10 April 2018 Photometric stereo via random sampling and tensor robust principal component analysis
Author Affiliations +
Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 1061539 (2018) https://doi.org/10.1117/12.2302425
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China
Abstract
In this paper, we propose a method for accurate 3D reconstruction based on Photometric Stereo. Instead of applying the global least square solution on the entire over-determined system, we randomly sample the images to form a set of overlapping groups and recover the surface normal for each group using the least square method. We then employ fourdimensional Tensor Robust Principal Component Analysis (TenRPCA) to obtain the accurate 3D reconstruction. Our method outperforms global least square in handling sparse noises such as shadows and specular highlights. Experiments demonstrate the reconstruction accuracy of our approach.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yakun Ju, Yakun Ju, Lin Qi, Lin Qi, Hao Fan, Hao Fan, Liang Lu, Liang Lu, Junyu Dong, Junyu Dong, } "Photometric stereo via random sampling and tensor robust principal component analysis", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 1061539 (10 April 2018); doi: 10.1117/12.2302425; https://doi.org/10.1117/12.2302425
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT


Back to Top