Self-Calibrating Deep Photometric Stereo Networks

Guanying Chen, Kai Han, Boxin Shi, Yasuyuki Matsushita, Kwan-Yee K. Wong; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 8739-8747

Abstract


This paper proposes an uncalibrated photometric stereo method for non-Lambertian scenes based on deep learning. Unlike previous approaches that heavily rely on assumptions of specific reflectances and light source distributions, our method is able to determine both shape and light directions of a scene with unknown arbitrary reflectances observed under unknown varying light directions. To achieve this goal, we propose a two-stage deep learning architecture, called SDPS-Net, which can effectively take advantage of intermediate supervision, resulting in reduced learning difficulty compared to a single-stage model. Experiments on both synthetic and real datasets show that our proposed approach significantly outperforms previous uncalibrated photometric stereo methods.

Related Material


[pdf]
[bibtex]
@InProceedings{Chen_2019_CVPR,
author = {Chen, Guanying and Han, Kai and Shi, Boxin and Matsushita, Yasuyuki and Wong, Kwan-Yee K.},
title = {Self-Calibrating Deep Photometric Stereo Networks},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}