Papers › Single Stage Adaptive Multi-Attention Network for Image Restoration

Single Stage Adaptive Multi-Attention Network for Image Restoration

10 Apr 2024IEEE Transactions on Image Processing 2024 4archive 2025-07-28

Anas Zafar, Danyal Aftab, Rizwan Qureshi, Xinqi Fan, Pingjun Chen, Jia Wu, Hazrat Ali, Shah Nawaz, Sheheryar Khan, Mubarak Shah

Recently attention-based networks have been successful for image restoration tasks. However, existing methods are either computationally expensive or have limited receptive fields, adding constraints to the model. They are also less resilient in spatial and contextual aspects and lack pixel-to-pixel correspondence, which may degrade feature representations. In this paper, we propose a novel and computationally efficient architecture Single Stage Adaptive Multi-Attention Network (SSAMAN) for image restoration tasks, particularly for image denoising and image deblurring. SSAMAN efficiently addresses computational challenges and expands receptive fields, enhancing robustness in spatial and contextual feature representation. Its Adaptive Multi-Attention Module (AMAM), which consists of Adaptive Pixel Attention Branch (APAB) and an Adaptive Channel Attention Branch (ACAB), uniquely integrates channel and pixel-wise dimensions, significantly improving sensitivity to edges, shapes, and textures. We perform extensive experiments and ablation studies to validate the performance of SSAMAN. Our model shows state-of-the-art results on various benchmarks, for example, on image denoising tasks, SSAMAN achieves a notable 40.08 dB PSNR on SIDD dataset, outperforming Restormer by 0.06 dB PSNR, with 41.02% less computational cost, and achieves a 40.05 dB PSNR on the DND dataset. For image deblurring, SSAMAN achieves 33.53 dB PSNR on GoPro dataset. Code and models are available at Github.

PaperPDFCode

Code

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

DeblurringDenoisingImage DeblurringImage DenoisingImage Restoration

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Denoising DND SSAMAN PSNR (sRGB) 40.05 #3 of 16 Archive leaderboard report
Image Denoising DND SSAMAN SSIM (sRGB) 0.963 #3 of 16 Archive leaderboard report
Image Denoising SIDD SSAMAN PSNR (sRGB) 40.08 #4 of 22 Archive leaderboard report
Image Denoising SIDD SSAMAN SSIM (sRGB) 0.962 #4 of 22 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

Multi-Attention Network

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