Disparity estimation using block matching and dynamic programming

In this paper, we present a novel disparity estimation algorithm which is a combination of a block matching part and a dynamic programming part. The block matching gives an initial estimate of the disparity field while the dynamic programming estimates a smooth disparity field. The proposed algorithm is also studied in terms of hardware complexity. The algorithm is tested using real image sequences. The estimated disparity fields are used for the calculation of intermediate views using a simple interpolation/extrapolation algorithm.