Adaptive Color Grading

Trevor D. Canham; Abhijith Punnappurath; Michael S. Brown

eess.IVSep 18, 2026

Adaptive Color Grading

Authors: Trevor D. Canham, Abhijith Punnappurath, Michael S. Brown

Organizations: York University, Canada

Abstract

Independent control of tonescale regions (e.g., shadows, highlights) is essential for painters, photographers and cinematographers to bring 2D images to life. In image manipulation software this is most directly addressed by color grading modules, which use intensity thresholds to segment distinct illumination regions for local manipulation. In this work we develop an open source color grading tool and use it to annotate a large dataset of video frames with tonescale region thresholds. Using these thresholds we conduct modeling experiments with strategies based on both practitioners' conventional wisdom and machine learning. Results show that K-nearest neighbors is an effective prediction strategy, outperforming state-of-the-art end-to-end methods for image enhancement. This outcome demonstrates the benefit of focusing on a compact set of core parameters when modeling creative stylization processes. Our adaptive color grading interface and data are available at https://github.com/SamsungLabs/adaptive-color-grading.

Figures & tables

Figure 1: A relatively “flat” image appears more voluminous when the contrast between its tonescale regions is increased 1,2 . This can be accomplished through tonemapping and chromatic shifts 2,3 . However, a static 3D color lookup table tuned to achieve this effect for one image may not work for another 4,5 . We present a method for predicting tonescale region thresholds such that these color effects can be adapted to new images 4,6 .

Figure 2: Color grading interface featuring chroma offset, TRT controls and grayscale visualization.

Figure 3: Color grading architecture. Regional LUTs are applied in a nested fashion to an identity LUT which is then applied to return the output image.

Figure 4: The HDR videographic survey dataset arranged according to scene type.

Figure 5: Histogram of tonescale region settings.

Location subset	Count	Scene type subsets
Toronto	90	Urban
Utah	458	Sunset, Night
Alaska	378	Sunset, Night
Seattle	286	Sunset, Night, Urban, Indoor
London	146	Sunset, Night, Urban, Indoor
NYC	206	Sunset, Urban, Indoor

Table 1: Breakdown of HVS locations and scene types which differ from the majority day, outdoor, nature scenes.

Figure 6: 1-D Optimization landscapes for Fixed and Percentile based strategies.

Figure 7: Multi-layer perceptron modeling overview.

Figure 8: K-nearest neighbors modeling overview.

Train/test	remainder/NYC		NYC/remainder		remainder/Night		Night/remainder
	$\Delta E_{00}$ $\downarrow$	PSNR $\uparrow$	$\Delta E_{00}$ $\downarrow$	PSNR $\uparrow$	$\Delta E_{00}$ $\downarrow$	PSNR $\uparrow$	$\Delta E_{00}$ $\downarrow$	PSNR $\uparrow$
U-Net [ 10 ]	2.96	34.90	3.83	33.15	2.99	36.22	2.81	36.19
NamedCurves [ 17 ]	3.44	32.86	4.02	32.44	4.85	30.99	3.83	32.68
NILUT [ 6 ]	2.65	35.46	2.86	35.80	1.62	40.84	2.56	36.87
Fixed	3.25	34.16	3.56	34.39	1.81	40.47	2.96	35.90
Percentile [ 3 ]	3.43	33.54	3.87	34.17	2.93	37.60	3.20	34.93

Table 2: Quantitative results of modeling approaches versus end-to-end deep learning approaches. In these experiments models are tested on a subset and trained on the remainder or vice-versa.

Panel of Figure 9 — Figure 9: Top row: 90th percentile $\Delta E_{00}$ averaged across the test set (x-axis). Bottom row: Correlation plots with ground truth darkest (purple) dark (blue) light (green) lightest (red) TRTs plotted against predicted ones by KNN, MLP, Fixed and Percentile strategies.

Figure 10: Qualitative results from KNN, NILUT [ 6 ] , Fixed and U-Net [ 10 ] strategies trained on “NYC” dataset subset. KNN follows yellow-blue shift regions of GT while other solutions struggle.

Explore similar work

CanonCGT: Reference-Based Color Grading via Canonical Pivot Representation
Jun 1, 2026Jinwon Ko, Keunsoo Ko, Chang-Su KimImage Style Transfer Unpaired Image-to-Image Translation
Korea University · The Catholic University of Korea
Learning Color Grading, No Photo Sharing: Federated Aesthetic Preference Learning for Personalized Image Enhancement
Jul 30, 2026Chuanzhi Xu, Ziyuan Tao, Jean Julien KNell +5Personalized Image Aesthetics Assessment Image Enhancement
The University of Sydney · Macquarie University
Hist2Style: Histogram-Guided Stylization with Bilateral Grids
Jun 1, 2026Dekel Galor, Adam Pikielny, Zhoutong Zhang +4Image Style Transfer
Adobe Nextcam · University of California, Berkeley

Jun 1, 2026J/K move · Enter open · S save

CanonCGT: Reference-Based Color Grading via Canonical Pivot Representation

Jinwon Ko, Keunsoo Ko, Chang-Su Kim

Korea University · The Catholic University of Korea

Image Style Transfer Unpaired Image-to-Image Translation Image Editing

Open paper AskPDF arXiv

Reference-based color grading aims to reproduce the tonal mood and lighting of a reference while preserving color harmony and scene structure. Existing photorealistic and filter-based methods often produce unstable tone mappings -- over-shifting or inconsistently retaining colors -- leading to unnatural results. We propose CanonCGT, a two-stage framework built on a canonical pivot -- a style-neutral intermediate representation for stable color mapping. The first stage canonicalizes the input by removing intrinsic tonal bias, and the second color-grades it to match the reference style. A dual-phase training scheme, DP-CGT, combines supervised preset learning with self-supervised refinement on unpaired photographs. CanonCGT delivers photorealistic and tonally consistent results across diverse datasets, surpassing state-of-the-art methods in stability and visual fidelity. Our codes are available at https://github.com/Jinwon-Ko/CanonCGT

Abstract

Explore similar work

CanonCGT: Reference-Based Color Grading via Canonical Pivot Representation

Learning Color Grading, No Photo Sharing: Federated Aesthetic Preference Learning for Personalized Image Enhancement

Hist2Style: Histogram-Guided Stylization with Bilateral Grids