English

MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifolds

Computer Vision and Pattern Recognition 2024-09-04 v1

Abstract

Incorporating temporal information effectively is important for accurate 3D human motion estimation and generation which have wide applications from human-computer interaction to AR/VR. In this paper, we present MoManifold, a novel human motion prior, which models plausible human motion in continuous high-dimensional motion space. Different from existing mathematical or VAE-based methods, our representation is designed based on the neural distance field, which makes human dynamics explicitly quantified to a score and thus can measure human motion plausibility. Specifically, we propose novel decoupled joint acceleration manifolds to model human dynamics from existing limited motion data. Moreover, we introduce a novel optimization method using the manifold distance as guidance, which facilitates a variety of motion-related tasks. Extensive experiments demonstrate that MoManifold outperforms existing SOTAs as a prior in several downstream tasks such as denoising real-world human mocap data, recovering human motion from partial 3D observations, mitigating jitters for SMPL-based pose estimators, and refining the results of motion in-betweening.

Keywords

Cite

@article{arxiv.2409.00736,
  title  = {MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifolds},
  author = {Ziqiang Dang and Tianxing Fan and Boming Zhao and Xujie Shen and Lei Wang and Guofeng Zhang and Zhaopeng Cui},
  journal= {arXiv preprint arXiv:2409.00736},
  year   = {2024}
}

Comments

Accepted by BMVC 2024. Supplementary material is included at the end of the main paper (12 pages, 11 figures, 5 tables)