaacson Yizhou Chen Ram Vasudevan Katherine A. Skinner http://arxiv.org/abs/2604.21714v1 2026-04-20T20:42:55Z

Real-time, high-fidelity 3D human reconstruction from RGB images is essential for interactive applications such as virtual reality and gaming, yet remains challenging due to the complex non-rigid deformations of dynamic human bodies. Although 3D Gaussian Splatting enables efficient rendering, existing methods struggle to capture fine geometric details and often produce artifacts such as fused fingers and over-smoothed faces. Moreover, conventional spatial-field-based dynamic modeling faces a trade-off between reconstruction fidelity and GPU memory consumption. To address these issues, we propose a novel 3D Gaussian human reconstruction framework that combines region-aware initialization with rich geometric priors. Specifically, we leverage the expressive SMPL-X model to initialize both 3D Gaussians and skinning weights, providing a robust geometric foundation for precise reconstruction. We further introduce a region-aware density initialization strategy and a geometry-aware multi-scale hash encoding module to improve local detail recovery while maintaining computational efficiency.Experiments on PeopleSnapshot and GalaBasketball show that our method achieves superior reconstruction quality and finer detail preservation under complex motions, while maintaining real-time rendering speed.

2026-04-20T20:42:55Z Yang Liu Zhiyong Zhang http://arxiv.org/abs/2604.07177v1 2026-04-08T15:05:29Z

We investigate the feasibility of real-time 3D Gaussian Splatting (3DGS) rasterisation on edge clients with varying Gaussian splat counts and GPU computational budgets. Instead of evaluating multiple physical devices, we adopt an emulation-based approach that approximates different GPU capability tiers on a single high-end GPU. By systematically under-clocking the GPU core frequency and applying power caps, we emulate a controlled range of floating-point performance levels that approximate different GPU capability tiers. At each point in this range, we measure frame rate, runtime behaviour, and power consumption across scenes of varying complexity, pipelines, and optimisations, enabling analysis of power-performance relationships such as FPS-power curves, energy per frame, and performance per watt. This method allows us to approximate the performance envelope of a diverse class of GPUs, from embedded and mobile-class devices to high-end consumer-grade systems. Our objective is to explore the practical lower bounds of client-side 3DGS rasterisation and assess its potential for deployment in energy-constrained environments, including standalone headsets and thin clients. Through this analysis, we provide early insights into the performance-energy trade-offs that govern the viability of edge-deployed 3DGS systems.

2026-04-08T15:05:29Z Muhammad Fahim Tajwar Arthur Wuhrlin Bhojan Anand http://arxiv.org/abs/2604.04331v1 2026-04-06T00:47:42Z

Reconstructing static 3D scene from monocular video with dynamic objects is important for numerous applications such as virtual reality and autonomous driving. Current approaches typically rely on background for static scene reconstruction, limiting the ability to recover regions occluded by dynamic objects. In this paper, we propose GA-GS, a Generation-Assisted Gaussian Splatting method for Static Scene Reconstruction. The key innovation of our work lies in leveraging generation to assist in reconstructing occluded regions. We employ a motion-aware module to segment and remove dynamic regions, and thenuse a diffusion model to inpaint the occluded areas, providing pseudo-ground-truth supervision. To balance contributions from real background and generated region, we introduce a learnable authenticity scalar for each Gaussian primitive, which dynamically modulates opacity during splatting for authenticity-aware rendering and supervision. Since no existing dataset provides ground-truth static scene of video with dynamic objects, we construct a dataset named Trajectory-Match, using a fixed-path robot to record each scene with/without dynamic objects, enabling quantitative evaluation in reconstruction of occluded regions. Extensive experiments on both the DAVIS and our dataset show that GA-GS achieves state-of-the-art performance in static scene reconstruction, especially in challenging scenarios with large-scale, persistent occlusions.

2026-04-06T00:47:42Z Yedong Shen Shiqi Zhang Sha Zhang Yifan Duan Xinran Zhang Wenhao Yu Lu Zhang Jiajun Deng Yanyong Zhang http://arxiv.org/abs/2605.13853v1 2026-03-25T21:34:06Z

Facial editing is an important task with applications in entertainment, virtual reality, and digital avatars. Most existing approaches rely on generative models in the 2D image domain, while in 3D the task is typically performed through labor-intensive manual editing. We propose FaceParts, a framework for unsupervised segmentation and editing of Gaussian Splatting avatars. Unlike existing 2D or mesh-assisted methods, our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision. The method integrates feature disentanglement, density-based clustering, and FLAME-anchored part transfer, enabling precise editing and cross-avatar part swapping. Experiments on the NeRSemble dataset with 11 subjects demonstrate robust isolation of features such as beards, eyebrows, eyes and mustaches. Quantitative evaluation confirms that transferred segments adapt to pose and expression, while maintaining identity consistency (ID = 0.943), low Average Expression Distance (AED = 0.021) and low Average Pose Distance (APD = 0.004).

