A provably-robust sampling method for generating colormaps of large data

摘要

First impressions from initial renderings of data are crucial for directing further exploration and analysis. In most visualization systems, default colormaps are generated by simply linearly interpolating color in some space based on a value's placement between the minimum and maximum taken on by the dataset. We design a simple sampling-based method for generating colormaps that high-lights important features. We use random sampling to determine the distribution of values observed in the data. The sample size required is independent of the dataset size and only depends on certain accuracy parameters. This leads to a computationally cheap and robust algorithm for colormap generation. Our approach (1) uses perceptual color distance to produce palettes from color curves, (2) allows the user to either emphasize or de-emphasize prominent values in the data, (3) uses quantiles to map distinct colors to values based on their frequency in the dataset, and (4) supports the highlighting of either inter- or intra-mode variations in the data.