Video Compression with CNN-based Post Processing

TL;DR

This paper introduces a CNN-based post-processing method for video compression that improves perceptual quality and achieves significant bit rate savings when integrated with VVC and AV1 standards.

Contribution

The paper presents a novel CNN-based post-processing approach that enhances compressed video quality and reduces bit rates, integrated with leading video coding standards.

Findings

Achieved 4.0% and 5.8% bit rate savings on PSNR-based metrics.

Improved perceptual quality with 13.9% and 10.5% gains using perceptually inspired loss functions.

Consistent coding gains across various sequences and resolutions.

Abstract

In recent years, video compression techniques have been significantly challenged by the rapidly increased demands associated with high quality and immersive video content. Among various compression tools, post-processing can be applied on reconstructed video content to mitigate visible compression artefacts and to enhance overall perceptual quality. Inspired by advances in deep learning, we propose a new CNN-based post-processing approach, which has been integrated with two state-of-the-art coding standards, VVC and AV1. The results show consistent coding gains on all tested sequences at various spatial resolutions, with average bit rate savings of 4.0% and 5.8% against original VVC and AV1 respectively (based on the assessment of PSNR). This network has also been trained with perceptually inspired loss functions, which have further improved reconstruction quality based on perceptual quality assessment (VMAF), with average coding gains of 13.9% over VVC and 10.5% against AV1.