PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913906659688448 |
|---|---|
| author | Jin, Chuhao Li, Haosen Zhang, Bingzi Liu, Che Wang, Xiting Song, Ruihua Huang, Wenbing Qin, Ying Zhang, Fuzheng Zhang, Di |
| author_facet | Jin, Chuhao Li, Haosen Zhang, Bingzi Liu, Che Wang, Xiting Song, Ruihua Huang, Wenbing Qin, Ying Zhang, Fuzheng Zhang, Di |
| contents | Recent advances in large language models (LLMs) have enabled breakthroughs in many multimodal generation tasks, but a significant performance gap still exists in text-to-motion generation, where LLM-based methods lag far behind non-LLM methods. We identify the granularity of motion tokenization as a critical bottleneck: fine-grained tokenization induces local dependency issues, where LLMs overemphasize short-term coherence at the expense of global semantic alignment, while coarse-grained tokenization sacrifices motion details. To resolve this issue, we propose PlanMoGPT, an LLM-based framework integrating progressive planning and flow-enhanced fine-grained motion tokenization. First, our progressive planning mechanism leverages LLMs' autoregressive capabilities to hierarchically generate motion tokens by starting from sparse global plans and iteratively refining them into full sequences. Second, our flow-enhanced tokenizer doubles the downsampling resolution and expands the codebook size by eight times, minimizing detail loss during discretization, while a flow-enhanced decoder recovers motion nuances. Extensive experiments on text-to-motion benchmarks demonstrate that it achieves state-of-the-art performance, improving FID scores by 63.8% (from 0.380 to 0.141) on long-sequence generation while enhancing motion diversity by 49.9% compared to existing methods. The proposed framework successfully resolves the diversity-quality trade-off that plagues current non-LLM approaches, establishing new standards for text-to-motion generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_17912 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesis Jin, Chuhao Li, Haosen Zhang, Bingzi Liu, Che Wang, Xiting Song, Ruihua Huang, Wenbing Qin, Ying Zhang, Fuzheng Zhang, Di Computer Vision and Pattern Recognition Multimedia Recent advances in large language models (LLMs) have enabled breakthroughs in many multimodal generation tasks, but a significant performance gap still exists in text-to-motion generation, where LLM-based methods lag far behind non-LLM methods. We identify the granularity of motion tokenization as a critical bottleneck: fine-grained tokenization induces local dependency issues, where LLMs overemphasize short-term coherence at the expense of global semantic alignment, while coarse-grained tokenization sacrifices motion details. To resolve this issue, we propose PlanMoGPT, an LLM-based framework integrating progressive planning and flow-enhanced fine-grained motion tokenization. First, our progressive planning mechanism leverages LLMs' autoregressive capabilities to hierarchically generate motion tokens by starting from sparse global plans and iteratively refining them into full sequences. Second, our flow-enhanced tokenizer doubles the downsampling resolution and expands the codebook size by eight times, minimizing detail loss during discretization, while a flow-enhanced decoder recovers motion nuances. Extensive experiments on text-to-motion benchmarks demonstrate that it achieves state-of-the-art performance, improving FID scores by 63.8% (from 0.380 to 0.141) on long-sequence generation while enhancing motion diversity by 49.9% compared to existing methods. The proposed framework successfully resolves the diversity-quality trade-off that plagues current non-LLM approaches, establishing new standards for text-to-motion generation. |
| title | PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesis |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2506.17912 |