从单视频恢复被自遮挡的人体，突破无约束场景重建瓶颈
SOAR: Self-Occluded Avatar Recovery from a Single Video In the Wild
- 用可重构的表面点模型建模人体结构，结合扩散生成先验
- 在多个基准上优于现有重建与生成方法，性能媲美同期工作
- 适合真实场景下人体姿态捕捉与虚拟形象重建应用
在自然场景中捕捉人物时，自遮挡普遍存在，而现有单目人体重建系统通常假设身体完全可见。本文提出自遮挡虚拟人恢复（SOAR），可在部分观测条件下实现完整人体重建，即使身体某些部位完全不可见。SOAR融合结构正则先验与生成式扩散先验：前者采用可重构的表面点模型，保证形状清晰可读；后者通过初始重建并利用得分蒸馏进行优化。在多个基准测试中，SOAR表现优于当前先进重建与生成方法，且与同期工作持平。更多视频结果与代码见 https://soar-avatar.github.io/。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。