Adaptive fusion of shape from shading and photometric stereo

Abstract

So far, a lot of studies have been made in the areas of shape from shading (SFS) and photometric stereo. In these studies, different methods are usually applied separately. In some of these studies, different methods were combined to obtain better results. In this study, a new approach is proposed to combined adaptively the SFS and photometric stereo methods. The depth map obtained from the SFS approach is appropriate to bring out the details. In photometric stereo aproach, rough surface information is obtained better than the other approaches. In the proposed method, best features of both methods are combined in an appropriate manner. Errors in the depth map obtained from experimental studies were examined and it is seen that the proposed method works successfully.