FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility

• URL: http://arxiv.org/abs/2607.19100v1
• Date: Tue, 21 Jul 2026 13:43:31 GMT
• Title: FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility
• Abstract summary: We introduce FlexiAvatar, a unified framework that explicitly optimize only the visible body regions.<n>Our method integrates occlusion-robust SMPL-X tracking with part-specific residual refinement to capture high-frequency geometric and appearance details.<n>Experiments on full-body (NeuMan), upper/half-body (talk-show clips), and head-only (INSTA) inputs show that FlexiAvatar delivers consistently higher reconstruction quality.
• Score: 14.672501057469878
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Reconstructing animatable 3D human avatars from monocular video is a fundamental problem in computer vision with broad applications in AR/VR and digital content creation. Existing approaches typically couple parametric body models with neural rendering or 3D Gaussian splatting and optimize all body regions jointly from short videos, which often degrades fidelity in the visible areas. To overcome this limitation, we introduce FlexiAvatar, a unified framework that explicitly optimizes only the visible body regions, effectively eliminating artifacts arising from unobserved limbs. Our method integrates occlusion-robust SMPL-X tracking with part-specific residual refinement to capture high-frequency geometric and appearance details. To complete entirely unseen regions (e.g., back views), we leverage a diffusion-based approach to generate texture consistent with the observed appearance. Experiments on full-body (NeuMan, ZJU-MoCap, WildAvatar), upper/half-body (talk-show clips), and head-only (INSTA) inputs show that FlexiAvatar delivers consistently higher reconstruction quality, outperforming state-of-the-art methods by an average PSNR improvement of approximately 3% across datasets. Finally, by restricting optimization to observed regions, our method reduces the effective number of Gaussians that must be optimized and rendered, leading to reduced runtime and memory overhead in partial-visibility scenarios.

Related papers

• Intrinsic Geometry-Appearance Consistency Optimization for Sparse-View Gaussian Splatting [36.3168821104293]
  3D human reconstruction from a single image is a challenging problem.<n>We present emphMVD-HuGaS, enabling free-view 3D human rendering from a single image via a multi-view human diffusion model.
  arXiv  Detail & Related papers  (2026-03-03T11:44:46Z)
• FMGS-Avatar: Mesh-Guided 2D Gaussian Splatting with Foundation Model Priors for 3D Monocular Avatar Reconstruction [18.570290675633732]
  We introduce Mesh-Guided 2D Gaussian Splatting, where 2D primitives are attached directly to template mesh faces with constrained position, rotation, and movement.<n>We leverage foundation models trained on large-scale datasets, such as Sapiens, to complement the limited visual cues from monocular videos.<n> Experimental evaluation demonstrates superior reconstruction quality compared to existing methods, with notable gains in geometric accuracy and appearance fidelity.
  arXiv  Detail & Related papers  (2025-09-18T08:41:41Z)
• Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting [95.61137026932062]
  Intern-GS is a novel approach to enhance the process of sparse-view Gaussian splatting.<n>We show that Intern-GS achieves state-of-the-art rendering quality across diverse datasets.
  arXiv  Detail & Related papers  (2025-05-27T05:17:49Z)
• TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling [52.87836237427514]
  Photoreal avatars are seen as a key component in emerging applications in telepresence, extended reality, and entertainment.<n>We present a new high-detail 3D head avatar model that improves upon the state of the art.
  arXiv  Detail & Related papers  (2025-05-08T22:10:27Z)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction [86.87464903285208]
  We introduce MonoGSDF, a novel method that couples primitives with a neural Signed Distance Field (SDF) for high-quality reconstruction.<n>To handle arbitrary-scale scenes, we propose a scaling strategy for robust generalization.<n>Experiments on real-world datasets outperforms prior methods while maintaining efficiency.
  arXiv  Detail & Related papers  (2024-11-25T20:07:07Z)
• EVA-Gaussian: 3D Gaussian-based Real-time Human Novel View Synthesis under Diverse Multi-view Camera Settings [11.248908608011941]
  3D Gaussian Splatting methods have demonstrated exceptional capability in real-time novel view synthesis for human models.<n>We propose a novel pipeline named EVA-Gaussian for 3D human novel view synthesis across diverse multi-view camera settings.
  arXiv  Detail & Related papers  (2024-10-02T11:23:08Z)
• Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping [12.308192525760667]
  Existing methods only reconstruct a head without the body, substantially limiting their application scenarios. We propose to model the body part with a neural texture that consists of coarse and pose-dependent fine colors. We demonstrate that Gaussian Head & Shoulders can fit the high-frequency details on the clothed upper body with high fidelity and potentially improve the accuracy and fidelity of the head region.
  arXiv  Detail & Related papers  (2024-05-20T14:39:49Z)
• OccGaussian: 3D Gaussian Splatting for Occluded Human Rendering [55.50438181721271]
  Previous method utilizing NeRF for surface rendering to recover the occluded areas requires more than one day to train and several seconds to render occluded areas.<n>We propose OccGaussian based on 3D Gaussian Splatting, which can be trained within 6 minutes and produces high-quality human renderings up to 160 FPS with occluded input.
  arXiv  Detail & Related papers  (2024-04-12T13:00:06Z)
• Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering [71.44349029439944]
  Recent 3D Gaussian Splatting method has achieved the state-of-the-art rendering quality and speed. We introduce Scaffold-GS, which uses anchor points to distribute local 3D Gaussians. We show that our method effectively reduces redundant Gaussians while delivering high-quality rendering.
  arXiv  Detail & Related papers  (2023-11-30T17:58:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.