Papers › CURL: Neural Curve Layers for Global Image Enhancement

CURL: Neural Curve Layers for Global Image Enhancement

29 Nov 2019arXiv:1911.13175archive 2025-07-28

Sean Moran, Steven McDonagh, Gregory Slabaugh

We present a novel approach to adjust global image properties such as colour, saturation, and luminance using human-interpretable image enhancement curves, inspired by the Photoshop curves tool. Our method, dubbed neural CURve Layers (CURL), is designed as a multi-colour space neural retouching block trained jointly in three different colour spaces (HSV, CIELab, RGB) guided by a novel multi-colour space loss. The curves are fully differentiable and are trained end-to-end for different computer vision problems including photo enhancement (RGB-to-RGB) and as part of the image signal processing pipeline for image formation (RAW-to-RGB). To demonstrate the effectiveness of CURL we combine this global image transformation block with a pixel-level (local) image multi-scale encoder-decoder backbone network. In an extensive experimental evaluation we show that CURL produces state-of-the-art image quality versus recently proposed deep learning approaches in both objective and perceptual metrics, setting new state-of-the-art performance on multiple public datasets. Our code is publicly available at: https://github.com/sjmoran/CURL.

PaperPDFCode

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

Code

sjmoran/CURL officialmentioned in papermentioned on GitHubpytorch report
sjmoran/difar mentioned on GitHubpytorch report
sjmoran/neural_curve_layers mentioned on GitHubpytorch 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

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

Tasks

DecoderDemosaickingDenoisingImage EnhancementPhoto Retouching

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Enhancement MIT-Adobe 5k DIFAR (MSCA, level 1) PSNR on proRGB 24.2 #10 of 11 Archive leaderboard report
Image Enhancement MIT-Adobe 5k DIFAR (MSCA, level 1) SSIM on proRGB 0.88 #10 of 11 Archive leaderboard report
Photo Retouching MIT-Adobe 5k DIFAR (MSCA, level 1) PSNR 24.2 #4 of 5 Archive leaderboard report
Photo Retouching MIT-Adobe 5k DIFAR (MSCA, level 1) SSIM 0.88 #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