Efficient Image Vectorisation Using Mesh Colours
Abstract
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.
BibTeX
@inproceedings {10.2312:stag.20211484,
booktitle = {Smart Tools and Apps for Graphics - Eurographics Italian Chapter Conference},
editor = {Frosini, Patrizio and Giorgi, Daniela and Melzi, Simone and Rodolà, Emanuele},
title = {{Efficient Image Vectorisation Using Mesh Colours}},
author = {Hettinga, Gerben Jan and Echevarria, Jose and Kosinka, Jiri},
year = {2021},
publisher = {The Eurographics Association},
ISSN = {2617-4855},
ISBN = {978-3-03868-165-6},
DOI = {10.2312/stag.20211484}
}
booktitle = {Smart Tools and Apps for Graphics - Eurographics Italian Chapter Conference},
editor = {Frosini, Patrizio and Giorgi, Daniela and Melzi, Simone and Rodolà, Emanuele},
title = {{Efficient Image Vectorisation Using Mesh Colours}},
author = {Hettinga, Gerben Jan and Echevarria, Jose and Kosinka, Jiri},
year = {2021},
publisher = {The Eurographics Association},
ISSN = {2617-4855},
ISBN = {978-3-03868-165-6},
DOI = {10.2312/stag.20211484}
}