Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining

TL;DR

This paper introduces a novel cross-scale non-local attention module for single image super-resolution, leveraging cross-scale feature correlations within a single low-resolution image to significantly improve reconstruction quality.

Contribution

It proposes the first cross-scale non-local attention mechanism integrated into a recurrent network for enhanced super-resolution performance.

Findings

Achieves new state-of-the-art results on multiple benchmarks.

Effectively models cross-scale feature correlations within LR images.

Demonstrates significant performance gains over existing methods.

Abstract

Deep convolution-based single image super-resolution (SISR) networks embrace the benefits of learning from large-scale external image resources for local recovery, yet most existing works have ignored the long-range feature-wise similarities in natural images. Some recent works have successfully leveraged this intrinsic feature correlation by exploring non-local attention modules. However, none of the current deep models have studied another inherent property of images: cross-scale feature correlation. In this paper, we propose the first Cross-Scale Non-Local (CS-NL) attention module with integration into a recurrent neural network. By combining the new CS-NL prior with local and in-scale non-local priors in a powerful recurrent fusion cell, we can find more cross-scale feature correlations within a single low-resolution (LR) image. The performance of SISR is significantly improved by exhaustively integrating all possible priors. Extensive experiments demonstrate the effectiveness of the proposed CS-NL module by setting new state-of-the-arts on multiple SISR benchmarks.