Super-Resolving Compressed Video in Coding Chain

TL;DR

This paper introduces a mixed-resolution coding framework with a reference-based deep neural network that enhances the resolution of compressed videos by effectively handling artifacts and motion, improving perceptual quality.

Contribution

The paper proposes a novel coding chain integrating a reference-based DCNN with deformable alignment and disentangled loss for superior video super-resolution in compressed videos.

Findings

Outperforms state-of-the-art methods in resolution enhancement

Effectively handles motion and artifacts in compressed videos

Improves perceptual quality of reconstructed videos

Abstract

Scaling and lossy coding are widely used in video transmission and storage. Previous methods for enhancing the resolution of such videos often ignore the inherent interference between resolution loss and compression artifacts, which compromises perceptual video quality. To address this problem, we present a mixed-resolution coding framework, which cooperates with a reference-based DCNN. In this novel coding chain, the reference-based DCNN learns the direct mapping from low-resolution (LR) compressed video to their high-resolution (HR) clean version at the decoder side. We further improve reconstruction quality by devising an efficient deformable alignment module with receptive field block to handle various motion distances and introducing a disentangled loss that helps networks distinguish the artifact patterns from texture. Extensive experiments demonstrate the effectiveness of proposed innovations by comparing with state-of-the-art single image, video and reference-based restoration methods.