Tutrace: Editable Animated Vector Shape from Video

Loïc Vital

2025

Abstract

We present a new video vectorization technique for converting a sequence of binary images into an animated vector shape. Our approach offers the benefit of producing an output that can be directly used in a compositing software to apply manual edits and corrections, which is often a mandatory constraint for rotoscoping artists in the VFX industry. Our process initially builds a frame-by-frame vectorization of the input, finds correspondences between vertices at different frames, and extracts an animated vector shape from the induced graph structure. Although the presented method is completely automatic, the general approach is flexible and offers several controls to adjust the fidelity vs. simplicity trade-off in the generated output.

Paper Citation

in Harvard Style

Vital L. (2025). Tutrace: Editable Animated Vector Shape from Video. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP; ISBN 978-989-758-728-3, SciTePress, pages 19-28. DOI: 10.5220/0013097900003912

in Bibtex Style

@conference{grapp25,
author={Loïc Vital},
title={Tutrace: Editable Animated Vector Shape from Video},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP},
year={2025},
pages={19-28},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013097900003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP
TI - Tutrace: Editable Animated Vector Shape from Video
SN - 978-989-758-728-3
AU - Vital L.
PY - 2025
SP - 19
EP - 28
DO - 10.5220/0013097900003912
PB - SciTePress