Keypoint-driven line drawing vectorization via polyvector flow
dc.contributor.author | Puhachov, Ivan | |
dc.contributor.author | Neveu, William | |
dc.contributor.author | Chien, Edward | |
dc.contributor.author | Bessmeltsev, Mikhail | |
dc.date.accessioned | 2021-11-22T16:07:15Z | |
dc.date.available | NO_RESTRICTION | fr |
dc.date.available | 2021-11-22T16:07:15Z | |
dc.date.issued | 2021-12 | |
dc.identifier.uri | http://hdl.handle.net/1866/25811 | |
dc.publisher | Association for Computing Machinery | fr |
dc.title | Keypoint-driven line drawing vectorization via polyvector flow | fr |
dc.type | Article | fr |
dc.contributor.affiliation | Université de Montréal. Faculté des arts et des sciences. Département d'informatique et de recherche opérationnelle | fr |
dc.identifier.doi | 10.1145/3478513.3480529 | |
dcterms.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. | fr |
dcterms.isPartOf | urn:ISSN: 0730-0301 | fr |
dcterms.isPartOf | urn:ISSN:1557-7368 | fr |
dcterms.language | eng | fr |
UdeM.ReferenceFournieParDeposant | Keypoint-Driven Line Drawing Vectorization via PolyVector Flow Ivan Puhachov, William Neveu, Edward Chien, Mikhail Bessmeltsev ACM Transaction on Graphics (SIGGRAPH ASIA 2021) | fr |
UdeM.VersionRioxx | Version acceptée / Accepted Manuscript | fr |
oaire.citationTitle | ACM Transactions on graphics | fr |
oaire.citationVolume | 40 | fr |
oaire.citationIssue | 6 | fr |
Fichier·s constituant ce document
Ce document figure dans la ou les collections suivantes
Ce document diffusé sur Papyrus est la propriété exclusive des titulaires des droits d'auteur et est protégé par la Loi sur le droit d'auteur (L.R.C. (1985), ch. C-42). Il peut être utilisé dans le cadre d'une utilisation équitable et non commerciale, à des fins d'étude privée ou de recherche, de critique ou de compte-rendu comme le prévoit la Loi. Pour toute autre utilisation, une autorisation écrite des titulaires des droits d'auteur sera nécessaire.