2026-03-25T21:34:06Z Tymoteusz Zapała Julia Farganus Dominik Galus Mikołaj Czachorowski Piotr Syga Przemysław Spurek http://arxiv.org/abs/2603.20560v1 2026-03-20T23:25:51Z

In this work, we present a multimodal data acquisition workflow for the digital preservation and virtual reconstruction of at-risk historical sites in the island of Nevis. Facing threats from coastal erosion, rising sea levels, and aggressive vegetation, the archaeological heritage of Nevis requires documentation strategies that bridge the gap between high-cost professional surveying and consumer accessibility. Experimental test compared acquisition variables, specifically camera height (1m vs. 3m) and operator trajectory against high-resolution control data. Moreover, we explore the virtual reconstruction between mesh reconstruction and 3D gaussian splatting to serve as different modalities for documentation. The resulting data is fused into immersive virtual reality (VR) environments, offering a scalable, non-proprietary model for democratizing digital heritage in the Caribbean.

2026-03-20T23:25:51Z ARCHERIX Workshop - IEEE VR 2026 Alex Apffel Huy Tran Vuthea Chheang http://arxiv.org/abs/2603.17131v1 2026-03-17T20:47:49Z

Creating high-fidelity, animatable 3D dog avatars remains a formidable challenge in computer vision. Unlike human digital doubles, animal reconstruction faces a critical shortage of large-scale, annotated datasets for specialized applications. Furthermore, the immense morphological diversity across species, breeds, and crosses, which varies significantly in size, proportions, and features, complicates the generalization of existing models. Current reconstruction methods often struggle to capture realistic fur textures. Additionally, ensuring these avatars are fully editable and capable of performing complex, naturalistic movements typically necessitates labor-intensive manual mesh manipulation and expert rigging. This paper introduces SMAL-pets, a comprehensive framework that generates high-quality, editable animal avatars from a single input image. Our approach bridges the gap between reconstruction and generative modeling by leveraging a hybrid architecture. Our method integrates 3D Gaussian Splatting with the SMAL parametric model to provide a representation that is both visually high-fidelity and anatomically grounded. We introduce a multimodal editing suite that enables users to refine the avatar's appearance and execute complex animations through direct textual prompts. By allowing users to control both the aesthetic and behavioral aspects of the model via natural language, SMAL-pets provides a flexible, robust tool for animation and virtual reality.

2026-03-17T20:47:49Z Piotr Borycki Joanna Waczyńska Yizhe Zhu Yongqiang Gao Przemysław Spurek http://arxiv.org/abs/2603.14316v2 2026-07-13T15:16:14Z

Object-level 3D reconstruction play important roles across domains such as cultural heritage digitization, industrial manufacturing, and virtual reality. However, existing Gaussian Splatting-based approaches generally rely on full-scene reconstruction, in which substantial redundant background information is introduced, leading to increased computational and storage overhead. To address this limitation, we propose an efficient single-object 3D reconstruction method based on 2D Gaussian Splatting. By directly integrating foreground-background probability cues into Gaussian primitives and dynamically pruning low-probability Gaussians during training, the proposed method fundamentally focuses on an object of interest and improves the memory and computational efficiency. Our pipeline leverages probability masks generated by YOLO and SAM to supervise probabilistic Gaussian attributes, replacing binary masks with continuous probability values to mitigate boundary ambiguity. Additionally, we propose a dual-stage filtering strategy for training's startup to suppress background Gaussians. And, during training, rendered probability masks are conversely employed to refine supervision and enhance boundary consistency across views. Experiments conducted on the MIP-360, T&T, and NVOS datasets demonstrate that our method exhibits strong self-correction capability in the presence of mask errors and achieves reconstruction quality comparable to standard 3DGS approaches, while requiring only approximately 1/10 of their Gaussian amount. These results validate the efficiency and robustness of our method for single-object reconstruction and highlight its potential for applications requiring both high fidelity and computational efficiency.

2026-03-15T10:17:14Z Shuai Guo Ao Guo Junchao Zhao Qi Chen Yuxiang Qi Zechuan Li Dong Chen Mingliang Xu http://arxiv.org/abs/2603.10801v1 2026-03-11T14:11:42Z

Accurate reconstruction of reflective surfaces remains a fundamental challenge in computer vision, with broad applications in real-time virtual reality and digital content creation. Although 3D Gaussian Splatting (3DGS) enables efficient novel-view rendering with explicit representations, its performance on reflective surfaces still lags behind implicit neural methods, especially in recovering fine geometry and surface normals. To address this gap, we propose PolGS++, a physically-guided polarimetric Gaussian Splatting framework for fast reflective surface reconstruction. Specifically, we integrate a polarized BRDF (pBRDF) model into 3DGS to explicitly decouple diffuse and specular components, providing physically grounded reflectance modeling and stronger geometric cues for reflective surface recovery. Furthermore, we introduce a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization (AoP)-based tangent-space consistency constraints in Gaussian Splatting without costly ray-tracing intersections. This physically guided design improves reconstruction quality and efficiency, requiring only about 10 minutes of training. Extensive experiments on both synthetic and real-world datasets validate the effectiveness of our method.

