PicToon: A Personalized Image-based Cartoon System
Author(s): Hong Chen, Lin Liang, Yan Li, Ying-Qing Xu, Heung-Yeung Shum.
Proceedings: Proceedings of the tenth ACM international conference on Multimedia (MULTIMEDIA '02), pp. 171--178, December,
2002.
[BibTeX]
Abstract:
In this paper, we present PicToon, a cartoon system which can generate
a personalized cartoon face from an input image. PicToon is
easy to use and requires little user interaction. Our system consists
of three major components: an image-based automatic Cartoon
Generator, an interactive Cartoon Editor for exaggeration, and a
speech-driven Cartoon Animator. First, to capture an artistic style,
the cartoon generation is decoupled into two processes: sketch generation
and stroke rendering. An example-based approach is taken
to automatically generate sketch lines which depict the facial structure.
An inhomogeneous non-parametric sampling plus a flexible
facial template is employed to extract the vector-based facial
sketch. Various styles of strokes can then be applied. Second, with
the pre-designed templates in Cartoon Editor, the user can easily
make the cartoon exaggerated or more expressive. Third, a real
time lip-syncing algorithm is also developed by recovering a statistical
audio-visual mapping between the character’s voice and the
corresponding lip configuration. Experimental results demonstrate
the effectiveness of our system.