Learning to Minify Photometric Stereo
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.
Cite
Text
Li et al. "Learning to Minify Photometric Stereo." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00775Markdown
[Li et al. "Learning to Minify Photometric Stereo." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/li2019cvpr-learning-d/) doi:10.1109/CVPR.2019.00775BibTeX
@inproceedings{li2019cvpr-learning-d,
title = {{Learning to Minify Photometric Stereo}},
author = {Li, Junxuan and Robles-Kelly, Antonio and You, Shaodi and Matsushita, Yasuyuki},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.00775},
url = {https://mlanthology.org/cvpr/2019/li2019cvpr-learning-d/}
}