Perceptually-inspired super-resolution of compressed videos

TL;DR

This paper introduces a perceptually-inspired super-resolution method for compressed videos that leverages GANs and perceptual loss functions, significantly improving visual quality and reducing bitrate in HEVC-encoded UHD videos.

Contribution

It proposes a novel CNN-based super-resolution approach trained with perceptual loss and GANs, tailored for compressed video enhancement, outperforming traditional pixel-based methods.

Findings

Achieved 35.6% bitrate savings on UHD sequences.

Significant perceptual quality improvement over standard HEVC decoding.

Validated on JVET Common Test Conditions with positive results.

Abstract

Spatial resolution adaptation is a technique which has often been employed in video compression to enhance coding efficiency. This approach encodes a lower resolution version of the input video and reconstructs the original resolution during decoding. Instead of using conventional up-sampling filters, recent work has employed advanced super-resolution methods based on convolutional neural networks (CNNs) to further improve reconstruction quality. These approaches are usually trained to minimise pixel-based losses such as Mean-Squared Error (MSE), despite the fact that this type of loss metric does not correlate well with subjective opinions. In this paper, a perceptually-inspired super-resolution approach (M-SRGAN) is proposed for spatial up-sampling of compressed video using a modified CNN model, which has been trained using a generative adversarial network (GAN) on compressed content with perceptual loss functions. The proposed method was integrated with HEVC HM 16.20, and has been evaluated on the JVET Common Test Conditions (UHD test sequences) using the Random Access configuration. The results show evident perceptual quality improvement over the original HM 16.20, with an average bitrate saving of 35.6% (Bj{\o}ntegaard Delta measurement) based on a perceptual quality metric, VMAF.