Statistical Analysis Based H.264 High Profile Deblocking Speedup

This paper proposes a novel scheme to achieve deblocking speedup for H.264 high profile decoders. The proposed approach is to use statistics dependent decoding which takes advantage of the biased statistical distribution in video streams. Specifically, in the proposed scheme, Huffman tree structures are introduced for boundary strength derivation, and hierarchical true edge detection is applied in the boundary filtering process to reduce the computation. As a result, significant computation can be saved in the deblocking process, while bit-exact output is maintained. This platform and encoder independent scheme can be incorporated into both standard conforming encoders and decoders. Since deblocking accounts for a significant percentage of decoding time, the scheme is especially important for decoder implementations. The analyses and experiments show that the proposed scheme could reduce the deblocking computational load by a factor of more than three times.