Papers › Learning to See in the Dark

Learning to See in the Dark

4 May 2018CVPR 2018 6arXiv:1805.01934archive 2025-07-28

Chen Chen, Qifeng Chen, Jia Xu, Vladlen Koltun

Imaging in low light is challenging due to low photon count and low SNR. Short-exposure images suffer from noise, while long exposure can induce blur and is often impractical. A variety of denoising, deblurring, and enhancement techniques have been proposed, but their effectiveness is limited in extreme conditions, such as video-rate imaging at night. To support the development of learning-based pipelines for low-light image processing, we introduce a dataset of raw short-exposure low-light images, with corresponding long-exposure reference images. Using the presented dataset, we develop a pipeline for processing low-light images, based on end-to-end training of a fully-convolutional network. The network operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. We report promising results on the new dataset, analyze factors that affect performance, and highlight opportunities for future work. The results are shown in the supplementary video at https://youtu.be/qWKUFK7MWvg

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 14 code samples harvested from 5 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 5 repositories, 8 ran (7 with no instrument failure; 1 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

19 repositories listed; official and paper-mentioned ones first.

ashikshafi08/learning_to_see_in_the_dark_Fastai mentioned on GitHubMITSyntology: 2 samples, 0 ran · 2 unverified report
compscikaran/nightlight-web mentioned on GitHubtfSyntology: not harvested report
cydonia999/Learning_to_See_in_the_Dark_PyTorch mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
danilka-na/DegreeWork mentioned on GitHubpytorchSyntology: not harvested report
eoinoreilly30/seeing-in-the-dark mentioned on GitHubtfSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
kauziishere/lowLightImageEnhancement mentioned on GitHubtfApache-2.0Syntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
nickolor/Learning-to-See-in-the-Dark mentioned on GitHubtfSyntology: not harvested report
nickolor/Learning-to-See-in-the-Dark_and_DeepISP mentioned on GitHubtfSyntology: not harvested report
samyakjain0112/Image-Denoising-in-extreme-low-light mentioned on GitHubtfSyntology: not harvested report
sdoria/SID mentioned on GitHubpytorchSyntology: not harvested report
someshfengde/learning_to_see_in_dark mentioned on GitHubSyntology: not harvested report
2023-MindSpore-4/Code-5 mindsporeSyntology: not harvested report
Mind23-2/MindCode-101 mindsporeSyntology: not harvested report
Mind23-2/MindCode-3 mindsporeSyntology: not harvested report
WangChen0902/SID-Paddle paddleSyntology: not harvested report
cchen156/Learning-to-See-in-the-Dark tfMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
code-implementation1/Code4 mindsporeSyntology: not harvested report
huyvnphan/Learning-To-See-In-The-Dark pytorchSyntology: not harvested report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

14 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 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.

1ran · our draft was wrong
7ran
6unverified

Licence: 3 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

ashikshafi08/learning_to_see_in_the_dark_Fastai community (archive-listed) 2 samples, 0 ran · 2 unverified
get_file_content_as_string libs/functionality.py unverified MIT (permissive) · 6800b859a41149ac · report
predict in 126 papers libs/functionality.py unverified MIT (permissive) · c44e194c35a67b4c · report
cydonia999/Learning_to_See_in_the_Dark_PyTorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
pixel_shuffle in 5 papers models/lsid.py ran MIT (permissive) · 83d71e95179cbcfc · report fixture: signature input:Tensor/4/float, upscale_factor:int/0/int, depth_first:bool/0/bool · returned Tensor · level recorded 2026-09-26
eoinoreilly30/seeing-in-the-dark community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
read_in_pickle adamw_fujifilm.py ran · our draft was wrong no licence file found · pointer only · 430f2f205dce4756 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-22
crop_images adamw_fujifilm.py unverified no licence file found · pointer only · 6fe3c6e45de063e5 · report
kauziishere/lowLightImageEnhancement community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
create_files preprocess.py ran Apache-2.0 (permissive) · cf3152406f05fa10 · report fixture: signature train_images_file:str/0/str, test_images_file:str/0/str, val_images_file:str/0/str · returned tuple · level recorded 2026-09-26
demosaicing Traditional.py ran fingerprinted Apache-2.0 (permissive) · de6a4c519048370e · report fixture: signature img_arr:ndarray/2/float, imrows:int/0/int, imcols:int/0/int · returned ndarray · level recorded 2026-09-26
denoising_sharpening Traditional.py ran Apache-2.0 (permissive) · 8a3d4f41e8538215 · report fixture: signature img_arr:ndarray/3/int · returned ndarray · level recorded 2026-09-26
function_to_remove_negs model.py ran fingerprinted Apache-2.0 (permissive) · 853442f9f5fee7a7 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
white_balance Traditional.py ran Apache-2.0 (permissive) · 610d5091b3bf0f9f · report fixture: signature img_arr:ndarray/3/int · returned ndarray · level recorded 2026-09-26
function_to_depth_to_space model.py unverified Apache-2.0 (permissive) · 37a55ee112ef2110 · report
cchen156/Learning-to-See-in-the-Dark community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
lrelu in 33 papers train_Fuji.py ran fingerprinted MIT (permissive) · f406422099514e4c · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-25
get_confirm_token in 41 papers download_models.py unverified MIT (permissive) here; the stored copy is pointer only · 135b3dc835ffe6ad · report
upsample_and_concat train_Fuji.py unverified MIT (permissive) · 99be22ebba093e63 · report

Tasks

DeblurringDenoisingImage Denoising

Datasets

Introduced by this paper, per the archive.

SID

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Denoising ELD SonyA7S2 x100 Paired Data(SID) PSNR (Raw) 44.47 #7 of 9 Archive leaderboard report
Image Denoising ELD SonyA7S2 x100 Paired Data(SID) SSIM (Raw) 0.968 #7 of 9 Archive leaderboard report
Image Denoising ELD SonyA7S2 x200 Paired Data(SID) PSNR (Raw) 41.97 #7 of 10 Archive leaderboard report
Image Denoising ELD SonyA7S2 x200 Paired Data(SID) SSIM (Raw) 0.928 #7 of 10 Archive leaderboard report
Image Denoising SID SonyA7S2 x250 Paired Data (SID) PSNR (Raw) 39.60 #5 of 10 Archive leaderboard report
Image Denoising SID SonyA7S2 x250 Paired Data (SID) SSIM (Raw) 0.938 #5 of 10 Archive leaderboard report
Image Denoising SID x100 SID (paired real data) PSNR (Raw) 42.06 #5 of 8 Archive leaderboard report
Image Denoising SID x100 SID (paired real data) SSIM 0.955 #5 of 8 Archive leaderboard report
Image Denoising SID x300 Paired Data(SID) PSNR (Raw) 36.85 #4 of 8 Archive leaderboard report
Image Denoising SID x300 Paired Data(SID) SSIM 0.923 #4 of 8 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