Shading-Based Image Intrinsics: Derivation and Potential Applications

Shape from shading (SFS) is a classic problem in computer vision, which aims to infer the shape of an object from its shading information in a single image. Since this problem is ill-posed, a number of assumptions have been used extensively in the computer vision community for the SFS problem, such as orthographic projection, Lambertian reflectance model, single light source, and constant surface albedo. In this paper, starting with this typical set of assumptions, we derive new image intrinsic values based on image shading information. We validated the obtained intrinsic values on hundreds of real and synthetic images. Furthermore, we study the effect of intensity and geometric non-linearities (e.g., gamma correction and lens distortion) on the derived image intrinsics. One important application of this study is the possibility of using the image intrinsics to undo some effects of these non-linearities or to correct input images in order to obtain better SFS results