Papers › Learning Enriched Features via Selective State Spaces Model for Efficient Image Deblurring

Learning Enriched Features via Selective State Spaces Model for Efficient Image Deblurring

29 Mar 2024arXiv:2403.20106archive 2025-07-28

Hu Gao, Depeng Dang

Image deblurring aims to restore a high-quality image from its corresponding blurred. The emergence of CNNs and Transformers has enabled significant progress. However, these methods often face the dilemma between eliminating long-range degradation perturbations and maintaining computational efficiency. While the selective state space model (SSM) shows promise in modeling long-range dependencies with linear complexity, it also encounters challenges such as local pixel forgetting and channel redundancy. To address this issue, we propose an efficient image deblurring network that leverages selective state spaces model to aggregate enriched and accurate features. Specifically, we introduce an aggregate local and global information block (ALGBlock) designed to effectively capture and integrate both local invariant properties and non-local information. The ALGBlock comprises two primary modules: a module for capturing local and global features (CLGF), and a feature aggregation module (FA). The CLGF module is composed of two branches: the global branch captures long-range dependency features via a selective state spaces model, while the local branch employs simplified channel attention to model local connectivity, thereby reducing local pixel forgetting and channel redundancy. In addition, we design a FA module to accentuate the local part by recalibrating the weight during the aggregation of the two branches for restoration. Experimental results demonstrate that the proposed method outperforms state-of-the-art approaches on widely used benchmarks.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Tombs98/ALGNet officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational EfficiencyDeblurringImage DeblurringImage Defocus Deblurring

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Deblurring RealBlur-J ALGNet PSNR (sRGB) 32.94 #5 of 17 Archive leaderboard report
Deblurring RealBlur-J ALGNet SSIM (sRGB) 0.946 #5 of 17 Archive leaderboard report
Deblurring RealBlur-J (trained on GoPro) ALGNet PSNR (sRGB) 29.12 #3 of 15 Archive leaderboard report
Deblurring RealBlur-J (trained on GoPro) ALGNet SSIM (sRGB) 0.886 #3 of 15 Archive leaderboard report
Deblurring RealBlur-R ALGNet PSNR (sRGB) 41.16 #2 of 17 Archive leaderboard report
Deblurring RealBlur-R ALGNet SSIM (sRGB) 0.981 #2 of 17 Archive leaderboard report
Deblurring RealBlur-R (trained on GoPro) ALGNet PSNR (sRGB) 36.35 #2 of 19 Archive leaderboard report
Deblurring RealBlur-R (trained on GoPro) ALGNet SSIM (sRGB) 0.961 #2 of 19 Archive leaderboard report
Image Deblurring GoPro ALGNet-B PSNR 34.05 #7 of 55 Archive leaderboard report
Image Deblurring GoPro ALGNet-B SSIM 0.969 #7 of 55 Archive leaderboard report
Image Deblurring HIDE ALGNet-B PSNR 31.68 #3 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

FA

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections