ML Anthology

Robust Photometric Stereo Using Sparse Regression

Satoshi Ikehata, David P. Wipf, Yasuyuki Matsushita, Kiyoharu Aizawa
CVPR 2012 pp. 318-325
doi:10.1109/CVPR.2012.6247691 /cvpr/2012/ikehata2012cvpr-robust/

Abstract

This paper presents a robust photometric stereo method that effectively compensates for various non-Lambertian corruptions such as specularities, shadows, and image noise. We construct a constrained sparse regression problem that enforces both Lambertian, rank-3 structure and sparse, additive corruptions. A solution method is derived using a hierarchical Bayesian approximation to accurately estimate the surface normals while simultaneously separating the non-Lambertian corruptions. Extensive evaluations are performed that show state-of-the-art performance using both synthetic and real-world images.

CVPR Semantic Scholar

Cite

Text

Ikehata et al. "Robust Photometric Stereo Using Sparse Regression." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6247691

Markdown

[Ikehata et al. "Robust Photometric Stereo Using Sparse Regression." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/ikehata2012cvpr-robust/) doi:10.1109/CVPR.2012.6247691

BibTeX

@inproceedings{ikehata2012cvpr-robust,
  title     = {{Robust Photometric Stereo Using Sparse Regression}},
  author    = {Ikehata, Satoshi and Wipf, David P. and Matsushita, Yasuyuki and Aizawa, Kiyoharu},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {318-325},
  doi       = {10.1109/CVPR.2012.6247691},
  url       = {https://mlanthology.org/cvpr/2012/ikehata2012cvpr-robust/}
}