Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper presents a very novel and interesting algorithm for shape-from-shading in unknown illumination. Because SFS is inherently underconstrained even when illumination is known, any SFS algorithm must appeal to some prior assumptions --- usually in the form of smoothness constraints on surfaces. This paper, instead, revives the old notion of the generic viewpoint assumption: that the appearance of an object should be stable under small perturbations. Surprisingly, the authors show that this prior is roughly as effective as a more conventional state-of-the-art shape-from-shading algorithm.