StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Yiheng, Yang, Hui, Luo, Chuanchen, Wang, Yuxi, Xu, Shibiao, Zhang, Zhaoxiang, Zhang, Man, Peng, Junran
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913601625784320
author Huang, Yiheng
Yang, Hui
Luo, Chuanchen
Wang, Yuxi
Xu, Shibiao
Zhang, Zhaoxiang
Zhang, Man
Peng, Junran
author_facet Huang, Yiheng
Yang, Hui
Luo, Chuanchen
Wang, Yuxi
Xu, Shibiao
Zhang, Zhaoxiang
Zhang, Man
Peng, Junran
contents Thanks to the powerful generative capacity of diffusion models, recent years have witnessed rapid progress in human motion generation. Existing diffusion-based methods employ disparate network architectures and training strategies. The effect of the design of each component is still unclear. In addition, the iterative denoising process consumes considerable computational overhead, which is prohibitive for real-time scenarios such as virtual characters and humanoid robots. For this reason, we first conduct a comprehensive investigation into network architectures, training strategies, and inference processs. Based on the profound analysis, we tailor each component for efficient high-quality human motion generation. Despite the promising performance, the tailored model still suffers from foot skating which is an ubiquitous issue in diffusion-based solutions. To eliminate footskate, we identify foot-ground contact and correct foot motions along the denoising process. By organically combining these well-designed components together, we present StableMoFusion, a robust and efficient framework for human motion generation. Extensive experimental results show that our StableMoFusion performs favorably against current state-of-the-art methods. Project page: https://h-y1heng.github.io/StableMoFusion-page/
format Preprint
id arxiv_https___arxiv_org_abs_2405_05691
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework
Huang, Yiheng
Yang, Hui
Luo, Chuanchen
Wang, Yuxi
Xu, Shibiao
Zhang, Zhaoxiang
Zhang, Man
Peng, Junran
Computer Vision and Pattern Recognition
Multimedia
Thanks to the powerful generative capacity of diffusion models, recent years have witnessed rapid progress in human motion generation. Existing diffusion-based methods employ disparate network architectures and training strategies. The effect of the design of each component is still unclear. In addition, the iterative denoising process consumes considerable computational overhead, which is prohibitive for real-time scenarios such as virtual characters and humanoid robots. For this reason, we first conduct a comprehensive investigation into network architectures, training strategies, and inference processs. Based on the profound analysis, we tailor each component for efficient high-quality human motion generation. Despite the promising performance, the tailored model still suffers from foot skating which is an ubiquitous issue in diffusion-based solutions. To eliminate footskate, we identify foot-ground contact and correct foot motions along the denoising process. By organically combining these well-designed components together, we present StableMoFusion, a robust and efficient framework for human motion generation. Extensive experimental results show that our StableMoFusion performs favorably against current state-of-the-art methods. Project page: https://h-y1heng.github.io/StableMoFusion-page/
title StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2405.05691