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.
@article{arxiv.2412.11650,
title = {Image Gradient-Aided Photometric Stereo Network},
author = {Kaixuan Wang and Lin Qi and Shiyu Qin and Kai Luo and Yakun Ju and Xia Li and Junyu Dong},
journal= {arXiv preprint arXiv:2412.11650},
year = {2024}
}