LightSphere: fast lighting compensation for matching a 2D image to a 3D model

We describe a fast object recognition method that identifies 2D color image queries among a set of 3D models. It is fast enough for searching a very large database. The main application is face recognition, for which we report very good accuracy over a wide range of pose and lighting conditions. We make weaker assumptions about both lighting and reflectance than are usual. We avoid finding eigenvectors or solving systems of equations. Instead, we use the query to estimate a specialization of the BRDF to the fixed lighting and pose of the query. In a single image pass, we compute a lookup table for re-rendering, which represents expectation values for the action of the light via the BRDF. This yields a similarity measure of the consistency between model and query under the regularity assumptions. We report recognition results on a data set of 42 3D face models and 1764 query images, comprising 7 poses and 6 lighting conditions. The recognition accuracy is indistinguishable from much slower methods, which make stronger assumptions about the BRDF and lighting.