Efficient Image Vectorisation Using Mesh Colours

STAG 2021

Published October 26, 2021

Gerben Hettinga, Jose Echevarria, Jiri Kosinka

Best paper award

Image vectorisation methods proposed in the past have not seen wide adoption due to performance, quality, controllability, and/or generality issues.We present a vectorisation method that uses mesh colours as a vector primitive for image vectorisation. We show that mesh colours have clear benefits for rendering performance and texture detail. Due to their flexibility, they also enable a simplified and more efficient generation of meshes of curved triangular patches, which are in our case constrained by our image feature extraction algorithm. The proposed method follows a standard pipeline where each step is efficient and controllable, leading to results that compare favourably with those from previous work. We show results over a variety of input images including photos, drawings, paintings, designs, and cartoons and also devise a user-guided vectorisation variant.

Research Area:  Graphics (2D & 3D)