Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.07456 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912419310206976 |
|---|---|
| author | Yao, Wei Sun, Yunlian Liu, Chang Zhang, Hongwen Tang, Jinhui |
| author_facet | Yao, Wei Sun, Yunlian Liu, Chang Zhang, Hongwen Tang, Jinhui |
| contents | Driven by advancements in motion capture and generative artificial intelligence, leveraging large-scale MoCap datasets to train generative models for synthesizing diverse, realistic human motions has become a promising research direction. However, existing motion-capture techniques and generative models often neglect physical constraints, leading to artifacts such as interpenetration, sliding, and floating. These issues are exacerbated in multi-person motion generation, where complex interactions are involved. To address these limitations, we introduce physical mapping, integrated throughout the human interaction generation pipeline. Specifically, motion imitation within a physics-based simulation environment is used to project target motions into a physically valid space. The resulting motions are adjusted to adhere to real-world physics constraints while retaining their original semantic meaning. This mapping not only improves MoCap data quality but also directly informs post-processing of generated motions. Given the unique interactivity of multi-person scenarios, we propose a tailored motion representation framework. Motion Consistency (MC) and Marker-based Interaction (MI) loss functions are introduced to improve model performance. Experiments show our method achieves impressive results in generated human motion quality, with a 3%-89% improvement in physical fidelity. Project page http://yw0208.github.io/physiinter |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07456 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation Yao, Wei Sun, Yunlian Liu, Chang Zhang, Hongwen Tang, Jinhui Computer Vision and Pattern Recognition Driven by advancements in motion capture and generative artificial intelligence, leveraging large-scale MoCap datasets to train generative models for synthesizing diverse, realistic human motions has become a promising research direction. However, existing motion-capture techniques and generative models often neglect physical constraints, leading to artifacts such as interpenetration, sliding, and floating. These issues are exacerbated in multi-person motion generation, where complex interactions are involved. To address these limitations, we introduce physical mapping, integrated throughout the human interaction generation pipeline. Specifically, motion imitation within a physics-based simulation environment is used to project target motions into a physically valid space. The resulting motions are adjusted to adhere to real-world physics constraints while retaining their original semantic meaning. This mapping not only improves MoCap data quality but also directly informs post-processing of generated motions. Given the unique interactivity of multi-person scenarios, we propose a tailored motion representation framework. Motion Consistency (MC) and Marker-based Interaction (MI) loss functions are introduced to improve model performance. Experiments show our method achieves impressive results in generated human motion quality, with a 3%-89% improvement in physical fidelity. Project page http://yw0208.github.io/physiinter |
| title | PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.07456 |