A Novel Intermediate View Synthesis Method Based on Disparity Estimation

A novel intermediate view synthesis method based on disparity estimation is presented in this paper. Color distance is adopted to set truncation value adaptively when Belief Propagation (BP) algorithm is used in disparity estimation. In view interpolation, the left and right part of the image are divided into three kinds using strong and weak consistency constraints separately. Then different strategy is applied according to the characteristic of each region. Experimental results show that it can synthesize virtual images with high quality.