Keypoint-Driven Line Drawing Vectorization via PolyVector Flow

Ivan Puhachov\(^1\), William Neveu\(^1\), Edward Chien\(^2\), Mikhail Bessmeltsev\(^1\)

\(^1\) Université de Montréal
\(^2\) Boston University

SIGGRPAPH Asia 2021

PDF

Supplementary (105MB)

BibTeX

Code

Data

Given a greyscale bitmap drawing, we use deep learning--based machinery to extract keypoints: junctions, curve endpoints, and sharp corners. We then compute a frame field aligned to the drawing and extract the drawing topology finding curves connecting the keypoints. Finally, we use our novel PolyVector flow that aligns those curves to the frame field, robustly disambiguating directions around keypoints. Input image is from www.easy-drawings-and-sketches.com (c) Ivan Huska.

Abstract

Line drawing vectorization is a daily task in graphic design, computer animation, and engineering, necessary to convert raster images to a set of curves for editing and geometry processing. Despite recent progress in the area, automatic vectorization tools often produce spurious branches or incorrect connectivity around curve junctions; or smooth out sharp corners. These issues detract from the use of such vectorization tools, both from an aesthetic viewpoint and for feasibility of downstream applications (e.g., automatic coloring or inbetweening). We address these problems by introducing a novel line drawing vectorization algorithm that splits the task into three components: (1) finding keypoints, i.e., curve endpoints, junctions, and sharp corners; (2) extracting drawing topology, i.e., finding connections between keypoints; and (3) computing the geometry of those connections. We compute the optimal geometry of the connecting curves via a novel geometric flow — PolyVector Flow — that aligns the curves to the drawing, disambiguating directions around Y-, X-, and T-junctions. We show that our system robustly infers both the geometry and topology of detailed complex drawings. We validate our system both quantitatively and qualitatively, demonstrating that our method visually outperforms previous work.

Citation

@article{Puhachov2021KeypointPolyvector,
    author = {Ivan Puhachov and William Neveu and Edward Chien and Mikhail Bessmeltsev},
    title = {Keypoint-Driven Line Drawing Vectorization via PolyVector Flow},
    journal = {ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia)},
    volume = {40}, number = {6}, year = {2021}, month = dec,
    doi = {10.1145/3478513.3480529}
}