This article presents a new approach based on deep learning to automatically extract colormaps from visualizations. After summarizing colors in an input visualization image as a Lab color histogram, we pass the histogram to a pre-trained deep neural network, which learns to predict the colormap that produces the visualization. To train the network, we create a new dataset of $\sim$ 64K visualizations that cover a wide variety of data distributions, chart types, and colormaps. The network adopts an atrous spatial pyramid pooling module to capture color features at multiple scales in the input color histograms. We then classify the predicted colormap as discrete or continuous, and refine the predicted colormap based on its color histogram. Quantitative comparisons to existing methods show the superior performance of our approach on both synthetic and real-world visualizations. We further demonstrate the utility of our method with two use cases, i.e., color transfer and color remapping.

中文翻译：

---

从可视化中提取深度颜色图

本文介绍了一种基于深度学习的新方法，用于从可视化中自动提取颜色图。在将输入可视化图像中的颜色汇总为 Lab 颜色直方图后，我们将直方图传递给预训练的深度神经网络，该网络学习预测产生可视化的颜色图。为了训练网络，我们创建了一个新的数据集$\sim$ 64K 可视化，涵盖各种数据分布、图表类型和颜色图。该网络采用多孔空间金字塔池化模块来捕获输入颜色直方图中多个尺度的颜色特征。然后，我们将预测的颜色图分类为离散的或连续的，并根据其颜色直方图细化预测的颜色图。与现有方法的定量比较显示了我们的方法在合成和真实世界可视化方面的卓越性能。我们进一步证明了我们的方法在两个用例中的实用性，即颜色转移和颜色重映射。