DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution

TL;DR

DCS-RISR introduces a dynamic channel splitting method with octave convolution and degradation prediction to efficiently enhance real-world images, balancing quality and resource usage.

Contribution

It proposes a novel adaptive channel splitting scheme with octave convolution and degradation modeling for efficient real-world image super-resolution.

Findings

Achieves superior PSNR and SSIM on benchmark datasets.

Reduces computation and memory costs compared to existing methods.

Effectively handles diverse real-world image degradations.

Abstract

Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation. Existing methods rely on the heavy SR models to enhance low-resolution (LR) images of different degradation levels, which significantly restricts their practical deployments on resource-limited devices. In this paper, we propose a novel Dynamic Channel Splitting scheme for efficient Real-world Image Super-Resolution, termed DCS-RISR. Specifically, we first introduce the light degradation prediction network to regress the degradation vector to simulate the real-world degradations, upon which the channel splitting vector is generated as the input for an efficient SR model. Then, a learnable octave convolution block is proposed to adaptively decide the channel splitting scale for low- and high-frequency features at each block, reducing computation overhead and memory cost by offering the large scale to low-frequency features and the small scale to the high ones. To further improve the RISR performance, Non-local regularization is employed to supplement the knowledge of patches from LR and HR subspace with free-computation inference. Extensive experiments demonstrate the effectiveness of DCS-RISR on different benchmark datasets. Our DCS-RISR not only achieves the best trade-off between computation/parameter and PSNR/SSIM metric, and also effectively handles real-world images with different degradation levels.