A Class of Photometric Invariants: Separating Material from Shape and Illumination
Abstract
We derive a new class of photometric invariants that can be used for a variety of vision tasks including lighting invariant material segmentation, change detection and tracking, as well as material invariant shape recognition. The key idea is the formulation of a scene radiance model for the class of “separable ” BRDFs, that can be decomposed into material related terms and object shape and lighting related terms. All the proposed invariants are simple rational functions of the appearance parameters (say, material or shape and lighting). The invariants in this class differ from one another in the number and type of image measurements they require. Most of the invariants in this class need changes in illumination or object position between image acquisitions. The invariants can handle large changes in lighting which pose problems for
Cite
Text
Narasimhan et al. "A Class of Photometric Invariants: Separating Material from Shape and Illumination." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238652Markdown
[Narasimhan et al. "A Class of Photometric Invariants: Separating Material from Shape and Illumination." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/narasimhan2003iccv-class/) doi:10.1109/ICCV.2003.1238652BibTeX
@inproceedings{narasimhan2003iccv-class,
title = {{A Class of Photometric Invariants: Separating Material from Shape and Illumination}},
author = {Narasimhan, Srinivasa G. and Ramesh, Visvanathan and Nayar, Shree K.},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2003},
pages = {1387-1394},
doi = {10.1109/ICCV.2003.1238652},
url = {https://mlanthology.org/iccv/2003/narasimhan2003iccv-class/}
}