End-to-End Line Drawing Vectorization


  • Hanyuan Liu The Chinese University of Hong Kong
  • Chengze Li Caritas Institute of Higher Education
  • Xueting Liu Caritas Institute of Higher Education
  • Tien-Tsin Wong The Chinese University of Hong Kong




Domain(s) Of Application (APP), Computer Vision (CV), Machine Learning (ML)


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.




How to Cite

Liu, H., Li, C., Liu, X., & Wong, T.-T. (2022). End-to-End Line Drawing Vectorization. Proceedings of the AAAI Conference on Artificial Intelligence, 36(4), 4559-4566. https://doi.org/10.1609/aaai.v36i4.20379



AAAI Technical Track on Domain(s) Of Application