PhysDNet: Physics-Guided Decomposition Network of Side-Scan Sonar Imagery
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_ | 1866911284346224640 |
|---|---|
| author | Lei, Can Rajani, Hayat Gracias, Nuno Garcia, Rafael Wang, Huigang |
| author_facet | Lei, Can Rajani, Hayat Gracias, Nuno Garcia, Rafael Wang, Huigang |
| contents | Side-scan sonar (SSS) imagery is widely used for seafloor mapping and underwater remote sensing, yet the measured intensity is strongly influenced by seabed reflectivity, terrain elevation, and acoustic path loss. This entanglement makes the imagery highly view-dependent and reduces the robustness of downstream analysis. In this letter, we present PhysDNet, a physics-guided multi-branch network that decouples SSS images into three interpretable fields: seabed reflectivity, terrain elevation, and propagation loss. By embedding the Lambertian reflection model, PhysDNet reconstructs sonar intensity from these components, enabling self-supervised training without ground-truth annotations. Experiments show that the decomposed representations preserve stable geological structures, capture physically consistent illumination and attenuation, and produce reliable shadow maps. These findings demonstrate that physics-guided decomposition provides a stable and interpretable domain for SSS analysis, improving both physical consistency and downstream tasks such as registration and shadow interpretation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19539 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PhysDNet: Physics-Guided Decomposition Network of Side-Scan Sonar Imagery Lei, Can Rajani, Hayat Gracias, Nuno Garcia, Rafael Wang, Huigang Atmospheric and Oceanic Physics Computer Vision and Pattern Recognition Side-scan sonar (SSS) imagery is widely used for seafloor mapping and underwater remote sensing, yet the measured intensity is strongly influenced by seabed reflectivity, terrain elevation, and acoustic path loss. This entanglement makes the imagery highly view-dependent and reduces the robustness of downstream analysis. In this letter, we present PhysDNet, a physics-guided multi-branch network that decouples SSS images into three interpretable fields: seabed reflectivity, terrain elevation, and propagation loss. By embedding the Lambertian reflection model, PhysDNet reconstructs sonar intensity from these components, enabling self-supervised training without ground-truth annotations. Experiments show that the decomposed representations preserve stable geological structures, capture physically consistent illumination and attenuation, and produce reliable shadow maps. These findings demonstrate that physics-guided decomposition provides a stable and interpretable domain for SSS analysis, improving both physical consistency and downstream tasks such as registration and shadow interpretation. |
| title | PhysDNet: Physics-Guided Decomposition Network of Side-Scan Sonar Imagery |
| topic | Atmospheric and Oceanic Physics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.19539 |