Residual in Residual Based Convolutional Neural Network In-loop Filter for AVS3
Authors:
- 1 November 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Deep learning based video coding tools development has been an emerging topic recently. In this paper, we propose a novel deep convolutional neural network (CNN) based in-loop filter algorithm for the third generation of Audio Video Coding Standard (AVS3). Specifically, we first introduce a residual block based CNN model with global identity connection for the luminance in-loop filter to replace conventional rule-based algorithms in AVS3. Subsequently, the reconstructed luminance channel is deployed as textural and structural guidance for chrominance filtering. The corresponding syntax elements are also designed for the CNN based in-loop filtering. In addition, we build a large scale database for the learning based in-loop filtering algorithm. Experimental results show that our method achieves on average 7.5%, 16.9% and 18.6% BD-rate reduction under all intra (AI) configuration on common test sequences. In particular, the performance for 4K videos is 6.4%, 15.5% and 17.5% respectively. Moreover, under random access (RA) configuration, the proposed method brings 3.3%, 14.4%, and 13.6% BD-rate reduction separately.Keywords
This publication has 18 references indexed in Scilit:
- Spatial-temporal residue network based in-loop filter for video coding2017
- NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study2017
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding2016
- Deep Residual Learning for Image Recognition2016
- The second generation IEEE 1857 video coding standard2015
- Framework of AVS2-video coding2013
- Adaptive Loop Filtering for Video CodingIEEE Journal of Selected Topics in Signal Processing, 2013
- Sample Adaptive Offset in the HEVC StandardIEEE Transactions on Circuits and Systems for Video Technology, 2012
- HEVC Deblocking FilterIEEE Transactions on Circuits and Systems for Video Technology, 2012