InpaintHuman: 通过多尺度UV映射和身份保持扩散修复重建被遮挡的人类
InpaintHuman: Reconstructing Occluded Humans with Multi-Scale UV Mapping and Identity-Preserving Diffusion Inpainting
AI总结：
InpaintHuman通过多尺度UV映射和身份保持扩散修复技术，从被遮挡的单目视频中生成高保真、完整且可动画的3D人类化身。
摘要：
从单目视频中重建完整且可动画化的3D人类化身仍然具有挑战性，特别是在严重遮挡的情况下。虽然3D高斯点云技术已经实现了逼真的人体渲染，但现有方法在面对不完整观察时往往会产生损坏的几何结构和时间不一致的问题。我们提出了InpaintHuman，一种从被遮挡的单目视频中生成高保真、完整且可动画的化身的新方法。我们的方法引入了两个关键创新：(i) 一种多尺度UV参数化表示，具有层次化的粗到细特征插值，使能够稳健地重建被遮挡区域并保持几何细节；(ii) 一个身份保持扩散修复模块，整合了文本倒置与语义条件引导，以实现特定主体、时间一致的完成。与基于SDS的方法不同，我们的方法采用直接像素级监督以确保身份保真度。在合成基准（PeopleSnapshot，ZJU-MoCap）和真实场景（OcMotion）上的实验表明，与一致的改进在多样化的姿态和视角下重建质量。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
