An Integrated Segmentation for 3-D Shape Reconstruction from Shading

摘要

To recover 3-D shapes, a new algorithm which is based on the neural-learning-based reflectance model is presented. We present an approach to recovery of 3-D volumetric primitives from a single 2-D image. The approach first take a set of 3-D volumetric modeling primitives and generates a hierarchical aspect representation based on the projected surfaces of the primitives; conditional probabilities capture the ambiguity of mapping between of the hierarchy. The slant and tilt angle at each point of the intensity images which are the inputs for the algorithm is determined from the 3-D reference table. Finally, the 3-D shape of objects is recovered.