Learned Image Restoration for VVC Intra Coding

Ming Lu, Tong Chen, Haojie Liu, Zhan Ma; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 0-0

Abstract


We propose a learned image restoration network as the post-processing module for emerging Versatile Video Coding (VVC) Intra Profile (https://jvet.hhi.fraunhofer.de) based image coding to further improve the reconstructed image quality. The image restoration network is designed using multi-scale spatial priors to effectively alleviate compression artifacts in the decoded images induced by the quantization based lossy compression algorithms. Experimental results demonstrate the performance gains of our proposed post-porcessing network with VVC Intra coding, offering about 6.5% Bjontegaard-Delta Rate (BD-Rate) reduction for YUV 4:4:4 and 12.2% for YUV 4:2:0, against the VVC Intra without our restoration network on the Test Dataset P/M released by the Computer Vision Lab of ETH Zurich, where the distortion is Peak Signal to Noise Ratio (PSNR).

Related Material


[pdf]
[bibtex]
@InProceedings{Lu_2019_CVPR_Workshops,
author = {Lu, Ming and Chen, Tong and Liu, Haojie and Ma, Zhan},
title = {Learned Image Restoration for VVC Intra Coding},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}