Papers › Rethinking Coarse-to-Fine Approach in Single Image Deblurring

Rethinking Coarse-to-Fine Approach in Single Image Deblurring

11 Aug 2021ICCV 2021 10arXiv:2108.05054archive 2025-07-28

Sung-Jin Cho, Seo-won Ji, Jun-Pyo Hong, Seung-Won Jung, Sung-Jea Ko

Coarse-to-fine strategies have been extensively used for the architecture design of single image deblurring networks. Conventional methods typically stack sub-networks with multi-scale input images and gradually improve sharpness of images from the bottom sub-network to the top sub-network, yielding inevitably high computational costs. Toward a fast and accurate deblurring network design, we revisit the coarse-to-fine strategy and present a multi-input multi-output U-net (MIMO-UNet). The MIMO-UNet has three distinct features. First, the single encoder of the MIMO-UNet takes multi-scale input images to ease the difficulty of training. Second, the single decoder of the MIMO-UNet outputs multiple deblurred images with different scales to mimic multi-cascaded U-nets using a single U-shaped network. Last, asymmetric feature fusion is introduced to merge multi-scale features in an efficient manner. Extensive experiments on the GoPro and RealBlur datasets demonstrate that the proposed network outperforms the state-of-the-art methods in terms of both accuracy and computational complexity. Source code is available for research purposes at https://github.com/chosj95/MIMO-UNet.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2108.05054")

Code

Syntology Ran 1 of 9 code samples harvested from 2 repositories linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 6 samples from 1 repository, 0 ran; community (archive-listed): 3 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

chosj95/mimo-unet officialmentioned in papermentioned on GitHubpytorch report
LKLQQ/MIMO-UNet mentioned on GitHubmindsporeApache-2.0 report
hw666666666666/MIMO-UNet mindsporeNOASSERTION 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

9 samples harvested; 1 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
8unverified

Licence: 6 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

AFF chosj95/mimo-unet/models/MIMOUNet.py official repository unverified no licence file found · pointer only · 022010d7b2ebdef7 · report
DBlock chosj95/mimo-unet/models/MIMOUNet.py official repository unverified no licence file found · pointer only · 2752bd96b49aa01a · report
EBlock chosj95/mimo-unet/models/MIMOUNet.py official repository unverified no licence file found · pointer only · 6442256266f49509 · report
FAM chosj95/mimo-unet/models/MIMOUNet.py official repository unverified no licence file found · pointer only · b7be3cfb21d90f3e · report
MIMOUNet chosj95/mimo-unet/models/MIMOUNet.py official repository unverified no licence file found · pointer only · 2f2607919d29a6bb · report
SCM chosj95/mimo-unet/models/MIMOUNet.py official repository unverified no licence file found · pointer only · c5a460a8a5c0da6a · report
merge LKLQQ/MIMO-UNet/src/config.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · b9e24c3e3e0e88a7 · report
parse_cli_to_yaml LKLQQ/MIMO-UNet/src/config.py community (archive-listed) unverified Apache-2.0 (permissive) · 96d37c643b26e9d8 · report
parse_yaml LKLQQ/MIMO-UNet/src/config.py community (archive-listed) unverified Apache-2.0 (permissive) · 96a9939953d5992d · report

Tasks

DeblurringDecoderImage DeblurringSingle Image Deblurring

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Deblurring GoPro MIMO-UNet++ PSNR 32.68 #32 of 56 Archive leaderboard report
Deblurring GoPro MIMO-UNet++ SSIM 0.959 #32 of 56 Archive leaderboard report
Deblurring RSBlur MIMO-UNet+ Average PSNR 33.37 #10 of 12 Archive leaderboard report
Deblurring RSBlur MIMO-UNet Average PSNR 32.73 #11 of 12 Archive leaderboard report
Deblurring RealBlur-J MIMO-UNet++ PSNR (sRGB) 32.05 #13 of 17 Archive leaderboard report
Deblurring RealBlur-J MIMO-UNet++ Params(M) 16.1 #13 of 17 Archive leaderboard report
Deblurring RealBlur-J MIMO-UNet++ SSIM (sRGB) 0.921 #13 of 17 Archive leaderboard report
Image Deblurring GoPro MIMO-UNet++ PSNR 32.68 #33 of 55 Archive leaderboard report
Image Deblurring GoPro MIMO-UNet++ Params (M) 16.1 #33 of 55 Archive leaderboard report
Image Deblurring GoPro MIMO-UNet++ SSIM 0.959 #33 of 55 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

Concatenated Skip ConnectionConvolutionMax PoolingReLUU-Net

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