CNN based post-processing to improve HEVC

Chen Li, Li Song, Rong Xie, Wenjun Zhang
September 2017
Cite DOI

Abstract

In this paper, we propose a frame-based dynamic metadata post-processing scheme in HEVC. Video sequence is classified into different categories contains complexity of video content and quality indicator for each frame, an up-to-one byte flag embedded in the bitstream is transferred as side information. Meanwhile dynamic metadata contains classification information indicates the offline training of separate network models. Specifically, we adopt a 20-layers CNN (Con-volutional Neural networks) model to extract more meaningful information from the reconstructed error and improve the filtering performance. Experimental results shows that our proposed post-processing scheme leads on average 1.6% BD-rate reduction compared with HEVC baseline on the six sequences given in 2017 ICIP Grand Challenge.

Type
Conference paper
Publication
2017 IEEE International Conference on Image Processing (ICIP)
"Bit rate" "CNN" "Complexity theory" "Data mining" "dynamic metadata" "Encoding" "HEVC" "image reconstruction" "out-of-loop" "postprocessing" "Silicon" "Training"
Chen Li
Chen Li
PhD Student

I’m a Research PHD candidate at SJTU Media Lab. I’m doing my research on Image/Video Processing, Computer Vision, under the direction of Prof. Li Song.

Li Song
Li Song
Professor, IEEE Senior Member

Professor, Doctoral Supervisor, the Deputy Director of the Institute of Image Communication and Network Engineering of Shanghai Jiao Tong University, the Double-Appointed Professor of the Institute of Artificial Intelligence and the Collaborative Innovation Center of Future Media Network, the Deputy Secretary-General of the China Video User Experience Alliance and head of the standards group.