Multi-scale Grouped Dense Network for VVC Intra Coding

TL;DR

This paper introduces a multi-scale grouped dense network (MSGDN) and a GAN-based variant (MSGDN-GAN) to enhance image quality and reduce artifacts in VVC intra coding, achieving higher PSNR and better subjective quality.

Contribution

The paper proposes a novel MSGDN architecture for post-processing VVC intra-coded images and a GAN extension for improved subjective quality, advancing compression artifact reduction techniques.

Findings

MSGDN achieves an average PSNR of 32.622 at 0.15 bit-rate.

MSGDN-GAN improves subjective visual quality.

The methods outperform traditional post-processing techniques.

Abstract

Versatile Video Coding (H.266/VVC) standard achieves better image quality when keeping the same bits than any other conventional image codec, such as BPG, JPEG, and etc. However, it is still attractive and challenging to improve the image quality with high compression ratio on the basis of traditional coding techniques. In this paper, we design the multi-scale grouped dense network (MSGDN) to further reduce the compression artifacts by combining the multi-scale and grouped dense block, which are integrated as the post-process network of VVC intra coding. Besides, to improve the subjective quality of compressed image, we also present a generative adversarial network (MSGDN-GAN) by utilizing our MSGDN as generator. Across the extensive experiments on validation set, our MSGDN trained by MSE losses yields the PSNR of 32.622 on average with teams IMC at the bit-rate of 0.15 in Lowrate track. Moreover, our MSGDN-GAN could achieve the better subjective performance.