2026-03-11T14:11:42Z arXiv admin note: substantial text overlap with arXiv:2509.19726 Yufei Han Chu Zhou Youwei Lyu Qi Chen Si Li Boxin Shi Yunpeng Jia Heng Guo Zhanyu Ma http://arxiv.org/abs/2602.20342v1 2026-02-23T20:40:26Z

In this study, we present an end-to-end pipeline capable of converting drone-captured video streams into high-fidelity 3D reconstructions with minimal latency. Unmanned aerial vehicles (UAVs) are extensively used in aerial real-time perception applications. Moreover, recent advances in 3D Gaussian Splatting (3DGS) have demonstrated significant potential for real-time neural rendering. However, their integration into end-to-end UAV-based reconstruction and visualization systems remains underexplored. Our goal is to propose an efficient architecture that combines live video acquisition via RTMP streaming, synchronized sensor fusion, camera pose estimation, and 3DGS optimization, achieving continuous model updates and low-latency deployment within interactive visualization environments that supports immersive augmented and virtual reality (AR/VR) applications. Experimental results demonstrate that the proposed method achieves competitive visual fidelity, while delivering significantly higher rendering performance and substantially reduced end-to-end latency, compared to NeRF-based approaches. Reconstruction quality remains within 4-7\% of high-fidelity offline references, confirming the suitability of the proposed system for real-time, scalable augmented perception from aerial platforms.

2026-02-23T20:40:26Z 7 pages, 2 figures Christos Maikos Georgios Angelidis Georgios Th. Papadopoulos http://arxiv.org/abs/2602.01674v2 2026-05-04T04:40:10Z

We present VRGaussianAvatar, an integrated system that enables real-time full-body 3D Gaussian Splatting (3DGS) avatars in virtual reality using only head-mounted display (HMD) tracking signals. The system adopts a parallel pipeline with a VR Frontend and a GA Backend. The VR Frontend uses inverse kinematics to estimate full-body pose and streams the resulting pose along with stereo camera parameters to the backend. The GA Backend stereoscopically renders a 3DGS avatar reconstructed from a single image. To improve stereo rendering efficiency, we introduce Binocular Batching, which jointly processes left and right eye views in a single batched pass to reduce redundant computation and support high-resolution VR displays. We evaluate VRGaussianAvatar with quantitative performance tests and a within-subject user study against image- and video-based mesh avatar baselines. Results show that VRGaussianAvatar sustains interactive VR performance and yields higher perceived appearance similarity, embodiment, and plausibility. Project page and source code are available at https://vrgaussianavatar.github.io.

2026-02-02T05:42:40Z Accepted as an IEEE TVCG paper at IEEE VR 2026 (journal track) Hail Song Boram Yoon Seokhwan Yang Seoyoung Kang Hyunjeong Kim Henning Metzmacher Woontack Woo 10.1109/TVCG.2026.3680708 http://arxiv.org/abs/2601.22026v1 2026-01-29T17:33:14Z

Volumetric medical imaging offers great potential for understanding complex pathologies. Yet, traditional 2D slices provide little support for interpreting spatial relationships, forcing users to mentally reconstruct anatomy into three dimensions. Direct volumetric path tracing and VR rendering can improve perception but are computationally expensive, while precomputed representations, like Gaussian Splatting, require planning ahead. Both approaches limit interactive use. We propose a hybrid rendering approach for high-quality, interactive, and immersive anatomical visualization. Our method combines streamed foveated path tracing with a lightweight Gaussian Splatting approximation of the periphery. The peripheral model generation is optimized with volume data and continuously refined using foveal renderings, enabling interactive updates. Depth-guided reprojection further improves robustness to latency and allows users to balance fidelity with refresh rate. We compare our method against direct path tracing and Gaussian Splatting. Our results highlight how their combination can preserve strengths in visual quality while re-generating the peripheral model in under a second, eliminating extensive preprocessing and approximations. This opens new options for interactive medical visualization.

2026-01-29T17:33:14Z Scheduled for publication in the Proceedings of IEEE VR 2026 2026 IEEE Conference on Virtual Reality and 3D User Interfaces (VR), 585-595 (2026) Constantin Kleinbeck Luisa Theelke Hannah Schieber Ulrich Eck Rüdiger von Eisenhart-Rothe Daniel Roth 10.1109/VR67842.2026.00078 http://arxiv.org/abs/2601.19310v1 2026-01-27T07:48:59Z

High-fidelity cinematic medical visualization on mobile virtual reality (VR) remains challenging. Although ClipGS enables cross-sectional exploration via 3D Gaussian Splatting, it lacks arbitrary-angle slicing on consumer-grade VR headsets. To achieve real-time interactive performance, we introduce ClipGS-VR and restructure ClipGS's neural inference into a consolidated dataset, integrating high-fidelity layers from multiple pre-computed slicing states into a unified rendering structure. Our framework further supports arbitrary-angle slicing via gradient-based opacity modulation for smooth, visually coherent rendering. Evaluations confirm our approach maintains visual fidelity comparable to offline results while offering superior usability and interaction efficiency.

