Palette-Based and Harmony-Guided Colorization for Vector Icons

Abstract

Colorizing icon is a challenging task, even for skillful artists, as it involves balancing aesthetics and practical considerations. Prior works have primarily focused on colorizing pixel-based icons, which do not seamlessly integrate into the current vectorbased icon design workflow. In this paper, we propose a palette-based colorization algorithm for vector icons without the need for rasterization. Our algorithm takes a vector icon and a five-color palette as input and generates various colorized results for designers to choose from. Inspired by the common icon design workflow, we developed our algorithm to consist of two steps: generating a colorization template and performing the palette-based color transfer. To generate the colorization templates, we introduce a novel vector icon colorization model that employs an MRF-based loss and a color harmony loss. The color harmony loss encourages the alignment of the resulting color template with widely used harmony templates. We then map the predicted colorization template to chroma-like palette colors to obtain diverse colorization results. We compare our results with those generated by previous pixel-based icon colorization methods and validate the effectiveness of our algorithm by evaluations in both qualitative and quantitative measurements. Our method enables icon designers to explore diverse colorization results for a single icon using different color palettes while also efficiently evaluating the suitability of a color palette for a set of icons.