Color Constancy Beyond Bags of Pixels
MetadataShow full item record
CitationChakrabarti, Ayan, Keigo Hirakawa, and Todd Zickler. 2008. Color constancy beyond bags of pixels. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska, June 23-28, 2008, ed. IEE CVPR 2008, 1-6. Los Alamitos, California: IEEE.
AbstractEstimating the color of a scene illuminant often plays a central role in computational color constancy. While this problem has received significant attention, the methods that exist do not maximally leverage spatial dependencies between pixels. Indeed, most methods treat the observed color (or its spatial derivative) at each pixel independently of its neighbors. We propose an alternative approach to illuminant estimation-one that employs an explicit statistical model to capture the spatial dependencies between pixels induced by the surfaces they observe. The parameters of this model are estimated from a training set of natural images captured under canonical illumination, and for a new image, an appropriate transform is found such that the corrected image best fits our model.
Citable link to this pagehttp://nrs.harvard.edu/urn-3:HUL.InstRepos:2886301
- FAS Scholarly Articles