2026-01-27T07:48:59Z IEEE VR 2026 Posters Yuqi Tong Ruiyang Li Chengkun Li Qixuan Liu Shi Qiu Pheng-Ann Heng http://arxiv.org/abs/2601.15431v1 2026-01-21T19:56:22Z

Radiance field-based rendering methods have attracted significant interest from the computer vision and computer graphics communities. They enable high-fidelity rendering with complex real-world lighting effects, but at the cost of high rendering time. 3D Gaussian Splatting solves this issue with a rasterisation-based approach for real-time rendering, enabling applications such as autonomous driving, robotics, virtual reality, and extended reality. However, current 3DGS implementations are difficult to integrate into traditional mesh-based rendering pipelines, which is a common use case for interactive applications and artistic exploration. To address this limitation, this software solution uses Nvidia's interprocess communication (IPC) APIs to easily integrate into implementations and allow the results to be viewed in external clients such as Unity, Blender, Unreal Engine, and OpenGL viewers. The code is available at https://github.com/RockyXu66/splatbus.

2026-01-21T19:56:22Z Yinghan Xu Théo Morales John Dingliana http://arxiv.org/abs/2601.10606v1 2026-01-15T17:23:19Z

Talking head generation is increasingly important in virtual reality (VR), especially for social scenarios involving multi-turn conversation. Existing approaches face notable limitations: mesh-based 3D methods can model dual-person dialogue but lack realistic textures, while large-model-based 2D methods produce natural appearances but incur prohibitive computational costs. Recently, 3D Gaussian Splatting (3DGS) based methods achieve efficient and realistic rendering but remain speaker-only and ignore social relationships. We introduce RSATalker, the first framework that leverages 3DGS for realistic and socially-aware talking head generation with support for multi-turn conversation. Our method first drives mesh-based 3D facial motion from speech, then binds 3D Gaussians to mesh facets to render high-fidelity 2D avatar videos. To capture interpersonal dynamics, we propose a socially-aware module that encodes social relationships, including blood and non-blood as well as equal and unequal, into high-level embeddings through a learnable query mechanism. We design a three-stage training paradigm and construct the RSATalker dataset with speech-mesh-image triplets annotated with social relationships. Extensive experiments demonstrate that RSATalker achieves state-of-the-art performance in both realism and social awareness. The code and dataset will be released.

2026-01-15T17:23:19Z Peng Chen Xiaobao Wei Yi Yang Naiming Yao Hui Chen Feng Tian http://arxiv.org/abs/2512.09162v3 2026-03-19T12:23:13Z

Recent advancements in Gaussian Splatting have enabled increasingly accurate reconstruction of photorealistic head avatars, opening the door to numerous applications in visual effects, videoconferencing, and virtual reality. This, however, comes with the lack of intuitive editability offered by traditional triangle mesh-based methods. In contrast, we propose a method that combines the accuracy and fidelity of 2D Gaussian Splatting with the intuitiveness of UV texture mapping. By embedding each canonical Gaussian primitive's local frame into a patch in the UV space of a template mesh in a computationally efficient manner, we reconstruct continuous editable material head textures from a single monocular video on a conventional UV domain. Furthermore, we leverage an efficient physically based reflectance model to enable relighting and editing of these intrinsic material maps. Through extensive comparisons with state-of-the-art methods, we demonstrate the accuracy of our reconstructions, the quality of our relighting results, and the ability to provide intuitive controls for modifying an avatar's appearance and geometry via texture mapping without additional optimization.

2025-12-09T22:19:28Z Accepted to Eurographics 2026. Project page: https://kelianb.github.io/GTAvatar/ Kelian Baert Mae Younes Francois Bourel Marc Christie Adnane Boukhayma 10.1111/cgf.70351 http://arxiv.org/abs/2512.05060v1 2025-12-04T18:15:27Z

Constructing 4D language fields is crucial for embodied AI, augmented/virtual reality, and 4D scene understanding, as they provide enriched semantic representations of dynamic environments and enable open-vocabulary querying in complex scenarios. However, existing approaches to 4D semantic field construction primarily rely on scene-specific Gaussian splatting, which requires per-scene optimization, exhibits limited generalization, and is difficult to scale to real-world applications. To address these limitations, we propose 4DLangVGGT, the first Transformer-based feed-forward unified framework for 4D language grounding, that jointly integrates geometric perception and language alignment within a single architecture. 4DLangVGGT has two key components: the 4D Visual Geometry Transformer, StreamVGGT, which captures spatio-temporal geometric representations of dynamic scenes; and the Semantic Bridging Decoder (SBD), which projects geometry-aware features into a language-aligned semantic space, thereby enhancing semantic interpretability while preserving structural fidelity. Unlike prior methods that depend on costly per-scene optimization, 4DLangVGGT can be jointly trained across multiple dynamic scenes and directly applied during inference, achieving both deployment efficiency and strong generalization. This design significantly improves the practicality of large-scale deployment and establishes a new paradigm for open-vocabulary 4D scene understanding. Experiments on HyperNeRF and Neu3D datasets demonstrate that our approach not only generalizes effectively but also achieves state-of-the-art performance, achieving up to 2% gains under per-scene training and 1% improvements under multi-scene training. Our code released in https://github.com/hustvl/4DLangVGGT

