Succinct Palette and Color Model Generation and Manipulation Using Hierarchical Representation

Abstract

We propose a new method to obtain the representative colors and their distributions of an image. Our intuition is that it is possible to derive the global model from the local distributions. Beginning by sampling pure colors, we build a hierarchical representation of colors in the image via a bottom‐up approach. From the resulting hierarchy, we can obtain satisfactory palettes/color models automatically without a predefined size. Furthermore, we provide interactive operations to manipulate the results which allow the users to reflect their intention directly. In our experiment, we show that the proposed method produces more succinct results that faithfully represent all the colors in the image with an appropriate number of components. We also show that the proposed interactive approach can improve the results of applications such as recoloring and soft segmentation.

LoCoPalettes: Local Control for Palette‐based Image Editing

“…[ZNZ * 21] formulated an optimization solving for palette colors and mixing weights simultaneously by considering color separation priors. [JYS19] create palettes in a hierarchical, bottom‐up manner. These are quite different from the image‐space and palette‐space hierarchies we use to support local editing.…”

Soft Colour Segmentation On Light Fields

“…Jeong et al first sample pure colours, then build a hierarchical model by splitting each layer, and all the possible colours within it, into two layers where the colour variance is much smaller and the dominant colours are as distinct from each other as possible. [11]…”