Papers › Strip Attention for Image Restoration

Strip Attention for Image Restoration

1 Aug 2023IJCAI 2023 8archive 2025-07-28

Yuning Cui, Yi Tao, Luoxi Jing, Alois Knoll

As a long-standing task, image restoration aims to recover the latent sharp image from its degraded counterpart. In recent years, owing to the strong ability of self-attention in capturing longrange dependencies, Transformer based methods have achieved promising performance on multifarious image restoration tasks. However, the canonical self-attention leads to quadratic complexity with respect to input size, hindering its further applications in image restoration. In this paper, we propose a Strip Attention Network (SANet) for image restoration to integrate information in a more efficient and effective manner. Specifically, a strip attention unit is proposed to harvest the contextual information for each pixel from its adjacent pixels in the same row or column. By employing this operation in different directions, each location can perceive information from an expanded region. Furthermore, we apply various receptive fields in different feature groups to enhance representation learning. Incorporating these designs into a U-shaped backbone, our SANet performs favorably against state-of-the-art algorithms on several image restoration tasks. The code is available at https://github. com/c-yn/SANet.

Paper PDF Code

Code

c-yn/SANet pytorchMIT 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

Image Dehazing Image Restoration Representation Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Image Dehazing	SOTS Indoor	SANet	PSNR	40.40	#14 of 34	Archive leaderboard	report
Image Dehazing	SOTS Indoor	SANet	SSIM	0.996	#14 of 34	Archive leaderboard	report
Image Dehazing	SOTS Outdoor	SANet	PSNR	38.01	#9 of 31	Archive leaderboard	report
Image Dehazing	SOTS Outdoor	SANet	SSIM	0.995	#9 of 31	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

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection SANet Softmax Transformer

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