Part of Advances in Neural Information Processing Systems 15 (NIPS 2002)
Marshall Tappen, William Freeman, Edward Adelson
We present an algorithm that uses multiple cues to recover shading and reﬂectance intrinsic images from a single image. Using both color in- formation and a classiﬁer trained to recognize gray-scale patterns, each image derivative is classiﬁed as being caused by shading or a change in the surface’s reﬂectance. Generalized Belief Propagation is then used to propagate information from areas where the correct classiﬁcation is clear to areas where it is ambiguous. We also show results on real images.