Please use this identifier to cite or link to this item:
Title: End-to-end line drawing vectorization
Author(s): Li, Chengze 
Liu, Xueting 
Author(s): Liu, H.
Wong, T.-T.
Issue Date: 2022
Publisher: AAAI Press
Related Publication(s): Proceedings of the 36th AAAI Conference on Artificial Intelligence
Volume: 36
Issue: 4
Start page: 4559
End page: 4566
Vector graphics is broadly used in a variety of forms, such as illustrations, logos, posters, billboards, and printed ads. Despite its broad use, many artists still prefer to draw with pen and paper, which leads to a high demand of converting raster designs into the vector form. In particular, line drawing is a primary art and attracts many research efforts in automatically converting raster line drawings to vector form. However, the existing methods generally adopt a two-step approach, stroke segmentation and vectorization. Without vector guidance, the raster-based stroke segmentation frequently obtains unsatisfying segmentation results, such as over-grouped strokes and broken strokes. In this paper, we make an attempt in proposing an end-to-end vectorization method which directly generates vectorized stroke primitives from raster line drawing in one step. We propose a Transformer-based framework to perform stroke tracing like human does in an automatic stroke-by-stroke way with a novel stroke feature representation and multi-modal supervision to achieve vectorization with high quality and fidelity. Qualitative and quantitative evaluations show that our method achieves state of the art performance.
CIHE Affiliated Publication: Yes
Appears in Collections:CIS Publication

Files in This Item:
File Description SizeFormat
View Online103 BHTMLView/Open
SFX Query Show full item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.