Papers › Focal Network for Image Restoration

Focal Network for Image Restoration

1 Jan 2023ICCV 2023 1archive 2025-07-28

Yuning Cui, Wenqi Ren, Xiaochun Cao, Alois Knoll

Image restoration aims to reconstruct a sharp image from its degraded counterpart, which plays an important role in many fields. Recently, Transformer models have achieved promising performance on various image restoration tasks. However, their quadratic complexity remains an intractable issue for practical applications. The aim of this study is to develop an efficient and effective framework for image restoration. Inspired by the fact that different regions in a corrupted image always undergo degradations in various degrees, we propose to focus more on the important areas for reconstruction. To this end, we introduce a dual-domain selection mechanism to emphasize crucial information for restoration, such as edge signals and hard regions. In addition, we split high-resolution features to insert multi-scale receptive fields into the network, which improves both efficiency and performance. Finally, the proposed network, dubbed FocalNet, is built by incorporating these designs into a U-shaped backbone. Extensive experiments demonstrate that our model achieves state-of-the-art performance on ten datasets for three tasks, including single-image defocus deblurring, image dehazing, and image desnowing. Our code is available at https://github.com/c-yn/FocalNet.

Paper PDF Code

Code

c-yn/focalnet officialmentioned in paperpytorchMIT 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

Deblurring Image Defocus Deblurring Image Dehazing Image Restoration

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Image Dehazing	SOTS Indoor	FocalNet	PSNR	40.82	#12 of 34	Archive leaderboard	report
Image Dehazing	SOTS Indoor	FocalNet	SSIM	0.996	#12 of 34	Archive leaderboard	report
Image Dehazing	SOTS Outdoor	FocalNet	PSNR	37.71	#11 of 31	Archive leaderboard	report
Image Dehazing	SOTS Outdoor	FocalNet	SSIM	0.995	#11 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 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