Shading models for illumination and reflectance invariant shape detectors

Many objects have smooth surfaces of a fairly uniform color, thereby exhibiting shading patterns that reveal information about its shape, an important clue to the nature of the object. This papers explores extracting this information from images, by creating shape detectors based on shading. Recent work has derived low-dimensional models of shading that can handle realistic unknown lighting conditions and surface reflectance properties. We extend this theory by also incorporating variations in the surface shape. In doing so it enables the creation of very general models for the 2D appearance of objects, not only coping with variations in illumination and BRDF but also in shape alterations such as small scale and pose changes. Using this framework we propose a scheme to build shading models that can be used for shape detection in a bottom up fashion without any a priori knowledge about the scene. From the developed theory we construct detectors for two basic shape primitives, spheres and cylinders. Their performance is evaluated by extensive synthetic experiments as well as experiments on real images.