DuoMo：用于世界空间人体重建的双运动扩散模型
DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction
把世界坐标运动重建拆成相机空间估计+世界空间精修两个扩散模型，并直接生成网格顶点而非参数化人体模型，这套「先局部估计再全局精修」的因子化思路可迁移到其他需要全局一致性的视频到3D任务（如场景级SLAM式重建、多人交互重建）。
原文依据 The camera-space model first estimates motion from videos in camera coordinates. The world-space model then lifts this initial estimate into world coordinates and refines it to be globally consistent.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 DuoMo，一种从存在噪声或不完整观测的无约束视频中恢复世界坐标系人体运动的生成式方法。重建此类运动需要解决一个根本性权衡：既要能从多样且含噪的视频输入中泛化，又要保持全局运动一致性。我们的方法通过将运动学习分解为两个扩散模型来解决该问题。相机空间模型首先在相机坐标系下从视频中估计运动。世界空间模型随后将该初始估计提升到世界坐标系并进行精修，使其具备全局一致性。两个模型协同工作，能够跨多样场景与轨迹重建运动，即使观测噪声很大或不完整。此外，我们的形式化方法是通用的，可直接生成网格顶点的运动（绕过参数化模型）。DuoMo 取得了最优性能。在 EMDB 上，本方法在世界空间 MPJPE 误差上降低 16%，同时保持较低的脚部滑移；在 RICH 上，世界空间 MPJPE 误差降低 30%。项目主页：yufu-wang.github.io/duomo/
英文原文摘要 1127 字符
We present DuoMo, a generative method that recovers human motion in world-space coordinates from unconstrained videos with noisy or incomplete observations. Reconstructing such motion requires solving a fundamental trade-off: generalizing from diverse and noisy video inputs while maintaining global motion consistency. Our approach addresses this problem by factorizing motion learning into two diffusion models. The camera-space model first estimates motion from videos in camera coordinates. The world-space model then lifts this initial estimate into world coordinates and refines it to be globally consistent. Together, the two models can reconstruct motion across diverse scenes and trajectories, even from highly noisy or incomplete observations. Moreover, our formulation is general, generating the motion of mesh vertices directly (bypassing parametric models). DuoMo achieves state-of-the-art performance. On EMDB, our method obtains a 16% reduction in world-space MPJPE error while maintaining low foot skating. On RICH, it obtains a 30% reduction in world-space MPJPE error. Project page: yufu-wang.github.io/duomo/