Image Gradient-Aided Photometric Stereo Network
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912158790451200 |
|---|---|
| author | Wang, Kaixuan Qi, Lin Qin, Shiyu Luo, Kai Ju, Yakun Li, Xia Dong, Junyu |
| author_facet | Wang, Kaixuan Qi, Lin Qin, Shiyu Luo, Kai Ju, Yakun Li, Xia Dong, Junyu |
| contents | Photometric stereo (PS) endeavors to ascertain surface normals using shading clues from photometric images under various illuminations. Recent deep learning-based PS methods often overlook the complexity of object surfaces. These neural network models, which exclusively rely on photometric images for training, often produce blurred results in high-frequency regions characterized by local discontinuities, such as wrinkles and edges with significant gradient changes. To address this, we propose the Image Gradient-Aided Photometric Stereo Network (IGA-PSN), a dual-branch framework extracting features from both photometric images and their gradients. Furthermore, we incorporate an hourglass regression network along with supervision to regularize normal regression. Experiments on DiLiGenT benchmarks show that IGA-PSN outperforms previous methods in surface normal estimation, achieving a mean angular error of 6.46 while preserving textures and geometric shapes in complex regions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11650 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Image Gradient-Aided Photometric Stereo Network Wang, Kaixuan Qi, Lin Qin, Shiyu Luo, Kai Ju, Yakun Li, Xia Dong, Junyu Computer Vision and Pattern Recognition Photometric stereo (PS) endeavors to ascertain surface normals using shading clues from photometric images under various illuminations. Recent deep learning-based PS methods often overlook the complexity of object surfaces. These neural network models, which exclusively rely on photometric images for training, often produce blurred results in high-frequency regions characterized by local discontinuities, such as wrinkles and edges with significant gradient changes. To address this, we propose the Image Gradient-Aided Photometric Stereo Network (IGA-PSN), a dual-branch framework extracting features from both photometric images and their gradients. Furthermore, we incorporate an hourglass regression network along with supervision to regularize normal regression. Experiments on DiLiGenT benchmarks show that IGA-PSN outperforms previous methods in surface normal estimation, achieving a mean angular error of 6.46 while preserving textures and geometric shapes in complex regions. |
| title | Image Gradient-Aided Photometric Stereo Network |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.11650 |