SOAR：从单段野外视频中恢复自遮挡虚拟化身
SOAR: Self-Occluded Avatar Recovery from a Single Video In the Wild
AI总结：
针对野外单目视频人体自遮挡导致现有重建系统失效的问题，提出结合结构法向先验与生成式扩散先验的SOAR方法，可从局部观测完成人体完整重建，性能优于现有最优方法、与同期工作相当。
摘要：
在野外拍摄人物时，自遮挡现象十分常见，此时表演者不会遵循预设的动作脚本。这对假设全身可见的现有单目人体重建系统构成了挑战。我们提出了自遮挡虚拟化身恢复方法（Self-Occluded Avatar Recovery，SOAR），用于从身体部分完全未被观测到的局部观测结果中完成人体完整重建。SOAR利用结构法向先验和生成式扩散先验来解决这一不适定重建问题。对于结构法向先验，我们采用具有清晰易读形状的可重定位 surfels 模型对人体进行建模。对于生成式扩散先验，我们先执行初始重建，再使用分数蒸馏对其进行优化。在多个基准测试上，我们证明SOAR的性能优于当前最优的重建和生成方法，与同期工作表现相当。更多视频结果和代码可访问https://soar-avatar.github.io/获取。
英文摘要：
Self-occlusion is common when capturing people in the wild, where the performer do not follow predefined motion scripts. This challenges existing monocular human reconstruction systems that assume full body visibility. We introduce Self-Occluded Avatar Recovery (SOAR), a method for complete human reconstruction from partial observations where parts of the body are entirely unobserved. SOAR leverages structural normal prior and generative diffusion prior to address such an ill-posed reconstruction problem. For structural normal prior, we model human with an reposable surfel model with well-defined and easily readable shapes. For generative diffusion prior, we perform an initial reconstruction and refine it using score distillation. On various benchmarks, we show that SOAR performs favorably than state-of-the-art reconstruction and generation methods, and on-par comparing to concurrent works. Additional video results and code are available at https://soar-avatar.github.io/.
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。
