MoMask: Generative Masked Modeling of 3D Human Motions

Chuan Guo; Yuxuan Mu; Muhammad Gohar Javed; Sen Wang; Li Cheng

doi:10.1109/cvpr52733.2024.00186

CVPR2024顶会

MoMask: Generative Masked Modeling of 3D Human Motions

Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Sen Wang, Li Cheng

DOI 出版方

2024年份

162顶会引用

摘要

Walking forward and steps over an object, and then continue walking. Taking two strides forward, pivot swiftly on left foot, and then walk the other way. A person performs a standing back kick. Figure 1 . Our MoMask, when provided with a text input, generates high-quality 3D human motion with diversity and precise control over subtleties such as "two strides forward", "pivot on left foot", and "pivot swiftly".