Simultaneous deblocking and error concealment for decoded visual signal

Guangtao Zhai, Xiaokang Yang, Weisi Lin, Wenjun Zhang

Abstract: We propose a unified deblocking/error-concealment algorithm for simultaneously alleviating blockiness and restoring lost blocks. Blockiness and block loss are two of the most frequently encountered artifacts for block-DCT based visual signal coding and transmission. The problem of error-concealment and deblocking is formulated as block-wise expectation estimation processes conditioned on available pixels in a local neighborhood. A nonparametric kernel regression approach is used for approximating the conditional probability and thus the conditional expectation of each image block. Missing blocks are restored and blockiness are suppressed with a single pass of the algorithm. The algorithm is highly efficient in that only block-wise additions and multiplications in pixel domain within a local neighborhood are involved. Experimental results are provided to justify the effectiveness of the proposed unified error-concealment/deblocking algorithm.