AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward
This addresses the challenge of generating realistic human motion from complex event-level text prompts, which is an incremental advancement in text-to-motion generation.
The paper tackles the problem of aligning text-to-motion models with event-level textual descriptions by introducing AToM, a framework that uses GPT-4Vision reward to fine-tune an existing model, resulting in significant improvements in alignment quality.
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.