CNN based post-processing to improve HEVC
Authors:
- 1 September 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4577-4580
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.Keywords
This publication has 7 references indexed in Scilit:
- A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding2016
- Shot boundary detection using convolutional neural networks2016
- CNN-based in-loop filtering for coding efficiency improvement2016
- Deep Residual Learning for Image Recognition2016
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks2016
- SJTU 4K video subjective quality dataset for content adaptive bit rate estimation without encoding2016
- Caffe2014