Viva: a Variational Image Vectorization Algorithm on Dual-Primal Graph Pairs

Yuchen HE*, Sung Ha KANG, Jean-Michel MOREL

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

2 Citations (Scopus)

Abstract

We propose a novel variational image vectorization algorithm (VIVA) which alternatively smooths contours by affine shortening flow and eliminates spurious regions by minimizing a Mumford-Shah-type functional. We introduce dual-primal graphs representing domain partitions which allows for effective iterative computation. The method provides varying levels of simplicity on the topology of the resulted vector graphics while effectively removing pixelization. It compares favorably to the state-of-the-art (SOTA) vectorization methods.
Original languageEnglish
Title of host publication2023 IEEE International Conference on Image Processing, ICIP 2023, Proceedings
PublisherIEEE
Pages1285-1289
Number of pages5
ISBN (Electronic)9781728198354
ISBN (Print)9781728198361
DOIs
Publication statusPublished - 2023
Externally publishedYes
Event2023 IEEE International Conference on Image Processing - Kuala Lumpur, Malaysia
Duration: 8 Oct 202311 Oct 2023

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference2023 IEEE International Conference on Image Processing
Country/TerritoryMalaysia
CityKuala Lumpur
Period8/10/2311/10/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Funding

∗Research is supported in part by Postdoctoral International Exchange Program by the Office of China Postdoc Council (OCPC) and INS, SJTU †Research is supported in part by Simons Foundation grant 584960. ‡Supported by Fondation Mathématique Jacques Hadamard

Keywords

  • affine-shortening flow
  • Image vectorization
  • Mumford-Shah functional
  • optimization

Fingerprint

Dive into the research topics of 'Viva: a Variational Image Vectorization Algorithm on Dual-Primal Graph Pairs'. Together they form a unique fingerprint.

Cite this