Guanying Chen1 Kai Han2 Boxin Shi3,4 Yasuyuki Matsushita5 Kwan-Yee K. Wong1 |
1The University of Hong Kong 2University of Oxford 3Peking University 4Peng Cheng Laboratory 5Osaka University |
|
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.
|
|
Up to Down: Sample Input, Object, GT Normal, Results of SDPS-Net, and Error Map |
Up to Down: Sample Input, Object, Results of SDPS-Net and UPS-FCN |
Acknowledgments |
Webpage template borrowed from Split-Brain Autoencoders, CVPR 2017.