Real Image Restoration via Structure-preserving Complementarity Attention

TL;DR

This paper introduces a lightweight neural network architecture with a novel attention module and gradient-based structure preservation for efficient image denoising, achieving state-of-the-art results with reduced computational complexity.

Contribution

The paper proposes a new lightweight Complementary Attention Module and a gradient-based structure-preserving branch for improved denoising performance.

Findings

Achieves state-of-the-art PSNR and SSIM on SIDD and DND benchmarks.

Reduces computational cost compared to existing methods.

Effectively preserves structural details in denoised images.

Abstract

Since convolutional neural networks perform well in learning generalizable image priors from large-scale data, these models have been widely used in image denoising tasks. However, the computational complexity increases dramatically as well on complex model. In this paper, We propose a novel lightweight Complementary Attention Module, which includes a density module and a sparse module, which can cooperatively mine dense and sparse features for feature complementary learning to build an efficient lightweight architecture. Moreover, to reduce the loss of details caused by denoising, this paper constructs a gradient-based structure-preserving branch. We utilize gradient-based branches to obtain additional structural priors for denoising, and make the model pay more attention to image geometric details through gradient loss optimization.Based on the above, we propose an efficiently Unet structured network with dual branch, the visual results show that can effectively preserve the structural details of the original image, we evaluate benchmarks including SIDD and DND, where SCANet achieves state-of-the-art performance in PSNR and SSIM while significantly reducing computational cost.