Papers › Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model

Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model

7 Aug 2023ICCV 2023 1arXiv:2308.03448archive 2025-07-28

Xin Jin, Jia-Wen Xiao, Ling-Hao Han, Chunle Guo, Xialei Liu, Chongyi Li, Ming-Ming Cheng

Explicit calibration-based methods have dominated RAW image denoising under extremely low-light environments. However, these methods are impeded by several critical limitations: a) the explicit calibration process is both labor- and time-intensive, b) challenge exists in transferring denoisers across different camera models, and c) the disparity between synthetic and real noise is exacerbated by digital gain. To address these issues, we introduce a groundbreaking pipeline named Lighting Every Darkness (LED), which is effective regardless of the digital gain or the camera sensor. LED eliminates the need for explicit noise model calibration, instead utilizing an implicit fine-tuning process that allows quick deployment and requires minimal data. Structural modifications are also included to reduce the discrepancy between synthetic and real noise without extra computational demands. Our method surpasses existing methods in various camera models, including new ones not in public datasets, with just a few pairs per digital gain and only 0.5% of the typical iterations. Furthermore, LED also allows researchers to focus more on deep learning advancements while still utilizing sensor engineering benefits. Code and related materials can be found in https://srameo.github.io/projects/led-iccv23/ .

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="2308.03448")

Code

Syntology Ran 4 of 11 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

srameo/led 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

11 samples harvested; 4 ran; 0 honoured the contract we drafted; 7 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.

4ran
7unverified

Licence: 11 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 srameo/led. “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.

gamma_correct srameo/led/led/models/raw_denoising_model.py official repository ran fingerprinted licence not identified · pointer only · 209f448dfe9fb7dd · report
gamma_expansion srameo/led/led/models/raw_denoising_model.py official repository ran fingerprinted licence not identified · pointer only · 8203ed9500723a9b · report
get_position_from_periods srameo/led/led/models/lr_scheduler.py official repository ran fingerprinted no licence file found · pointer only · cd569444547de84f · report
sum_img_and_noise srameo/led/led/models/raw_denoising_model.py official repository ran licence not identified · pointer only · 457851ad6b90a723 · report
g_path_regularize srameo/led/led/losses/gan_loss.py official repository unverified no licence file found · pointer only · fe05416387de89c6 · report
gradient_penalty_loss srameo/led/led/losses/gan_loss.py official repository unverified no licence file found · pointer only · 81eb425a41a7c2a1 · report
r1_penalty srameo/led/led/losses/gan_loss.py official repository unverified no licence file found · pointer only · c7cba9053f3cadb5 · report
reduce_loss srameo/led/led/losses/loss_util.py official repository unverified no licence file found · pointer only · a648a03a952822c0 · report
weight_reduce_loss srameo/led/led/losses/loss_util.py official repository unverified no licence file found · pointer only · 1ba39317ea81871a · report
weighted_loss srameo/led/led/losses/loss_util.py official repository unverified no licence file found · pointer only · cf63f8afc13f62a7 · report
zero_module srameo/led/led/archs/cunet_arch.py official repository unverified no licence file found · pointer only · da94debb8019ad46 · report

Tasks

DenoisingImage Denoising

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Denoising SID SonyA7S2 x100 LED PSNR (Raw) 41.98 #3 of 5 Archive leaderboard report
Image Denoising SID SonyA7S2 x100 LED SSIM (Raw) 0.954 #3 of 5 Archive leaderboard report
Image Denoising SID SonyA7S2 x250 LED PSNR (Raw) 39.34 #7 of 10 Archive leaderboard report
Image Denoising SID SonyA7S2 x250 LED SSIM (Raw) 0.932 #7 of 10 Archive leaderboard report
Image Denoising SID SonyA7S2 x300 LED PSNR (Raw) 36.67 #1 of 2 Archive leaderboard report
Image Denoising SID SonyA7S2 x300 LED SSIM (Raw) 0.915 #1 of 2 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

Focus

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