MSF-Net: Multi-Stage Feature Extraction and Fusion for Robust Photometric Stereo
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_ | 1866911239275282432 |
|---|---|
| author | Qin, Shiyu Cai, Zhihao Wang, Kaixuan Qi, Lin Dong, Junyu |
| author_facet | Qin, Shiyu Cai, Zhihao Wang, Kaixuan Qi, Lin Dong, Junyu |
| contents | Photometric stereo is a technique aimed at determining surface normals through the utilization of shading cues derived from images taken under different lighting conditions. However, existing learning-based approaches often fail to accurately capture features at multiple stages and do not adequately promote interaction between these features. Consequently, these models tend to extract redundant features, especially in areas with intricate details such as wrinkles and edges. To tackle these issues, we propose MSF-Net, a novel framework for extracting information at multiple stages, paired with selective update strategy, aiming to extract high-quality feature information, which is critical for accurate normal construction. Additionally, we have developed a feature fusion module to improve the interplay among different features. Experimental results on the DiLiGenT benchmark show that our proposed MSF-Net significantly surpasses previous state-of-the-art methods in the accuracy of surface normal estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_25221 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MSF-Net: Multi-Stage Feature Extraction and Fusion for Robust Photometric Stereo Qin, Shiyu Cai, Zhihao Wang, Kaixuan Qi, Lin Dong, Junyu Computer Vision and Pattern Recognition Photometric stereo is a technique aimed at determining surface normals through the utilization of shading cues derived from images taken under different lighting conditions. However, existing learning-based approaches often fail to accurately capture features at multiple stages and do not adequately promote interaction between these features. Consequently, these models tend to extract redundant features, especially in areas with intricate details such as wrinkles and edges. To tackle these issues, we propose MSF-Net, a novel framework for extracting information at multiple stages, paired with selective update strategy, aiming to extract high-quality feature information, which is critical for accurate normal construction. Additionally, we have developed a feature fusion module to improve the interplay among different features. Experimental results on the DiLiGenT benchmark show that our proposed MSF-Net significantly surpasses previous state-of-the-art methods in the accuracy of surface normal estimation. |
| title | MSF-Net: Multi-Stage Feature Extraction and Fusion for Robust Photometric Stereo |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.25221 |