Hettinga, Gerben JanEchevarria, JoseKosinka, JiriFrosini, Patrizio and Giorgi, Daniela and Melzi, Simone and Rodolà, Emanuele2021-10-252021-10-252021978-3-03868-165-62617-4855https://doi.org/10.2312/stag.20211484https://diglib.eg.org:443/handle/10.2312/stag20211484Image 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.Computing methodologiesImage processing10.2312/stag.20211484139-150