Real Image Restoration via Structure-preserving Complementarity Attention
This addresses efficient image restoration for applications requiring detail preservation, though it appears incremental as it builds on existing CNN and Unet architectures.
The paper tackles real image denoising by proposing SCANet, a lightweight dual-branch network with a Complementary Attention Module and gradient-based structure-preserving branch, achieving state-of-the-art PSNR and SSIM on SIDD and DND benchmarks while reducing computational cost.
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.