Breaking Coordinate Overfitting: Geometry-Aware WiFi Sensing for Cross-Layout 3D Pose Estimation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912831574638592 |
|---|---|
| author | Jia, Songming Lu, Yan Liu, Bin Zhang, Xiang Zhao, Peng Tang, Xinmeng Wei, Yelin Huang, Jinyang Yan, Huan Liu, Zhi |
| author_facet | Jia, Songming Lu, Yan Liu, Bin Zhang, Xiang Zhao, Peng Tang, Xinmeng Wei, Yelin Huang, Jinyang Yan, Huan Liu, Zhi |
| contents | WiFi-based 3D human pose estimation offers a low-cost and privacy-preserving alternative to vision-based systems for smart interaction. However, existing approaches rely on visual 3D poses as supervision and directly regress CSI to a camera-based coordinate system. We find that this practice leads to coordinate overfitting: models memorize deployment-specific WiFi transceiver layouts rather than only learning activity-relevant representations, resulting in severe generalization failures. To address this challenge, we present PerceptAlign, the first geometry-conditioned framework for WiFi-based cross-layout pose estimation. PerceptAlign introduces a lightweight coordinate unification procedure that aligns WiFi and vision measurements in a shared 3D space using only two checkerboards and a few photos. Within this unified space, it encodes calibrated transceiver positions into high-dimensional embeddings and fuses them with CSI features, making the model explicitly aware of device geometry as a conditional variable. This design forces the network to disentangle human motion from deployment layouts, enabling robust and, for the first time, layout-invariant WiFi pose estimation. To support systematic evaluation, we construct the largest cross-domain 3D WiFi pose estimation dataset to date, comprising 21 subjects, 5 scenes, 18 actions, and 7 device layouts. Experiments show that PerceptAlign reduces in-domain error by 12.3% and cross-domain error by more than 60% compared to state-of-the-art baselines. These results establish geometry-conditioned learning as a viable path toward scalable and practical WiFi sensing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12252 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Breaking Coordinate Overfitting: Geometry-Aware WiFi Sensing for Cross-Layout 3D Pose Estimation Jia, Songming Lu, Yan Liu, Bin Zhang, Xiang Zhao, Peng Tang, Xinmeng Wei, Yelin Huang, Jinyang Yan, Huan Liu, Zhi Human-Computer Interaction Computer Vision and Pattern Recognition WiFi-based 3D human pose estimation offers a low-cost and privacy-preserving alternative to vision-based systems for smart interaction. However, existing approaches rely on visual 3D poses as supervision and directly regress CSI to a camera-based coordinate system. We find that this practice leads to coordinate overfitting: models memorize deployment-specific WiFi transceiver layouts rather than only learning activity-relevant representations, resulting in severe generalization failures. To address this challenge, we present PerceptAlign, the first geometry-conditioned framework for WiFi-based cross-layout pose estimation. PerceptAlign introduces a lightweight coordinate unification procedure that aligns WiFi and vision measurements in a shared 3D space using only two checkerboards and a few photos. Within this unified space, it encodes calibrated transceiver positions into high-dimensional embeddings and fuses them with CSI features, making the model explicitly aware of device geometry as a conditional variable. This design forces the network to disentangle human motion from deployment layouts, enabling robust and, for the first time, layout-invariant WiFi pose estimation. To support systematic evaluation, we construct the largest cross-domain 3D WiFi pose estimation dataset to date, comprising 21 subjects, 5 scenes, 18 actions, and 7 device layouts. Experiments show that PerceptAlign reduces in-domain error by 12.3% and cross-domain error by more than 60% compared to state-of-the-art baselines. These results establish geometry-conditioned learning as a viable path toward scalable and practical WiFi sensing. |
| title | Breaking Coordinate Overfitting: Geometry-Aware WiFi Sensing for Cross-Layout 3D Pose Estimation |
| topic | Human-Computer Interaction Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.12252 |