Papers › Mixed Hierarchy Network for Image Restoration

Mixed Hierarchy Network for Image Restoration

19 Feb 2023arXiv:2302.09554archive 2025-07-28

Hu Gao, Depeng Dang

Image restoration is a long-standing low-level vision problem, e.g., deblurring and deraining. In the process of image restoration, it is necessary to consider not only the spatial details and contextual information of restoration to ensure the quality, but also the system complexity. Although many methods have been able to guarantee the quality of image restoration, the system complexity of the state-of-the-art (SOTA) methods is increasing as well. Motivated by this, we present a mixed hierarchy network that can balance these competing goals. Our main proposal is a mixed hierarchy architecture, that progressively recovers contextual information and spatial details from degraded images while we design intra-blocks to reduce system complexity. Specifically, our model first learns the contextual information using encoder-decoder architectures, and then combines them with high-resolution branches that preserve spatial detail. In order to reduce the system complexity of this architecture for convenient analysis and comparison, we replace or remove the nonlinear activation function with multiplication and use a simple network structure. In addition, we replace spatial convolution with global self-attention for the middle block of encoder-decoder. The resulting tightly interlinked hierarchy architecture, named as MHNet, delivers strong performance gains on several image restoration tasks, including image deraining, and deblurring.

PaperPDFCode

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

Code

tombs98/mhnet officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

DeblurringDecoderImage DeblurringImage RestorationRain RemovalSingle Image Deraining

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Deblurring GoPro MHNet PSNR 33.04 #29 of 55 Archive leaderboard report
Image Deblurring GoPro MHNet Params (M) 17 #29 of 55 Archive leaderboard report
Image Deblurring HIDE (trained on GOPRO) MHNet PSNR 30.71 #3 of 3 Archive leaderboard report
Single Image Deraining Rain100H MHNet PSNR 30.34 #11 of 19 Archive leaderboard report
Single Image Deraining Rain100L MHNet PSNR 39.47 #4 of 19 Archive leaderboard report
Single Image Deraining Rain100L MHNet SSIM 0.984 #4 of 19 Archive leaderboard report
Single Image Deraining Test100 MHNet PSNR 31.19 #3 of 12 Archive leaderboard report
Single Image Deraining Test100 MHNet SSIM 0.903 #3 of 12 Archive leaderboard report
Single Image Deraining Test1200 MHNet PSNR 33.41 #4 of 14 Archive leaderboard report
Single Image Deraining Test1200 MHNet SSIM 0.924 #4 of 14 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

AttentionConvolutionLinear LayerMulti-Head AttentionSoftmax

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