GraphiContact: Pose-aware Human-Scene Robust Contact Perception for Interactive Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908903246135296 |
|---|---|
| author | Lin, Xiaojian Shen, Yaomin Ma, Junyuan Sun, Yujie Bu, Chengqing Zhang, Wenxin Zhang, Zongzheng Fei, Hao Jin, Lei Zhao, Hao |
| author_facet | Lin, Xiaojian Shen, Yaomin Ma, Junyuan Sun, Yujie Bu, Chengqing Zhang, Wenxin Zhang, Zongzheng Fei, Hao Jin, Lei Zhao, Hao |
| contents | Monocular vertex-level human-scene contact prediction is a fundamental capability for interactive systems such as assistive monitoring, embodied AI, and rehabilitation analysis. In this work, we study this task jointly with single-image 3D human mesh reconstruction, using reconstructed body geometry as a scaffold for contact reasoning. Existing approaches either focus on contact prediction without sufficiently exploiting explicit 3D human priors, or emphasize pose/mesh reconstruction without directly optimizing robust vertex-level contact inference under occlusion and perceptual noise. To address this gap, we propose GraphiContact, a pose-aware framework that transfers complementary human priors from two pretrained Transformer encoders and predicts per-vertex human-scene contact on the reconstructed mesh. To improve robustness in real-world scenarios, we further introduce a Single-Image Multi-Infer Uncertainty (SIMU) training strategy with token-level adaptive routing, which simulates occlusion and noisy observations during training while preserving efficient single-branch inference at test time. Experiments on five benchmark datasets show that GraphiContact achieves consistent gains on both contact prediction and 3D human reconstruction. Our code, based on the GraphiContact method, provides comprehensive 3D human reconstruction and interaction analysis, and will be publicly available at https://github.com/Aveiro-Lin/GraphiContact. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_20310 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GraphiContact: Pose-aware Human-Scene Robust Contact Perception for Interactive Systems Lin, Xiaojian Shen, Yaomin Ma, Junyuan Sun, Yujie Bu, Chengqing Zhang, Wenxin Zhang, Zongzheng Fei, Hao Jin, Lei Zhao, Hao Computer Vision and Pattern Recognition Graphics I.4.8; I.4.5; I.3.7 Monocular vertex-level human-scene contact prediction is a fundamental capability for interactive systems such as assistive monitoring, embodied AI, and rehabilitation analysis. In this work, we study this task jointly with single-image 3D human mesh reconstruction, using reconstructed body geometry as a scaffold for contact reasoning. Existing approaches either focus on contact prediction without sufficiently exploiting explicit 3D human priors, or emphasize pose/mesh reconstruction without directly optimizing robust vertex-level contact inference under occlusion and perceptual noise. To address this gap, we propose GraphiContact, a pose-aware framework that transfers complementary human priors from two pretrained Transformer encoders and predicts per-vertex human-scene contact on the reconstructed mesh. To improve robustness in real-world scenarios, we further introduce a Single-Image Multi-Infer Uncertainty (SIMU) training strategy with token-level adaptive routing, which simulates occlusion and noisy observations during training while preserving efficient single-branch inference at test time. Experiments on five benchmark datasets show that GraphiContact achieves consistent gains on both contact prediction and 3D human reconstruction. Our code, based on the GraphiContact method, provides comprehensive 3D human reconstruction and interaction analysis, and will be publicly available at https://github.com/Aveiro-Lin/GraphiContact. |
| title | GraphiContact: Pose-aware Human-Scene Robust Contact Perception for Interactive Systems |
| topic | Computer Vision and Pattern Recognition Graphics I.4.8; I.4.5; I.3.7 |
| url | https://arxiv.org/abs/2603.20310 |