SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance
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_ | 1866912256003932160 |
|---|---|
| author | Cong, Peishan Wang, Ziyi Ma, Yuexin Yue, Xiangyu |
| author_facet | Cong, Peishan Wang, Ziyi Ma, Yuexin Yue, Xiangyu |
| contents | Generating reasonable and high-quality human interactive motions in a given dynamic environment is crucial for understanding, modeling, transferring, and applying human behaviors to both virtual and physical robots. In this paper, we introduce an effective method, SemGeoMo, for dynamic contextual human motion generation, which fully leverages the text-affordance-joint multi-level semantic and geometric guidance in the generation process, improving the semantic rationality and geometric correctness of generative motions. Our method achieves state-of-the-art performance on three datasets and demonstrates superior generalization capability for diverse interaction scenarios. The project page and code can be found at https://4dvlab.github.io/project_page/semgeomo/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01291 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance Cong, Peishan Wang, Ziyi Ma, Yuexin Yue, Xiangyu Computer Vision and Pattern Recognition Generating reasonable and high-quality human interactive motions in a given dynamic environment is crucial for understanding, modeling, transferring, and applying human behaviors to both virtual and physical robots. In this paper, we introduce an effective method, SemGeoMo, for dynamic contextual human motion generation, which fully leverages the text-affordance-joint multi-level semantic and geometric guidance in the generation process, improving the semantic rationality and geometric correctness of generative motions. Our method achieves state-of-the-art performance on three datasets and demonstrates superior generalization capability for diverse interaction scenarios. The project page and code can be found at https://4dvlab.github.io/project_page/semgeomo/. |
| title | SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.01291 |