Learning to Minify Photometric Stereo

Junxuan Li, Antonio Robles-Kelly, Shaodi You, Yasuyuki Matsushita; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 7568-7576

Abstract


Photometric stereo estimates the surface normal given a set of images acquired under different illumination conditions. To deal with diverse factors involved in the image formation process, recent photometric stereo methods demand a large number of images as input. We propose a method that can dramatically decrease the demands on the number of images by learning the most informative ones under different illumination conditions. To this end, we use a deep learning framework to automatically learn the critical illumination conditions required at input. Furthermore, we present an occlusion layer that can synthesize cast shadows, which effectively improves the estimation accuracy. We assess our method on challenging real-world conditions, where we outperform techniques elsewhere in the literature with a significantly reduced number of light conditions.

Related Material


[pdf]
[bibtex]
@InProceedings{Li_2019_CVPR,
author = {Li, Junxuan and Robles-Kelly, Antonio and You, Shaodi and Matsushita, Yasuyuki},
title = {Learning to Minify Photometric Stereo},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}