English

Deep Learning Methods for Calibrated Photometric Stereo and Beyond

Computer Vision and Pattern Recognition 2024-02-02 v2 Artificial Intelligence

Abstract

Photometric stereo recovers the surface normals of an object from multiple images with varying shading cues, i.e., modeling the relationship between surface orientation and intensity at each pixel. Photometric stereo prevails in superior per-pixel resolution and fine reconstruction details. However, it is a complicated problem because of the non-linear relationship caused by non-Lambertian surface reflectance. Recently, various deep learning methods have shown a powerful ability in the context of photometric stereo against non-Lambertian surfaces. This paper provides a comprehensive review of existing deep learning-based calibrated photometric stereo methods. We first analyze these methods from different perspectives, including input processing, supervision, and network architecture. We summarize the performance of deep learning photometric stereo models on the most widely-used benchmark data set. This demonstrates the advanced performance of deep learning-based photometric stereo methods. Finally, we give suggestions and propose future research trends based on the limitations of existing models.

Keywords

Cite

@article{arxiv.2212.08414,
  title  = {Deep Learning Methods for Calibrated Photometric Stereo and Beyond},
  author = {Yakun Ju and Kin-Man Lam and Wuyuan Xie and Huiyu Zhou and Junyu Dong and Boxin Shi},
  journal= {arXiv preprint arXiv:2212.08414},
  year   = {2024}
}

Comments

19 pages, 11 figures, 4 tables

R2 v1 2026-06-28T07:38:49.669Z