2025-12-04T18:15:27Z Code: https://github.com/hustvl/4DLangVGGT, Webpage: https://hustvl.github.io/4DLangVGGT Xianfeng Wu Yajing Bai Minghan Li Xianzu Wu Xueqi Zhao Zhongyuan Lai Wenyu Liu Xinggang Wang http://arxiv.org/abs/2511.22056v2 2025-12-01T10:21:18Z

In the Virtual Reality (VR) gaming industry, maintaining immersion during real-world interruptions remains a challenge, particularly during transitions along the reality-virtuality continuum (RVC). Existing methods tend to rely on digital replicas or simple visual transitions, neglecting to address the aesthetic discontinuities between real and virtual environments, especially in highly stylized VR games. This paper introduces the Environment-Aware Stylized Transition (EAST) framework, which employs a novel style-transferred 3D Gaussian Splatting (3DGS) technique to transfer real-world interruptions into the virtual environment with seamless aesthetic consistency. Rather than merely transforming the real world into game-like visuals, EAST minimizes the disruptive impact of interruptions by integrating real-world elements within the framework. Qualitative user studies demonstrate significant enhancements in cognitive comfort and emotional continuity during transitions, while quantitative experiments highlight EAST's ability to maintain visual coherence across diverse VR styles.

2025-11-27T03:21:20Z Xiaohan Zhang Kan Liu Yangle Liu Fengze Li Jieming Ma Yue Li http://arxiv.org/abs/2511.12930v1 2025-11-17T03:37:13Z

3D Gaussian Splatting (3DGS) rendering in real-time on resource-constrained devices is essential for delivering immersive augmented and virtual reality (AR/VR) experiences. However, existing solutions struggle to achieve high frame rates, especially for high-resolution rendering. Our analysis identifies the sorting stage in the 3DGS rendering pipeline as the major bottleneck due to its high memory bandwidth demand. This paper presents Neo, which introduces a reuse-and-update sorting algorithm that exploits temporal redundancy in Gaussian ordering across consecutive frames, and devises a hardware accelerator optimized for this algorithm. By efficiently tracking and updating Gaussian depth ordering instead of re-sorting from scratch, Neo significantly reduces redundant computations and memory bandwidth pressure. Experimental results show that Neo achieves up to 10.0x and 5.6x higher throughput than state-of-the-art edge GPU and ASIC solution, respectively, while reducing DRAM traffic by 94.5% and 81.3%. These improvements make high-quality and low-latency on-device 3D rendering more practical.

2025-11-17T03:37:13Z Changhun Oh Seongryong Oh Jinwoo Hwang Yoonsung Kim Hardik Sharma Jongse Park http://arxiv.org/abs/2511.11175v1 2025-11-14T11:20:43Z

Multi-view video reconstruction plays a vital role in computer vision, enabling applications in film production, virtual reality, and motion analysis. While recent advances such as 4D Gaussian Splatting (4DGS) have demonstrated impressive capabilities in dynamic scene reconstruction, they typically rely on the assumption that input video streams are temporally synchronized. However, in real-world scenarios, this assumption often fails due to factors like camera trigger delays or independent recording setups, leading to temporal misalignment across views and reduced reconstruction quality. To address this challenge, a novel temporal alignment strategy is proposed for high-quality 4DGS reconstruction from unsynchronized multi-view videos. Our method features a coarse-to-fine alignment module that estimates and compensates for each camera's time shift. The method first determines a coarse, frame-level offset and then refines it to achieve sub-frame accuracy. This strategy can be integrated as a readily integrable module into existing 4DGS frameworks, enhancing their robustness when handling asynchronous data. Experiments show that our approach effectively processes temporally misaligned videos and significantly enhances baseline methods.

2025-11-14T11:20:43Z AAAI 2026 Zhixin Xu Hengyu Zhou Yuan Liu Wenhan Xue Hao Pan Wenping Wang Bin Wang http://arxiv.org/abs/2510.26694v1 2025-10-30T17:01:18Z

Since its introduction, 3D Gaussian Splatting (3DGS) has rapidly transformed the landscape of 3D scene representations, inspiring an extensive body of associated research. Follow-up work includes analyses and contributions that enhance the efficiency, scalability, and real-world applicability of 3DGS. In this summary, we present an overview of several key directions that have emerged in the wake of 3DGS. We highlight advances enabling resource-efficient training and rendering, the evolution toward dynamic (or four-dimensional, 4DGS) representations, and deeper exploration of the mathematical foundations underlying its appearance modeling and rendering process. Furthermore, we examine efforts to bring 3DGS to mobile and virtual reality platforms, its extension to massive-scale environments, and recent progress toward near-instant radiance field reconstruction via feed-forward or distributed computation. Collectively, these developments illustrate how 3DGS has evolved from a breakthrough representation into a versatile and foundational tool for 3D vision and graphics.

