H.264 deblocking speedup

  • Authors:
  • Jian Lou;Ashish Jagmohan;Dake He;Ligang Lu;Ming-Ting Sun

  • Affiliations:
  • Department of Electrical Engineering, University of Washington, Seattle, WA;Department of Multimedia Technologies, IBM T. J. Watson Research Center, Yorktown Heights, NY;Research In Motion, SlipStream, Waterloo, ON, Canada and Department of Multimedia Technologies, IBM T. J. Watson Research Center, Yorktown Heights, NY;Department of Multimedia Technologies, IBM T. J. Watson Research Center, Yorktown Heights, NY;Department of Electrical Engineering, University of Washington, Seattle, WA

  • Venue:
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This letter tackles the problem of reducing the complexity of H.264 decoding. Since deblocking accounts for a significant percentage of H.264 decoding time, our focus is on the H.264 in-loop deblocking filter. Observing that branch operations are costly and that in the deblocking process there are events with significantly high probability of occurrence, we regroup and simplify the branch operations. We apply the idea of Huffman tree optimization to speed up the boundary strength derivation and the true-edge detection by taking advantage of the biased statistical distribution. Our analyses and experiments show that the proposed techniques can reduce the deblocking computation time typically by a factor of more than seven times, while maintaining the bit-exact output.