Color by Numbers: Interactive Structuring and Vectorization of Sketch Imagery

Amal Dev Parakkat (1) , Marie-Paule Cani (2, 3) , Karan Singh (4)

1 TU Delft - Delft University of Technology
2 IP Paris - Institut Polytechnique de Paris
3 LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
4 DCS - Department of Computer Science [University of Toronto]

We present a novel, interactive interface for the integrated cleanup, neatening, structuring and vectorization of sketch imagery. Converting scanned raster drawings into vector illustrations is a wellresearched set of problems. Our approach is based on a Delaunay subdivision of the raster drawing. We algorithmically generate a colored grouping of Delaunay regions that users interactively refine by dragging and dropping colors. Sketch strokes defined as marking boundaries of different colored regions are automatically neatened using Bézier curves, and turned into closed regions suitable for fills, textures, layering and animation. We show that minimal user interaction using our technique enables better sketch vectorization than state of art automated approaches. A user study, further shows our interface to be simple, fun and easy to use, yet effectively able to process messy images with a mix of construction lines, noisy and incomplete curves, sketched with arbitrary stroke style.

Domaines: Synthèse d'image et réalité virtuelle [cs.GR]; Géométrie algorithmique [cs.CG]; Interface homme-machine [cs.HC]; Traitement des images [eess.IV]

Amal Dev Parakkat, Marie-Paule Cani, Karan Singh. Color by Numbers: Interactive Structuring and Vectorization of Sketch Imagery. CHI '21: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, May 2021, Yokohama, Japan. ⟨hal-03116986⟩