This paper describes a CNN-based multi-frame post-processing approach based on a perceptually-inspired Generative Adversarial Network architecture, CVEGAN. This method has been integrated with the Versatile Video Coding Test Model (VTM) 15.2 to enhance the visual quality of the final reconstructed content. The evaluation results on the CLIC 2022 validation sequences show consistent coding gains over the original VVC VTM at the same bitrates when assessed by PSNR. The integrated codec has been submitted to the Challenge on Learned Image Compression (CLIC) 2022 (video track), and the team name associated with this submission is BVI_VC.
@article{arxiv.2205.09458,
title = {Enhancing VVC with Deep Learning based Multi-Frame Post-Processing},
author = {Duolikun Danier and Chen Feng and Fan Zhang and David Bull},
journal= {arXiv preprint arXiv:2205.09458},
year = {2022}
}
Comments
Accepted in CVPR 2022 Workshop and Challenge on Learned Image Compression