UIST 2024
Chromaticity Gradient Mapping
for Interactive Control of Color Contrast in Images and Video

Contrast Enhancement with Chromaticity: We adjust per-pixel chromaticity along a gradient curve according to a user-controlled adjustment curve. This method lets us enhance the perceived dynamic range and detail at a selected bandwidth without adjusting the illuminance of an image.
Abstract
We present a novel perceptually-motivated interactive tool for using color contrast to enhance details represented in the lightness channel of images and video. Our method lets users adjust the perceived contrast of different details by manipulating local chromaticity while preserving the original lightness of individual pixels. Inspired by the use of similar chromaticity mappings in painting, our tool effectively offers contrast along a user-selected gradient of chromaticities as additional bandwidth for representing and enhancing different details in an image. We provide an interface for our tool that closely resembles the familiar design of tonal contrast curve controls that are available in most professional image editing software. We show that our tool is effective for enhancing the perceived contrast of details without altering lightness in an image and present many examples of effects that can be achieved with our method on both images and video.
Chromaticity Mapping in Arts
Just as pixels have only a limited number of bits, a painter's palette can only represent a limited number of human-distinguishable colors. To counter this limitation, visual artists have used chromaticity as an alternative visual channel to convey variations of luminance. A striking example is Claude Monet's painting Sunrise, which manages to convey the brightness of a rising sun almost exclusively through chromaticity. Similarly, in Cezanne's painting Mardi Gras, cooler chromaticities are used in place of shading to depict Pierrot's outfit.

Color Contrast for Detail Enhancement: In the painting Sunrise by Claude Monet, details of the sun and its reflection on the water are conveyed almost entirely through variations in chromaticity.

Substituting Chromaticity Variations for Tonal Variations: CGM lets us apply the warm-cool gradient in Mardi Gras by Cezanne to a natural image with a similar white outfit.
Chromaticity mapping is widely observed in cinematography to enhance perceived contrast in both brightness and depths. On set, complementary lighting is applied from various angles to shape the scene, while in post-production, colorists adjust hues in shadows and highlights to achieve effects like the iconic 'Teal and Orange' look.
Blinding Lights, The Weekend, 2020
Tenet, Christopher Nolan, 2020
Chromaticity Gradient Mapping
We propose Chromaticity Gradient Mapping, a method for manipualting color contrast in images and videos. We parameterize chromaticity mapping with two controls: gradient curve and adjustment curve. The gradient curve defines the direction of shifts within the chromaticity space, while the adjustment curve controls the magnitude of these shifts as a function of lightness.

Chromaticity Gradient Mapping: The gradient curve defines the direction of shifts within the chromaticity space (A v.s. C), while the adjustment curve controls the magnitude of these shifts as a function of lightness (B v.s. C).
By filtering the input lightness map, our method can enhance different levels of details through color contrast adjustment. It can also be used for complementary tone mapping when lightness adjustments and chromaticity adjustments are applied at different frequency levels. Please see our paper for more detail.

Detail Manipulation in Chromaticity: Our method allows users to quickly explore chromaticity adjustments by focusing contrast on details at different scales. The top adjustment uses the chosen color gradient to enhance edge contrast, the middle enhances a mix of edge and detail contrast, and the bottom enhances detail contrast. Image credit to @signatureedits.
Results
Hover your cursor over each image to compare against the input, and click on it to see more visualizations of the adjustment process! Image credit to @signatureedits.
BibTeX
@inproceedings{chromapping2024,
author = {Yan, Ruyu and Sun, Jiatian and Davis, Abe},
title = {Chromaticity Gradient Mapping for Interactive Control of Color Contrast in Images and Video},
year = {2024},
isbn = {9798400706288},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3654777.3676340},
doi = {10.1145/3654777.3676340},
series = {UIST '24}
}
Acknowledgement
We thank Adam Finkelstein for support and helpful discussions on this project.