MoCapAnything：从单目视频为任意骨架统一进行三维运动捕捉
MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos
提出以任意绑定三维资产为提示词、从单目视频重建旋转动画的统一框架，其参考提示编码器与约束感知逆运动学拟合可复用于跨物种骨骼动画生成与重定向任务。
原文依据 given a monocular video and an arbitrary rigged 3D asset as a prompt, the goal is to reconstruct a rotation-based animation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论运动捕捉如今支撑的内容创作已远超数字人范畴，但多数流程仍局限于特定物种或模板。我们将这一差距形式化为类别无关运动捕捉（CAMoCap）：给定单目视频和作为提示词的任意绑定三维资产，目标是重建可直接驱动该特定资产的基于旋转的动画（如 BVH）。我们提出 MoCapAnything，一个参考引导的因子化框架，先预测三维关节轨迹，再通过约束感知的逆运动学（IK）拟合恢复资产特定的旋转。MoCapAnything 包含三个可学习模块和一个轻量级 IK 阶段：参考提示编码器从资产的骨架、网格和渲染图像集中提炼逐关节查询；视频特征提取器计算稠密视觉描述符并重建粗略的四维变形网格，以弥合 RGB 词元与类点云关节空间之间的模态差距；统一运动解码器融合这些线索以生成时间连贯的轨迹。我们还整理了 Truebones Zoo，包含 1,038 个运动片段，每个片段提供标准化的骨架-网格-渲染视频三元组。在域内基准和野外视频上的实验表明，MoCapAnything 能生成高质量的骨骼动画，并在异构绑定之间展现出非平凡的跨物种重定向能力，为基于提示词的任意资产三维运动捕捉提供了可扩展的路径。代码可在项目页面获取：https://animotionlab.github.io/MoCapAnything/
英文原文摘要 1561 字符
Motion capture now underpins content creation far beyond digital humans, yet most pipelines remain species- or template-specific. We formalize this gap as Category-Agnostic Motion Capture (CAMoCap): given a monocular video and an arbitrary rigged 3D asset as a prompt, the goal is to reconstruct a rotation-based animation (e.g., BVH) that directly drives the specific asset. We present MoCapAnything, a reference-guided, factorized framework that first predicts 3D joint trajectories and then recovers asset-specific rotations via constraint-aware Inverse Kinematics (IK) Fitting. MoCapAnything comprises three learnable modules and a lightweight IK stage: a Reference Prompt Encoder that distills per-joint queries from the asset's skeleton, mesh, and rendered image set; a Video Feature Extractor that computes dense visual descriptors and reconstructs a coarse 4D deforming mesh to bridge the modality gap between RGB tokens and the point-cloud-like joint space; and a Unified Motion Decoder that fuses these cues to produce temporally coherent trajectories. We also curate Truebones Zoo with 1,038 motion clips, each providing a standardized skeleton-mesh-rendered-video triad. Experiments on in-domain benchmarks and in-the-wild videos show that MoCapAnything delivers high-quality skeletal animations and exhibits non-trivial cross-species retargeting across heterogeneous rigs, offering a scalable path toward prompt-based 3D motion capture for arbitrary assets. The codes are available on our project page: https://animotionlab.github.io/MoCapAnything/