Unsupervised Color Constancy

Part of Advances in Neural Information Processing Systems 15 (NIPS 2002)

Bibtex Metadata Paper


Kinh Tieu, Erik Miller


In [1] we introduced a linear statistical model of joint color changes in images due to variation in lighting and certain non-geometric camera pa- rameters. We did this by measuring the mappings of colors in one image of a scene to colors in another image of the same scene under different lighting conditions. Here we increase the flexibility of this color flow model by allowing flow coefficients to vary according to a low order polynomial over the image. This allows us to better fit smoothly vary- ing lighting conditions as well as curved surfaces without endowing our model with too much capacity. We show results on image matching and shadow removal and detection.