Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.09555 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908533184790528 |
|---|---|
| author | Xu, Sirui Li, Dongting Zhang, Yucheng Xu, Xiyan Long, Qi Wang, Ziyin Lu, Yunzhi Dong, Shuchang Jiang, Hezi Gupta, Akshat Wang, Yu-Xiong Gui, Liang-Yan |
| author_facet | Xu, Sirui Li, Dongting Zhang, Yucheng Xu, Xiyan Long, Qi Wang, Ziyin Lu, Yunzhi Dong, Shuchang Jiang, Hezi Gupta, Akshat Wang, Yu-Xiong Gui, Liang-Yan |
| contents | While large-scale human motion capture datasets have advanced human motion generation, modeling and generating dynamic 3D human-object interactions (HOIs) remain challenging due to dataset limitations. Existing datasets often lack extensive, high-quality motion and annotation and exhibit artifacts such as contact penetration, floating, and incorrect hand motions. To address these issues, we introduce InterAct, a large-scale 3D HOI benchmark featuring dataset and methodological advancements. First, we consolidate and standardize 21.81 hours of HOI data from diverse sources, enriching it with detailed textual annotations. Second, we propose a unified optimization framework to enhance data quality by reducing artifacts and correcting hand motions. Leveraging the principle of contact invariance, we maintain human-object relationships while introducing motion variations, expanding the dataset to 30.70 hours. Third, we define six benchmarking tasks and develop a unified HOI generative modeling perspective, achieving state-of-the-art performance. Extensive experiments validate the utility of our dataset as a foundational resource for advancing 3D human-object interaction generation. To support continued research in this area, the dataset is publicly available at https://github.com/wzyabcas/InterAct, and will be actively maintained. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09555 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation Xu, Sirui Li, Dongting Zhang, Yucheng Xu, Xiyan Long, Qi Wang, Ziyin Lu, Yunzhi Dong, Shuchang Jiang, Hezi Gupta, Akshat Wang, Yu-Xiong Gui, Liang-Yan Computer Vision and Pattern Recognition While large-scale human motion capture datasets have advanced human motion generation, modeling and generating dynamic 3D human-object interactions (HOIs) remain challenging due to dataset limitations. Existing datasets often lack extensive, high-quality motion and annotation and exhibit artifacts such as contact penetration, floating, and incorrect hand motions. To address these issues, we introduce InterAct, a large-scale 3D HOI benchmark featuring dataset and methodological advancements. First, we consolidate and standardize 21.81 hours of HOI data from diverse sources, enriching it with detailed textual annotations. Second, we propose a unified optimization framework to enhance data quality by reducing artifacts and correcting hand motions. Leveraging the principle of contact invariance, we maintain human-object relationships while introducing motion variations, expanding the dataset to 30.70 hours. Third, we define six benchmarking tasks and develop a unified HOI generative modeling perspective, achieving state-of-the-art performance. Extensive experiments validate the utility of our dataset as a foundational resource for advancing 3D human-object interaction generation. To support continued research in this area, the dataset is publicly available at https://github.com/wzyabcas/InterAct, and will be actively maintained. |
| title | InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.09555 |