Abstract
A methodology for 3D surface modeling from a singleimage is proposed. The principal novelty is concave andspecular surface modeling without any externally imposedprior. The main idea of the method is to use BRDFs andgenerated rendered surfaces, to transfer the normal field,computed for the generated samples, to the unknown surface. The transferred information is adequate to blow andsculpt the segmented image mask in to a bas-relief of theobject. The object surface is further refined basing on a photo-consistency formulation that relates for error minimization the original image and the modeled object.