AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917850856292352 |
|---|---|
| author | Han, Haonan Wu, Xiangzuo Liao, Huan Xu, Zunnan Hu, Zhongyuan Li, Ronghui Zhang, Yachao Li, Xiu |
| author_facet | Han, Haonan Wu, Xiangzuo Liao, Huan Xu, Zunnan Hu, Zhongyuan Li, Ronghui Zhang, Yachao Li, Xiu |
| contents | Recently, text-to-motion models have opened new possibilities for creating realistic human motion with greater efficiency and flexibility. However, aligning motion generation with event-level textual descriptions presents unique challenges due to the complex relationship between textual prompts and desired motion outcomes. To address this, we introduce AToM, a framework that enhances the alignment between generated motion and text prompts by leveraging reward from GPT-4Vision. AToM comprises three main stages: Firstly, we construct a dataset MotionPrefer that pairs three types of event-level textual prompts with generated motions, which cover the integrity, temporal relationship and frequency of motion. Secondly, we design a paradigm that utilizes GPT-4Vision for detailed motion annotation, including visual data formatting, task-specific instructions and scoring rules for each sub-task. Finally, we fine-tune an existing text-to-motion model using reinforcement learning guided by this paradigm. Experimental results demonstrate that AToM significantly improves the event-level alignment quality of text-to-motion generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_18654 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward Han, Haonan Wu, Xiangzuo Liao, Huan Xu, Zunnan Hu, Zhongyuan Li, Ronghui Zhang, Yachao Li, Xiu Computer Vision and Pattern Recognition Recently, text-to-motion models have opened new possibilities for creating realistic human motion with greater efficiency and flexibility. However, aligning motion generation with event-level textual descriptions presents unique challenges due to the complex relationship between textual prompts and desired motion outcomes. To address this, we introduce AToM, a framework that enhances the alignment between generated motion and text prompts by leveraging reward from GPT-4Vision. AToM comprises three main stages: Firstly, we construct a dataset MotionPrefer that pairs three types of event-level textual prompts with generated motions, which cover the integrity, temporal relationship and frequency of motion. Secondly, we design a paradigm that utilizes GPT-4Vision for detailed motion annotation, including visual data formatting, task-specific instructions and scoring rules for each sub-task. Finally, we fine-tune an existing text-to-motion model using reinforcement learning guided by this paradigm. Experimental results demonstrate that AToM significantly improves the event-level alignment quality of text-to-motion generation. |
| title | AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.18654 |