Papers › Unprocessing Images for Learned Raw Denoising

Unprocessing Images for Learned Raw Denoising

27 Nov 2018CVPR 2019 6arXiv:1811.11127archive 2025-07-28

Tim Brooks, Ben Mildenhall, Tianfan Xue, Jiawen Chen, Dillon Sharlet, Jonathan T. Barron

Machine learning techniques work best when the data used for training resembles the data used for evaluation. This holds true for learned single-image denoising algorithms, which are applied to real raw camera sensor readings but, due to practical constraints, are often trained on synthetic image data. Though it is understood that generalizing from synthetic to real data requires careful consideration of the noise properties of image sensors, the other aspects of a camera's image processing pipeline (gain, color correction, tone mapping, etc) are often overlooked, despite their significant effect on how raw measurements are transformed into finished images. To address this, we present a technique to "unprocess" images by inverting each step of an image processing pipeline, thereby allowing us to synthesize realistic raw sensor measurements from commonly available internet photos. We additionally model the relevant components of an image processing pipeline when evaluating our loss function, which allows training to be aware of all relevant photometric processing that will occur after denoising. By processing and unprocessing model outputs and training data in this way, we are able to train a simple convolutional neural network that has 14%-38% lower error rates and is 9x-18x faster than the previous state of the art on the Darmstadt Noise Dataset, and generalizes to sensors outside of that dataset as well.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

caiyuanhao1998/PNGAN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training (arXiv:2204.02844; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
goutamgmb/NTIRE21_BURSTSR mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Burst Super-Resolution (arXiv:2101.10997; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mv-lab/AISP mentioned on GitHubpytorchSyntology: not harvested report
google-research/google-research tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Efficient Neural Architecture Search via Parameter Sharing (arXiv:1802.03268; that paper's own run record: 18 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified), Milking CowMask for Semi-Supervised Image Classification (arXiv:2003.12022; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result), Neural Additive Models: Interpretable Machine Learning with Neural Nets (arXiv:2004.13912; that paper's own run record: 26 ran (of which 14 constructed an object rather than computing a result; 26 with no instrument failure: 5 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified) and 21 more (every one in this page's JSON twin); 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DenoisingImage DenoisingNoise EstimationTone Mapping

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising Darmstadt Noise Dataset Image Unprocessing PSNR (Raw) 48.88 #1 of 6 Archive leaderboard report
Color Image Denoising Darmstadt Noise Dataset Image Unprocessing PSNR (sRGB) 40.35 #1 of 6 Archive leaderboard report
Color Image Denoising Darmstadt Noise Dataset Image Unprocessing SSIM (Raw) 0.9821 #1 of 6 Archive leaderboard report
Color Image Denoising Darmstadt Noise Dataset Image Unprocessing SSIM (sRGB) 0.9641 #1 of 6 Archive leaderboard report
Noise Estimation SIDD ULRD Average KL Divergence 0.545 #4 of 5 Archive leaderboard report
Noise Estimation SIDD ULRD PSNR Gap 4.90 #4 of 5 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