DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction
Yufu Wang, Evonne Ng, Soyong Shin, Rawal Khirodkar, Yuan Dong, Zhaoen Su, Jinhyung Park, Kris Kitani
Abstract
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/
BibTeX
@inproceedings{cvpr2026_duomodualmotiond,
title = {DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction},
author = {Yufu Wang and Evonne Ng and Soyong Shin and Rawal Khirodkar and Yuan Dong and Zhaoen Su and Jinhyung Park and Kris Kitani and Alexander Richard and Fabian Prada and Michael Zollhöfer},
booktitle = {CVPR 2026},
year = {2026}
}