ToonCap: A layered deformable model for capturing poses from cartoon characters

Xinyi Fan, Amit H. Bermano, Vladimir G. Kim, Jovan Popović, Szymon Rusinkiewicz

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Characters in traditional artwork such as children’s books or cartoon animations are typically drawn once, in xed poses, with little opportunity to change the characters’ appearance or re-use them in a dierent animation. To enable these applications one can t a consistent parametric deformable model — a puppet — to dier-ent images of a character, thus establishing consistent segmentation, dense semantic correspondence, and deformation parameters across poses. In this work, we argue that a layered deformable puppet is a natural representation for hand-drawn characters, providing an eective way to deal with the articulation, expressive deformation, and occlusion that are common to this style of artwork. Our main contribution is an automatic pipeline for tting these models to unlabeled images depicting the same character in various poses. We demonstrate that the output of our pipeline can be used directly for editing and re-targeting animations.

Original languageEnglish
Title of host publicationProceedings - Expressive 2018
Subtitle of host publicationComputational Aesthetics Sketch-Based Interfaces and Modeling Non-Photorealistic Animation and Rendering
EditorsStephen N. Spencer
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450358927
DOIs
StatePublished - 17 Aug 2018
Externally publishedYes
Event2018 Joint Symposium on Computational Aesthetics Sketch-Based Interfaces and Modeling Non-Photorealistic Animation and Rendering, Expressive 2018 - Victoria, Canada
Duration: 17 Aug 201819 Aug 2018

Publication series

NameProceedings - Expressive 2018: Computational Aesthetics Sketch-Based Interfaces and Modeling Non-Photorealistic Animation and Rendering

Conference

Conference2018 Joint Symposium on Computational Aesthetics Sketch-Based Interfaces and Modeling Non-Photorealistic Animation and Rendering, Expressive 2018
Country/TerritoryCanada
CityVictoria
Period17/08/1819/08/18

Keywords

  • Character animation
  • Correspondence
  • Registration
  • Segmentation

Fingerprint

Dive into the research topics of 'ToonCap: A layered deformable model for capturing poses from cartoon characters'. Together they form a unique fingerprint.

Cite this