Papers › Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring

Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring

7 Dec 2016CVPR 2017 7arXiv:1612.02177archive 2025-07-28

Seungjun Nah, Tae Hyun Kim, Kyoung Mu Lee

Non-uniform blind deblurring for general dynamic scenes is a challenging computer vision problem as blurs arise not only from multiple object motions but also from camera shake, scene depth variation. To remove these complicated motion blurs, conventional energy optimization based methods rely on simple assumptions such that blur kernel is partially uniform or locally linear. Moreover, recent machine learning based methods also depend on synthetic blur datasets generated under these assumptions. This makes conventional deblurring methods fail to remove blurs where blur kernel is difficult to approximate or parameterize (e.g. object motion boundaries). In this work, we propose a multi-scale convolutional neural network that restores sharp images in an end-to-end manner where blur is caused by various sources. Together, we present multi-scale loss function that mimics conventional coarse-to-fine approaches. Furthermore, we propose a new large-scale dataset that provides pairs of realistic blurry image and the corresponding ground truth sharp image that are obtained by a high-speed camera. With the proposed model trained on this dataset, we demonstrate empirically that our method achieves the state-of-the-art performance in dynamic scene deblurring not only qualitatively, but also quantitatively.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 11 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

SeungjunNah/DeepDeblur-PyTorch officialpytorchMITSyntology: 11 samples, 8 ran (0 instrument-failed) · 3 unverified 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

11 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

8ran
3unverified

Licence: 0 of the 11 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 SeungjunNah/DeepDeblur-PyTorch. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

SeungjunNah/DeepDeblur-PyTorch official repository 11 samples, 8 ran (0 instrument-failed) · 3 unverified
decoder in 19 papers src/model/structure.py ran MIT (permissive) · 63d5fc80979f2742 · report fixture: signature out_channels:int/0/int, n_feats:int/0/int · returned Sequential · level recorded 2026-09-25
default_conv in 70 papers src/model/common.py ran MIT (permissive) · 37a49bceb7355edb · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, bias:bool/0/bool, groups:int/0/int · returned Conv2d · level recorded 2026-09-25
default_norm src/model/common.py ran MIT (permissive) · 4e46152975c0143c · report fixture: signature n_feats:int/0/int · returned BatchNorm2d · level recorded 2026-09-25
empty_h src/model/common.py ran MIT (permissive) · 4986decdbcb47823 · report fixture: signature x:Tensor/5/float, n_feats:int/0/int · returned Tensor · level recorded 2026-09-25
encoder in 30 papers src/model/structure.py ran MIT (permissive) · febb4c023ef09ae5 · report fixture: signature in_channels:int/0/int, n_feats:int/0/int · returned Sequential · level recorded 2026-09-25
int2str src/utils.py ran fingerprinted MIT (permissive) · fc6599d8dacc846a · report fixture: signature val:int/0/int · returned str · level recorded 2026-09-25
setup in 24 papers src/option.py ran MIT (permissive) · 1d3b2776cacc0f66 · report fixture: signature args:Namespace/0/? · returned Namespace · level recorded 2026-09-25
str2bool in 533 papers src/utils.py ran MIT (permissive) · 5b79c2dada2b986a · report fixture: signature val:str/0/str · returned bool · level recorded 2026-09-25
ResNet in 139 papers src/model/structure.py unverified MIT (permissive) · 17a9b6e426c0dc58 · report
build_model in 469 papers src/model/MSResNet.py unverified MIT (permissive) · 10d1127a3f643335 · report
build_model in 469 papers src/model/ResNet.py unverified MIT (permissive) · bf5bf2723333f402 · report

Tasks

DeblurringImage Deblurring

Datasets

Introduced by this paper, per the archive.

GoPro

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Deblurring GoPro Nah et al PSNR 29.08 #51 of 56 Archive leaderboard report
Deblurring GoPro Nah et al SSIM 0.9135 #51 of 56 Archive leaderboard report
Deblurring HIDE (trained on GOPRO) Nah et al PSNR (sRGB) 25.73 #26 of 26 Archive leaderboard report
Deblurring RealBlur-R (trained on GoPro) Nah et al SSIM (sRGB) 0.841 #19 of 19 Archive leaderboard report
Image Deblurring GoPro Nah et al PSNR 29.08 #50 of 55 Archive leaderboard report
Image Deblurring GoPro Nah et al SSIM 0.9135 #50 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.

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