2025-10-30T17:01:18Z Article written for Frontiers of Science Award, International Congress on Basic Science, 2025 Bernhard Kerbl http://arxiv.org/abs/2510.22213v2 2025-11-30T05:21:55Z

Generating dynamic and interactive 3D trees has wide applications in virtual reality, games, and world simulation. However, existing methods still face various challenges in generating structurally consistent and realistic 4D motion for complex real trees. In this paper, we propose DynamicTree, the first framework that can generate long-term, interactive 3D motion for 3DGS reconstructions of real trees. Unlike prior optimization-based methods, our approach generates dynamics in a fast feed-forward manner. The key success of our approach is the use of a compact sparse voxel spectrum to represent the tree movement. Given a 3D tree from Gaussian Splatting reconstruction, our pipeline first generates mesh motion using the sparse voxel spectrum and then binds Gaussians to deform the mesh. Additionally, the proposed sparse voxel spectrum can also serve as a basis for fast modal analysis under external forces, allowing real-time interactive responses. To train our model, we also introduce 4DTree, the first large-scale synthetic 4D tree dataset containing 8,786 animated tree meshes with 100-frame motion sequences. Extensive experiments demonstrate that our method achieves realistic and responsive tree animations, significantly outperforming existing approaches in both visual quality and computational efficiency.

2025-10-25T08:21:40Z Project Page: https://dynamictree-dev.github.io/DynamicTree.github.io/ Yaokun Li Lihe Ding Xiao Chen Guang Tan Tianfan Xue http://arxiv.org/abs/2510.11878v2 2025-11-04T18:24:59Z

As the demand for immersive 3D content grows, the need for intuitive and efficient interaction methods becomes paramount. Current techniques for physically manipulating 3D content within Virtual Reality (VR) often face significant limitations, including reliance on engineering-intensive processes and simplified geometric representations, such as tetrahedral cages, which can compromise visual fidelity and physical accuracy. In this paper, we introduce GS-Verse (Gaussian Splatting for Virtual Environment Rendering and Scene Editing), a novel method designed to overcome these challenges by directly integrating an object's mesh with a Gaussian Splatting (GS) representation. Our approach enables more precise surface approximation, leading to highly realistic deformations and interactions. By leveraging existing 3D mesh assets, GS-Verse facilitates seamless content reuse and simplifies the development workflow. Moreover, our system is designed to be physics-engine-agnostic, granting developers robust deployment flexibility. This versatile architecture delivers a highly realistic, adaptable, and intuitive approach to interactive 3D manipulation. We rigorously validate our method against the current state-of-the-art technique that couples VR with GS in a comparative user study involving 18 participants. Specifically, we demonstrate that our approach is statistically significantly better for physics-aware stretching manipulation and is also more consistent in other physics-based manipulations like twisting and shaking. Further evaluation across various interactions and scenes confirms that our method consistently delivers high and reliable performance, showing its potential as a plausible alternative to existing methods.

2025-10-13T19:36:47Z Anastasiya Pechko Piotr Borycki Joanna Waczyńska Daniel Barczyk Agata Szymańska Sławomir Tadeja Przemysław Spurek http://arxiv.org/abs/2509.25122v1 2025-09-29T17:43:46Z

Reconstructing 3D scenes and synthesizing novel views has seen rapid progress in recent years. Neural Radiance Fields demonstrated that continuous volumetric radiance fields can achieve high-quality image synthesis, but their long training and rendering times limit practicality. 3D Gaussian Splatting (3DGS) addressed these issues by representing scenes with millions of Gaussians, enabling real-time rendering and fast optimization. However, Gaussian primitives are not natively compatible with the mesh-based pipelines used in VR headsets, and real-time graphics applications. Existing solutions attempt to convert Gaussians into meshes through post-processing or two-stage pipelines, which increases complexity and degrades visual quality. In this work, we introduce Triangle Splatting+, which directly optimizes triangles, the fundamental primitive of computer graphics, within a differentiable splatting framework. We formulate triangle parametrization to enable connectivity through shared vertices, and we design a training strategy that enforces opaque triangles. The final output is immediately usable in standard graphics engines without post-processing. Experiments on the Mip-NeRF360 and Tanks & Temples datasets show that Triangle Splatting+achieves state-of-the-art performance in mesh-based novel view synthesis. Our method surpasses prior splatting approaches in visual fidelity while remaining efficient and fast to training. Moreover, the resulting semi-connected meshes support downstream applications such as physics-based simulation or interactive walkthroughs. The project page is https://trianglesplatting2.github.io/trianglesplatting2/.

