CraGL: Computational Reality, Creativity and Graphics Lab

Palette-based color harmonization

Jianchao Tan, Jose Echevarria, Yotam Gingold
IEEE Transactions on Visualization and Computer Graphics (TVCG), to appear

Paper

Supplementary Material

A) Different harmonic templates applied to an input image of an island at sunset. Below each template is a color wheel with arrows indicating the movement of palette colors towards template axes. B) Three glass vials with red, blue, and purple hues have their colors adjusted to a harmonic template. A similar color wheel with arrows is shown alongside. C) A photo of two children has its colors adjusted to increase warm-cool contrast. A similar color wheel with arrows is shown alongside. Our framework is able to express harmonization and various other color operations in a concise manner via color-space axes (black lines). A) Different harmonic templates can be enforced over an input image. B) Our methods can automatically determine the best fitting one. C) New operators like warm-cool contrast can be easily expressed.

Abstract

We present a palette-based framework for color composition for visual applications and three large-scale, wide-ranging perceptual studies on the perception of color harmonization. We abstract relationships between palette colors as a compact set of axes describing harmonic templates over perceptually uniform color wheels. Our framework provides a basis for interactive color-aware operations such as color harmonization of images and videos. Because our approach to harmonization is palette-based, we are able to conduct the first controlled perceptual experiments evaluating preferences for harmonized images and color palettes. In a third study, we compare preference for archetypical harmonic palettes. In total, our studies involved over 1000 participants. We found that participants do not prefer harmonized images and that some archetypal palettes are reliably viewed as less harmonious than random palettes. These studies raise important questions for research and artistic practice.

BibTeX

(publisher page) 

@article{Tan:2025:PBC,
  author={Tan, Jianchao and Echevarria, Jose and Gingold, Yotam},
  journal={IEEE Transactions on Visualization and Computer Graphics}, 
  title={Palette-based color harmonization}, 
  year={2025},
  volume={},
  number={},
  pages={1--14},
  keywords={Image color analysis;Harmonic analysis;Visualization;Wheels;Histograms;Videos;Fitting;Three-dimensional displays;Image decomposition;Deep learning;Palette;Color;Harmonization;Recoloring},
  doi={10.1109/TVCG.2025.3546210}
}