Princeton > CS Dept > PIXL > Publications Local Access 

ToonCap: A Layered Deformable Model for Capturing Poses From Cartoon Characters
Expressive, August 2018

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


Given an input puppet constructed from a reference frame with annotated layers, joints, and handles, we capture poses in novel unlabeled images by registering the puppet to each image. This enables editing other frames by altering the puppet’s artwork and synthesizing novel animations by interpolation. We demonstrate the utility of this approach by animating static characters from books and by re-targeting motion to new characters.

Abstract

Characters in traditional artwork such as children's books or cartoon animations are typically drawn once, in fixed poses, with little opportunity to change the characters' appearance or re-use them in a different animation. To enable these applications one can fit a consistent parametric deformable model - a puppet - to different 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 effective 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 fitting 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.

Citation (BibTeX)

Xinyi Fan, Amit H. Bermano, Vladimir G. Kim, Jovan Popović, and Szymon Rusinkiewicz. ToonCap: A Layered Deformable Model for Capturing Poses From Cartoon Characters. Expressive, August 2018.

Paper
  PDF file
  Video