Fig. 1: Colormap recovery from a single visualization. (a) shows a visualization with subtle variations in the red dotted region. (b) Our method successfully predicts the original colormap by simultaneously decoupling colormap and data embedded in the visualization. (c) Replacing the original colormap with two newly designed colormaps better reveals spatial variations in the highlighted region. (d) The recovered colormap can be applied to new data for a consistent design style.

Abstract:

Recovering a continuous colormap from a single 2D scalar field visualization can be quite challenging, especially in the absence of a corresponding color legend. In this paper, we propose a novel colormap recovery approach that extracts the colormap from a color-encoded 2D scalar field visualization by simultaneously predicting the colormap and underlying data using a decoupling- and-reconstruction strategy. Our approach first separates the input visualization into colormap and data using a decoupling module, then reconstructs the visualization with a differentiable color-mapping module. To guide this process, we design a reconstruction loss between the input and reconstructed visualizations, which serves both as a constraint to ensure strong correlation between colormap and data during training, and as a self-supervised optimizer for fine-tuning the predicted colormap of unseen visualizations during inferencing. To ensure smoothness and correct color ordering in the extracted colormap, we introduce a compact colormap representation using cubic B-spline curves and an associated color order loss. We evaluate our method quantitatively and qualitatively on a synthetic dataset and a collection of real-world visualizations from the VIS30K dataset. Additionally, we demonstrate its utility in two prototype applications—colormap adjustment and colormap transfer—and explore its generalization to visualizations with color legends and ones encoded using discrete color palettes.

Downloads:

Acknowledgement:

The authors would like to thank Linping Yuan at HKUST and Wei Zeng at HKUST(GZ) for providing valuable discussions and source codes, as well as the anonymous reviewers for their helpful comments. In this study, Qiong Zeng is supported by grants from the National Key R&D Program of China (No. 2021YFF0704300), the National Natural Science Foundation of China (No. 62372271), and the Taishan Scholars Program (No. tsqn202408291); Manyi Li is supported by the Excellent Young Scientists Fund Program (Overseas) of Shandong Province (No. 2023HWYQ-034); and Yunhai Wang is supported by the National Natural Science Foundation of China (No. 62132017 and No. U2436209), the Natural Science Foundation of Shandong Province (No. ZQ2022JQ32), the Beijing Natural Science Foundation (L247027), and the Fundamental Research Funds for the Central Universities

Bibtex:

@inproceedings{coloritup,
title = {Self-Supervised Continuous Colormap Recovery from a 2D Scalar Field Visualization without a Legend},
author = {Hongxu Liu and Xinyu Chen and Haoyang Zheng and Manyi Li and Zhenfan Liu and Funmeng Yang and Yunhai Wang and Changhe Tu and Qiong Zeng},
year = {2025},
isbn = {},
publisher = {},
address = {New York, NY, USA},
url = {},
doi = {},
booktitle = {Proceedings of the IEEE VIS 2025},
articleno = {},
location = {Vienna, Austria},
series = {}
}