2025-09-29T17:43:46Z 9 pages, 6 figures, 2 tables Jan Held Renaud Vandeghen Sanghyun Son Daniel Rebain Matheus Gadelha Yi Zhou Ming C. Lin Marc Van Droogenbroeck Andrea Tagliasacchi http://arxiv.org/abs/2509.21702v1 2025-09-25T23:52:38Z

3D Gaussian Splatting (3DGS) combines classic image-based rendering, pointbased graphics, and modern differentiable techniques, and offers an interesting alternative to traditional physically-based rendering. 3DGS-family models are far from efficient for power-constrained Extended Reality (XR) devices, which need to operate at a Watt-level. This paper introduces PowerGS, the first framework to jointly minimize the rendering and display power in 3DGS under a quality constraint. We present a general problem formulation and show that solving the problem amounts to 1) identifying the iso-quality curve(s) in the landscape subtended by the display and rendering power and 2) identifying the power-minimal point on a given curve, which has a closed-form solution given a proper parameterization of the curves. PowerGS also readily supports foveated rendering for further power savings. Extensive experiments and user studies show that PowerGS achieves up to 86% total power reduction compared to state-of-the-art 3DGS models, with minimal loss in both subjective and objective quality. Code is available at https://github.com/horizon-research/PowerGS.

2025-09-25T23:52:38Z 10 pages, Accepted to Siggraph Asia 2025 Weikai Lin Sushant Kondguli Carl Marshall Yuhao Zhu http://arxiv.org/abs/2509.19726v1 2025-09-24T03:09:52Z

Efficient shape reconstruction for surfaces with complex reflectance properties is crucial for real-time virtual reality. While 3D Gaussian Splatting (3DGS)-based methods offer fast novel view rendering by leveraging their explicit surface representation, their reconstruction quality lags behind that of implicit neural representations, particularly in the case of recovering surfaces with complex reflective reflectance. To address these problems, we propose PolGS, a Polarimetric Gaussian Splatting model allowing fast reflective surface reconstruction in 10 minutes. By integrating polarimetric constraints into the 3DGS framework, PolGS effectively separates specular and diffuse components, enhancing reconstruction quality for challenging reflective materials. Experimental results on the synthetic and real-world dataset validate the effectiveness of our method.

2025-09-24T03:09:52Z Accepted by ICCV 2025 Yufei Han Bowen Tie Heng Guo Youwei Lyu Si Li Boxin Shi Yunpeng Jia Zhanyu Ma http://arxiv.org/abs/2509.16922v1 2025-09-21T05:01:54Z

Audio-driven talking head generation is crucial for applications in virtual reality, digital avatars, and film production. While NeRF-based methods enable high-fidelity reconstruction, they suffer from low rendering efficiency and suboptimal audio-visual synchronization. This work presents PGSTalker, a real-time audio-driven talking head synthesis framework based on 3D Gaussian Splatting (3DGS). To improve rendering performance, we propose a pixel-aware density control strategy that adaptively allocates point density, enhancing detail in dynamic facial regions while reducing redundancy elsewhere. Additionally, we introduce a lightweight Multimodal Gated Fusion Module to effectively fuse audio and spatial features, thereby improving the accuracy of Gaussian deformation prediction. Extensive experiments on public datasets demonstrate that PGSTalker outperforms existing NeRF- and 3DGS-based approaches in rendering quality, lip-sync precision, and inference speed. Our method exhibits strong generalization capabilities and practical potential for real-world deployment.

2025-09-21T05:01:54Z Main paper (15 pages). Accepted for publication by ICONIP( International Conference on Neural Information Processing) 2025 Tianheng Zhu Yinfeng Yu Liejun Wang Fuchun Sun Wendong Zheng http://arxiv.org/abs/2509.07774v1 2025-09-09T14:08:41Z

Human hair reconstruction is a challenging problem in computer vision, with growing importance for applications in virtual reality and digital human modeling. Recent advances in 3D Gaussians Splatting (3DGS) provide efficient and explicit scene representations that naturally align with the structure of hair strands. In this work, we extend the 3DGS framework to enable strand-level hair geometry reconstruction from multi-view images. Our multi-stage pipeline first reconstructs detailed hair geometry using a differentiable Gaussian rasterizer, then merges individual Gaussian segments into coherent strands through a novel merging scheme, and finally refines and grows the strands under photometric supervision. While existing methods typically evaluate reconstruction quality at the geometric level, they often neglect the connectivity and topology of hair strands. To address this, we propose a new evaluation metric that serves as a proxy for assessing topological accuracy in strand reconstruction. Extensive experiments on both synthetic and real-world datasets demonstrate that our method robustly handles a wide range of hairstyles and achieves efficient reconstruction, typically completing within one hour. The project page can be found at: https://yimin-pan.github.io/hair-gs/

2025-09-09T14:08:41Z This is the arXiv preprint of the paper "Hair Strand Reconstruction based on 3D Gaussian Splatting" published at BMVC 2025. Project website: https://yimin-pan.github.io/hair-gs/ Yimin Pan Matthias Nießner Tobias Kirschstein http://arxiv.org/abs/2508.20080v1 2025-08-27T17:46:46Z

