Color Recommendation for Vector Graphic Documents based on Multi-Palette Representation
This addresses the challenge of color selection for designers, but it is incremental as it builds on existing palette-based methods with a novel multi-palette approach.
The paper tackled the problem of recommending colors for multiple visual elements in vector graphic documents by extracting and combining multiple color palettes into a sequence, using a masked color model for completion. The method outperformed state-of-the-art approaches in evaluations and received positive feedback from professional designers.
Vector graphic documents present multiple visual elements, such as images, shapes, and texts. Choosing appropriate colors for multiple visual elements is a difficult but crucial task for both amateurs and professional designers. Instead of creating a single color palette for all elements, we extract multiple color palettes from each visual element in a graphic document, and then combine them into a color sequence. We propose a masked color model for color sequence completion and recommend the specified colors based on color context in multi-palette with high probability. We train the model and build a color recommendation system on a large-scale dataset of vector graphic documents. The proposed color recommendation method outperformed other state-of-the-art methods by both quantitative and qualitative evaluations on color prediction and our color recommendation system received positive feedback from professional designers in an interview study.