High Visual-Fidelity Learned Video Compression

TL;DR

This paper introduces HVFVC, a learned video compression framework that enhances perceptual visual quality by addressing reconstruction and artifact issues, outperforming traditional standards at lower bitrates.

Contribution

The paper proposes a confidence-based feature reconstruction and a periodic compensation loss to improve perceptual quality in learned video compression.

Findings

HVFVC achieves superior perceptual quality compared to VVC.

It requires only 50% of the bitrate used by traditional standards.

The method effectively reduces checkerboard artifacts and improves reconstruction in new regions.

Abstract

With the growing demand for video applications, many advanced learned video compression methods have been developed, outperforming traditional methods in terms of objective quality metrics such as PSNR. Existing methods primarily focus on objective quality but tend to overlook perceptual quality. Directly incorporating perceptual loss into a learned video compression framework is nontrivial and raises several perceptual quality issues that need to be addressed. In this paper, we investigated these issues in learned video compression and propose a novel High Visual-Fidelity Learned Video Compression framework (HVFVC). Specifically, we design a novel confidence-based feature reconstruction method to address the issue of poor reconstruction in newly-emerged regions, which significantly improves the visual quality of the reconstruction. Furthermore, we present a periodic compensation loss to mitigate the checkerboard artifacts related to deconvolution operation and optimization. Extensive experiments have shown that the proposed HVFVC achieves excellent perceptual quality, outperforming the latest VVC standard with only 50% required bitrate.