360-degree visual content is widely shared on platforms such as YouTube and plays a central role in virtual reality, robotics, and autonomous navigation. However, consumer-grade dual-fisheye systems consistently yield imperfect panoramas due to inherent lens separation and angular distortions. In this work, we introduce a novel calibration framework that incorporates a dual-fisheye camera model into the 3D Gaussian splatting pipeline. Our approach not only simulates the realistic visual artifacts produced by dual-fisheye cameras but also enables the synthesis of seamlessly rendered 360-degree images. By jointly optimizing 3D Gaussian parameters alongside calibration variables that emulate lens gaps and angular distortions, our framework transforms imperfect omnidirectional inputs into flawless novel view synthesis. Extensive evaluations on real-world datasets confirm that our method produces seamless renderings-even from imperfect images-and outperforms existing 360-degree rendering models.

2025-08-27T17:46:46Z Accepted to ICCV 2025. 10 pages main text, 4 figures, 4 tables, supplementary material included Changha Shin Woong Oh Cho Seon Joo Kim http://arxiv.org/abs/2508.13043v1 2025-08-18T16:00:31Z

Novel view synthesis from images, for example, with 3D Gaussian splatting, has made great progress. Rendering fidelity and speed are now ready even for demanding virtual reality applications. However, the problem of assisting humans in collecting the input images for these rendering algorithms has received much less attention. High-quality view synthesis requires uniform and dense view sampling. Unfortunately, these requirements are not easily addressed by human camera operators, who are in a hurry, impatient, or lack understanding of the scene structure and the photographic process. Existing approaches to guide humans during image acquisition concentrate on single objects or neglect view-dependent material characteristics. We propose a novel situated visualization technique for scanning at multiple scales. During the scanning of a scene, our method identifies important objects that need extended image coverage to properly represent view-dependent appearance. To this end, we leverage semantic segmentation and category identification, ranked by a vision-language model. Spherical proxies are generated around highly ranked objects to guide the user during scanning. Our results show superior performance in real scenes compared to conventional view sampling strategies.

2025-08-18T16:00:31Z This work is a pre-print version of a paper that has been accepted to the IEEE International Symposium on Mixed and Augmented Reality for future publication. Project Page: https://mediated-reality.github.io/projects/yasunaga_ismar25/ Ayaka Yasunaga Hideo Saito Dieter Schmalstieg Shohei Mori http://arxiv.org/abs/2508.00354v1 2025-08-01T06:36:19Z

3D Gaussian Splats (3DGSs) are 3D object models derived from multi-view images. Such "digital twins" are useful for simulations, virtual reality, marketing, robot policy fine-tuning, and part inspection. 3D object scanning usually requires multi-camera arrays, precise laser scanners, or robot wrist-mounted cameras, which have restricted workspaces. We propose Omni-Scan, a pipeline for producing high-quality 3D Gaussian Splat models using a bi-manual robot that grasps an object with one gripper and rotates the object with respect to a stationary camera. The object is then re-grasped by a second gripper to expose surfaces that were occluded by the first gripper. We present the Omni-Scan robot pipeline using DepthAny-thing, Segment Anything, as well as RAFT optical flow models to identify and isolate objects held by a robot gripper while removing the gripper and the background. We then modify the 3DGS training pipeline to support concatenated datasets with gripper occlusion, producing an omni-directional (360 degree view) model of the object. We apply Omni-Scan to part defect inspection, finding that it can identify visual or geometric defects in 12 different industrial and household objects with an average accuracy of 83%. Interactive videos of Omni-Scan 3DGS models can be found at https://berkeleyautomation.github.io/omni-scan/

2025-08-01T06:36:19Z Tianshuang Qiu Zehan Ma Karim El-Refai Hiya Shah Chung Min Kim Justin Kerr Ken Goldberg http://arxiv.org/abs/2507.16406v1 2025-07-22T09:57:28Z

Sparse-view 3D reconstruction is essential for applications in which dense image acquisition is impractical, such as robotics, augmented/virtual reality (AR/VR), and autonomous systems. In these settings, minimal image overlap prevents reliable correspondence matching, causing traditional methods, such as structure-from-motion (SfM) and multiview stereo (MVS), to fail. This survey reviews the latest advances in neural implicit models (e.g., NeRF and its regularized versions), explicit point-cloud-based approaches (e.g., 3D Gaussian Splatting), and hybrid frameworks that leverage priors from diffusion and vision foundation models (VFMs).We analyze how geometric regularization, explicit shape modeling, and generative inference are used to mitigate artifacts such as floaters and pose ambiguities in sparse-view settings. Comparative results on standard benchmarks reveal key trade-offs between the reconstruction accuracy, efficiency, and generalization. Unlike previous reviews, our survey provides a unified perspective on geometry-based, neural implicit, and generative (diffusion-based) methods. We highlight the persistent challenges in domain generalization and pose-free reconstruction and outline future directions for developing 3D-native generative priors and achieving real-time, unconstrained sparse-view reconstruction.

2025-07-22T09:57:28Z 30 pages, 6 figures Tanveer Younis Zhanglin Cheng