Shape, albedo, and illumination from a single image of an unknown object

We address the problem of recovering shape, albedo, and illumination from a single grayscale image of an object, using shading as our primary cue. Because this problem is fundamentally underconstrained, we construct statistical models of albedo and shape, and define an optimization problem that searches for the most likely explanation of a single image. We present two priors on albedo which encourage local smoothness and global sparsity, and three priors on shape which encourage flatness, outward-facing orientation at the occluding contour, and local smoothness. We present an optimization technique for using these priors to recover shape, albedo, and a spherical harmonic model of illumination. Our model, which we call SAIFS (shape, albedo, and illumination from shading) produces reasonable results on arbitrary grayscale images taken in the real world, and outperforms all previous grayscale "intrinsic image" - style algorithms on the MIT Intrinsic Images dataset.