Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance
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_ | 1866929291097276416 |
|---|---|
| author | Wang, Zan Chen, Yixin Jia, Baoxiong Li, Puhao Zhang, Jinlu Zhang, Jingze Liu, Tengyu Zhu, Yixin Liang, Wei Huang, Siyuan |
| author_facet | Wang, Zan Chen, Yixin Jia, Baoxiong Li, Puhao Zhang, Jinlu Zhang, Jingze Liu, Tengyu Zhu, Yixin Liang, Wei Huang, Siyuan |
| contents | Despite significant advancements in text-to-motion synthesis, generating language-guided human motion within 3D environments poses substantial challenges. These challenges stem primarily from (i) the absence of powerful generative models capable of jointly modeling natural language, 3D scenes, and human motion, and (ii) the generative models' intensive data requirements contrasted with the scarcity of comprehensive, high-quality, language-scene-motion datasets. To tackle these issues, we introduce a novel two-stage framework that employs scene affordance as an intermediate representation, effectively linking 3D scene grounding and conditional motion generation. Our framework comprises an Affordance Diffusion Model (ADM) for predicting explicit affordance map and an Affordance-to-Motion Diffusion Model (AMDM) for generating plausible human motions. By leveraging scene affordance maps, our method overcomes the difficulty in generating human motion under multimodal condition signals, especially when training with limited data lacking extensive language-scene-motion pairs. Our extensive experiments demonstrate that our approach consistently outperforms all baselines on established benchmarks, including HumanML3D and HUMANISE. Additionally, we validate our model's exceptional generalization capabilities on a specially curated evaluation set featuring previously unseen descriptions and scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_18036 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance Wang, Zan Chen, Yixin Jia, Baoxiong Li, Puhao Zhang, Jinlu Zhang, Jingze Liu, Tengyu Zhu, Yixin Liang, Wei Huang, Siyuan Computer Vision and Pattern Recognition Despite significant advancements in text-to-motion synthesis, generating language-guided human motion within 3D environments poses substantial challenges. These challenges stem primarily from (i) the absence of powerful generative models capable of jointly modeling natural language, 3D scenes, and human motion, and (ii) the generative models' intensive data requirements contrasted with the scarcity of comprehensive, high-quality, language-scene-motion datasets. To tackle these issues, we introduce a novel two-stage framework that employs scene affordance as an intermediate representation, effectively linking 3D scene grounding and conditional motion generation. Our framework comprises an Affordance Diffusion Model (ADM) for predicting explicit affordance map and an Affordance-to-Motion Diffusion Model (AMDM) for generating plausible human motions. By leveraging scene affordance maps, our method overcomes the difficulty in generating human motion under multimodal condition signals, especially when training with limited data lacking extensive language-scene-motion pairs. Our extensive experiments demonstrate that our approach consistently outperforms all baselines on established benchmarks, including HumanML3D and HUMANISE. Additionally, we validate our model's exceptional generalization capabilities on a specially curated evaluation set featuring previously unseen descriptions and scenes. |
| title | Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.18036 |