Stereo correspondence by surface reconstruction

An algorithm that solves the computational stereo correspondence and the surface reconstruction is presented. The algorithm integrates the reconstruction process in the correspondence analysis by means of multipass attribute matching and disparity refinement. In the matching process, the requirement of attribute similarity is relaxed with the pass number while the requirement for agreement between the predicted and the measured disparity is tightened. Disparity discontinuities and occluded areas are detected by analyzing the partial derivatives of the reconstructed disparity surface. Results on synthetic and on real stereo image pairs are reported.< >