UD-SfPNet: An Underwater Descattering Shape-from-Polarization Network for 3D Normal Reconstruction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917302719479808 |
|---|---|
| author | Wang, Puyun Yu, Kaimin He, Huayang Huang, Feng Wu, Xianyu Chen, Yating |
| author_facet | Wang, Puyun Yu, Kaimin He, Huayang Huang, Feng Wu, Xianyu Chen, Yating |
| contents | Underwater optical imaging is severely hindered by scattering, but polarization imaging offers the unique dual advantages of descattering and shape-from-polarization (SfP) 3D reconstruction. To exploit these advantages, this paper proposes UD-SfPNet, an underwater descattering shape-from-polarization network that leverages polarization cues for improved 3D surface normal prediction. The framework jointly models polarization-based image descattering and SfP normal estimation in a unified pipeline, avoiding error accumulation from sequential processing and enabling global optimization across both tasks. UD-SfPNet further incorporates a novel color embedding module to enhance geometric consistency by exploiting the relationship between color encodings and surface orientation. A detail enhancement convolution module is also included to better preserve high-frequency geometric details that are lost under scattering. Experiments on the MuS-Polar3D dataset show that the proposed method significantly improves reconstruction accuracy, achieving a mean surface normal angular error of 15.12$^\circ$ (the lowest among compared methods). These results confirm the efficacy of combining descattering with polarization-based shape inference, and highlight the practical significance and potential applications of UD-SfPNet for optical 3D imaging in challenging underwater environments. The code is available at https://github.com/WangPuyun/UD-SfPNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00908 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UD-SfPNet: An Underwater Descattering Shape-from-Polarization Network for 3D Normal Reconstruction Wang, Puyun Yu, Kaimin He, Huayang Huang, Feng Wu, Xianyu Chen, Yating Computer Vision and Pattern Recognition Underwater optical imaging is severely hindered by scattering, but polarization imaging offers the unique dual advantages of descattering and shape-from-polarization (SfP) 3D reconstruction. To exploit these advantages, this paper proposes UD-SfPNet, an underwater descattering shape-from-polarization network that leverages polarization cues for improved 3D surface normal prediction. The framework jointly models polarization-based image descattering and SfP normal estimation in a unified pipeline, avoiding error accumulation from sequential processing and enabling global optimization across both tasks. UD-SfPNet further incorporates a novel color embedding module to enhance geometric consistency by exploiting the relationship between color encodings and surface orientation. A detail enhancement convolution module is also included to better preserve high-frequency geometric details that are lost under scattering. Experiments on the MuS-Polar3D dataset show that the proposed method significantly improves reconstruction accuracy, achieving a mean surface normal angular error of 15.12$^\circ$ (the lowest among compared methods). These results confirm the efficacy of combining descattering with polarization-based shape inference, and highlight the practical significance and potential applications of UD-SfPNet for optical 3D imaging in challenging underwater environments. The code is available at https://github.com/WangPuyun/UD-SfPNet. |
| title | UD-SfPNet: An Underwater Descattering Shape-from-Polarization Network for 3D Normal Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.00908 |