Papers › Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

19 Jan 2020CVPR 2020 6arXiv:2001.06826archive 2025-07-28

Chunle Guo, Chongyi Li, Jichang Guo, Chen Change Loy, Junhui Hou, Sam Kwong, Runmin Cong

The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network. Our method trains a lightweight deep network, DCE-Net, to estimate pixel-wise and high-order curves for dynamic range adjustment of a given image. The curve estimation is specially designed, considering pixel value range, monotonicity, and differentiability. Zero-DCE is appealing in its relaxed assumption on reference images, i.e., it does not require any paired or unpaired data during training. This is achieved through a set of carefully formulated non-reference loss functions, which implicitly measure the enhancement quality and drive the learning of the network. Our method is efficient as image enhancement can be achieved by an intuitive and simple nonlinear curve mapping. Despite its simplicity, we show that it generalizes well to diverse lighting conditions. Extensive experiments on various benchmarks demonstrate the advantages of our method over state-of-the-art methods qualitatively and quantitatively. Furthermore, the potential benefits of our Zero-DCE to face detection in the dark are discussed. Code and model will be available at https://github.com/Li-Chongyi/Zero-DCE.

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="2001.06826")

Code

Syntology Ran 1 of 16 code samples harvested from 4 repositories linked to this paper; 15 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: community (archive-listed): 16 samples from 4 repositories, 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.

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

Li-Chongyi/Zero-DCE officialmentioned in paperpytorch report
Thehunk1206/Zero-DCE mentioned on GitHubtf report
canturan10/light_side mentioned on GitHubpytorchMIT report
cuiziteng/iccv_maet mentioned on GitHubpytorchApache-2.0 report
cuiziteng/maet mentioned on GitHubpytorchApache-2.0 report
sayannath/Zero-DCE-TFLite mentioned on GitHubtfApache-2.0 report
soumik12345/Zero-DCE mentioned on GitHubpytorchMIT report
pwc-1/Paper-9 mindspore report
pwc-1/Paper-9 mindspore 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

16 samples harvested; 1 ran; 0 honoured the contract we drafted; 15 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
15unverified

Licence: 0 of the 16 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 4 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.

process_checkpoint cuiziteng/iccv_maet/.dev_scripts/gather_models.py community (archive-listed) ran Apache-2.0 (permissive) · e76a491553cf9fcf · report
DCE_x tuvovan/Zero_DCE_TF/src/model.py community (archive-listed) unverified MIT (permissive) · e824e99cd0a86afe · report
L_TV tuvovan/Zero_DCE_TF/src/loss.py community (archive-listed) unverified MIT (permissive) · d3351079e85081a6 · report
L_color tuvovan/Zero_DCE_TF/src/loss.py community (archive-listed) unverified MIT (permissive) · 8ec5ded69fae1885 · report
L_exp tuvovan/Zero_DCE_TF/src/loss.py community (archive-listed) unverified MIT (permissive) · 037bf1c6b1f20806 · report
configure_batch canturan10/light_side/light_side/utils.py community (archive-listed) unverified MIT (permissive) · 33162905c6a70e6a · report
convert_np canturan10/light_side/light_side/utils.py community (archive-listed) unverified MIT (permissive) · 5a508e6403e60f0d · report
enhance_frame tuvovan/Zero_DCE_TF/video-dce.py community (archive-listed) unverified MIT (permissive) · b22c91880d31ebfb · report
get_final_epoch cuiziteng/iccv_maet/.dev_scripts/gather_models.py community (archive-listed) unverified Apache-2.0 (permissive) · e86ae414e2afc197 · report
get_final_results cuiziteng/iccv_maet/.dev_scripts/gather_models.py community (archive-listed) unverified Apache-2.0 (permissive) · fee6fb3d147348e3 · report
load_model tuvovan/Zero_DCE_TF/video-dce.py community (archive-listed) unverified MIT (permissive) · 619e70eaae247e45 · report
populate_train_list tuvovan/Zero_DCE_TF/src/data_lowlight.py community (archive-listed) unverified MIT (permissive) · a90a91cfd3bee533 · report
pretty_size soumik12345/Zero-DCE/zero_dce/utils.py community (archive-listed) unverified MIT (permissive) · 3fa4889eb961839a · report
read_imagefile canturan10/light_side/deployment/fastapi/service.py community (archive-listed) unverified MIT (permissive) · e5a657a01454b7f8 · report
save_grad cuiziteng/iccv_maet/mmdet/models/detectors/MAET_YOLO/MAET_YOLO.py community (archive-listed) unverified Apache-2.0 (permissive) · 149d779c3ce51b5d · report
visualize canturan10/light_side/light_side/utils.py community (archive-listed) unverified MIT (permissive) · d030fc89c60d67f4 · report

Tasks

Color ConstancyFace DetectionImage EnhancementLow-Light Image EnhancementSpeech Enhancement

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Constancy INTEL-TUT2 SRIE[8] Best 25% 3.2 #1 of 1 Archive leaderboard report
Low-Light Image Enhancement DICM Zero-DCE BRISQUE 27.56 #4 of 6 Archive leaderboard report
Low-Light Image Enhancement DICM Zero-DCE NIQE 4.58 #4 of 6 Archive leaderboard report
Low-Light Image Enhancement DICM Zero-DCE User Study Score 3.52 #4 of 6 Archive leaderboard report
Low-Light Image Enhancement LIME Zero-DCE BRISQUE 20.44 #5 of 6 Archive leaderboard report
Low-Light Image Enhancement LIME Zero-DCE NIQE 5.82 #5 of 6 Archive leaderboard report
Low-Light Image Enhancement LIME Zero-DCE User Study Score 3.8 #5 of 6 Archive leaderboard report
Low-Light Image Enhancement MEF Zero-DCE BRISQUE 17.32 #5 of 7 Archive leaderboard report
Low-Light Image Enhancement MEF Zero-DCE NIQE 4.93 #5 of 7 Archive leaderboard report
Low-Light Image Enhancement MEF Zero-DCE User Study Score 3.87 #5 of 7 Archive leaderboard report
Low-Light Image Enhancement NPE Zero-DCE BRISQUE 20.72 #5 of 6 Archive leaderboard report
Low-Light Image Enhancement NPE Zero-DCE NIQE 4.53 #5 of 6 Archive leaderboard report
Low-Light Image Enhancement NPE Zero-DCE User Study Score 3.81 #5 of 6 Archive leaderboard report
Low-Light Image Enhancement VV Zero-DCE BRISQUE 34.66 #4 of 7 Archive leaderboard report
Low-Light Image Enhancement VV Zero-DCE NIQE 4.81 #4 of 7 Archive leaderboard report
Low-Light Image Enhancement VV Zero-DCE User Study Score 3.24 #4 of 7 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