ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916439651254272 |
|---|---|
| author | Han, Gaoge Liang, Mingjiang Tang, Jinglei Cheng, Yongkang Liu, Wei Huang, Shaoli |
| author_facet | Han, Gaoge Liang, Mingjiang Tang, Jinglei Cheng, Yongkang Liu, Wei Huang, Shaoli |
| contents | Generating human motion from textual descriptions is a challenging task. Existing methods either struggle with physical credibility or are limited by the complexities of physics simulations. In this paper, we present \emph{ReinDiffuse} that combines reinforcement learning with motion diffusion model to generate physically credible human motions that align with textual descriptions. Our method adapts Motion Diffusion Model to output a parameterized distribution of actions, making them compatible with reinforcement learning paradigms. We employ reinforcement learning with the objective of maximizing physically plausible rewards to optimize motion generation for physical fidelity. Our approach outperforms existing state-of-the-art models on two major datasets, HumanML3D and KIT-ML, achieving significant improvements in physical plausibility and motion quality. Project: https://reindiffuse.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07296 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model Han, Gaoge Liang, Mingjiang Tang, Jinglei Cheng, Yongkang Liu, Wei Huang, Shaoli Computer Vision and Pattern Recognition Generating human motion from textual descriptions is a challenging task. Existing methods either struggle with physical credibility or are limited by the complexities of physics simulations. In this paper, we present \emph{ReinDiffuse} that combines reinforcement learning with motion diffusion model to generate physically credible human motions that align with textual descriptions. Our method adapts Motion Diffusion Model to output a parameterized distribution of actions, making them compatible with reinforcement learning paradigms. We employ reinforcement learning with the objective of maximizing physically plausible rewards to optimize motion generation for physical fidelity. Our approach outperforms existing state-of-the-art models on two major datasets, HumanML3D and KIT-ML, achieving significant improvements in physical plausibility and motion quality. Project: https://reindiffuse.github.io/ |
| title | ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.07296 |