Stroke style transfer

Sara Shaheen, Bernard Ghanem

Research output: Contribution to conferencePaperpeer-review

1 Scopus citations

Abstract

We propose a novel method to transfer sketch style at the stroke level from one free-hand line drawing to another, whereby these drawings can be from different artists. It aims to transfer the style of the input sketch at the stroke level to the style encountered in sketches by other artists. This is done by modifying all the parametric stroke segments in the input, so as to minimize a global stroke-level distance between the input and target styles. To do this, we exploit a recent work on stroke authorship recognition to define the stroke-level distance [SRG15], which is in turn minimized using conventional optimization tools. We showcase the quality of style transfer qualitatively by applying the proposed technique on several input-target combinations.

Original languageEnglish (US)
Pages53-56
Number of pages4
DOIs
StatePublished - 2017
Event38th Annual Conference on European Association for Computer Graphics, EUROGRAPHICS 2017 - Lyon, France
Duration: Apr 24 2017Apr 28 2017

Conference

Conference38th Annual Conference on European Association for Computer Graphics, EUROGRAPHICS 2017
Country/TerritoryFrance
CityLyon
Period04/24/1704/28/17

Bibliographical note

Funding Information:
Limitations Our proposed method is just the start towards achieving a comprehensive sketch style transfer. It only modifies existing strokes with no elimination or addition of strokes. Although this helps in applying changes where the difference between styles is minor, there is a great potential of improvement in progressive research work which enables major transformations. Acknowledgments This work was supported by competitive research funding from King Abdullah University of Science and Technology (KAUST).

Publisher Copyright:
Eurographics Proceedings © 2017 The Eurographics Association.

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'Stroke style transfer'. Together they form a unique fingerprint.

Cite this