Abstract

Intrinsic images are a useful midlevel description of scenes proposed by Barrow and Tenebaum [1]. An image is decomposed into two images: a reflectance image and an illumination image. Finding such a decomposition remains a difficult problem in computer vision. Here we focus on a slightly easier problem: given a sequence of T images where the reflectance is constant and the illumination changes, can we recover T illumination images and a single reflectance image? We show that this problem is still ill-posed and suggest approaching it as a maximum-likelihood estimation problem. Following recent work on the statistics of natural images, we use a prior that assumes that illumination images will give rise to sparse filter outputs. We show that this leads to a simple, novel algorithm for recovering reflectance images. We illustrate the algorithm's performance on real and synthetic image sequences.

Citations

683	Emergence of simple-cell receptive field properties by learning a sparse code for natural images - Olshausen, Field - 1996
259	Lightness and retinex theory - Land, McCann - 1971
156	Recovering intrinsic scene characteristics from images - Barrow, Tenenbaum - 1978
116	Statistical models for images: Compression, restoration and synthesis - Simoncelli - 1997
75	From few to many: generative models for recognition under variable pose and illumination - Georghiades, Belhumeur, et al. - 2000
63	Layer extraction from multiple images containing reflections and transparency - Szeliksi, Avidan, et al. - 2000
58	Photometric stereo under a light source with arbitrary motion - Hayakawa - 1994
56	Determining generative models of objects under varying illumination: Shape and albedo from multiple images using svd and integrability - Yuille, Snow, et al. - 1999
42	Construction and Refinement of Panoramic Mosaics with Global and Local Alignment - Shum, Szeliski - 1998
40	Separating reflections from images by use of independent components analysis - Farid, Adelson - 1999
35	Recovering shading from color images - Funt, Drew, et al. - 1992
12	Bayesian model of surface perception - Freeman, Viola - 1997