In this paper, a novel method of surface reconstruction from a single monocular image is proposed. Our proposed approach (called "shape from object-specific knowledge") is based on knowledge of objects, acquired by learning from a number of samples. To achieve this, we investigate the use of the Subband Pseudo 2D Hidden Markov Model (SPHMM), which is an extended version of normal Pseudo 2D HMMs. SPHMMs can model the correspondence between an intensity image and its depth information. We have applied our algorithm to 3D face, 3D hand, and 3D car reconstruction from single images, and the results show the effectiveness of the proposed method.
ASJC Scopus subject areas