Full Text:   <1853>

CLC number: TP391

On-line Access: 2012-03-01

Received: 2011-07-08

Revision Accepted: 2011-11-07

Crosschecked: 2012-02-08

Cited: 0

Clicked: 3728

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
1. Reference List
Open peer comments

Journal of Zhejiang University SCIENCE C 2012 Vol.13 No.3 P.196-207


Synthesizing style-preserving cartoons via non-negative style factorization

Author(s):  Zhang Liang, Jun Xiao, Yue-ting Zhuang

Affiliation(s):  Institute of Artificial Intelligence, School of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China

Corresponding email(s):   liangzhang@zju.edu.cn, junx@zju.edu.cn, yzhuang@zju.edu.cn

Key Words:  Character cartoon, Machine learning, Cartoon synthesis

Zhang Liang, Jun Xiao, Yue-ting Zhuang. Synthesizing style-preserving cartoons via non-negative style factorization[J]. Journal of Zhejiang University Science C, 2012, 13(3): 196-207.

@article{title="Synthesizing style-preserving cartoons via non-negative style factorization",
author="Zhang Liang, Jun Xiao, Yue-ting Zhuang",
journal="Journal of Zhejiang University Science C",
publisher="Zhejiang University Press & Springer",

%0 Journal Article
%T Synthesizing style-preserving cartoons via non-negative style factorization
%A Zhang Liang
%A Jun Xiao
%A Yue-ting Zhuang
%J Journal of Zhejiang University SCIENCE C
%V 13
%N 3
%P 196-207
%@ 1869-1951
%D 2012
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.C1100202

T1 - Synthesizing style-preserving cartoons via non-negative style factorization
A1 - Zhang Liang
A1 - Jun Xiao
A1 - Yue-ting Zhuang
J0 - Journal of Zhejiang University Science C
VL - 13
IS - 3
SP - 196
EP - 207
%@ 1869-1951
Y1 - 2012
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.C1100202

We present a complete framework for synthesizing style-preserving 2D cartoons by learning from traditional Chinese cartoons. In contrast to reusing-based approaches which rely on rearranging or retrieving existing cartoon sequences, we aim to generate stylized cartoons with the idea of style factorization. Specifically, starting with 2D skeleton features of cartoon characters extracted by an improved rotoscoping system, we present a non-negative style factorization (NNSF) algorithm to obtain style basis and weights and simultaneously preserve class separability. Thus, factorized style basis can be combined with heterogeneous weights to re-synthesize style-preserving features, and then these features are used as the driving source in the character reshaping process via our proposed subkey-driving strategy. Extensive experiments and examples demonstrate the effectiveness of the proposed framework.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article


[1]Agarwala, A., Hertzmann, A., Salesin, D.H., Seitz, S.M., 2004. Keyframe-based tracking for rotoscoping and animation. ACM Trans. Graph., 23(3):584-591.

[2]Aharon, M., Elad, M., Bruckstein, A., 2006. K-SVD: an algorithm for designing of overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process., 54(11):4311-4322.

[3]Alexa, M., Cohen-Or, D., Levin, D., 2000. As-Rigid-as-Possible Shape Interpolation. Proc. SIGGRAPH, p.157-164.

[4]Brand, M., Hertzmann, A., 2000. Style Machines. Proc. SIGGRAPH, p.183-192.

[5]Bregler, C., Loeb, L., Chuang, E., Deshpande, H., 2002. Turning to the masters: motion capturing cartoons. ACM Trans. Graph., 21(3):399-407.

[6]Chenney, S., Pingel, M., Iverson, R., Szymanski, M., 2002. Simulating Cartoon Style Animation. Proc. NPAR, p.133-138.

[7]Freifeld, O., Weiss, A., Zuffi, S., Black, M.J., 2010. Contour People: a Parameterized Model of 2D Articulated Human Shape. Proc. CVPR, p.639-646.

[8]Guan, P., Freifeld, O., Black, M., 2010. A 2D Human Body Model Dressed in Eigen Clothing. Proc. ECCV, p.285-298.

[9]Hoch, M., Litwinowicz, P.C., 1996. A semi-automatic system for edge tracking with snakes. Vis. Comput., 12(2):75-83.

[10]Hornung, A., Dekkers, E., Kobbelt, L., 2007. Character animation from 2D pictures and 3D motion data. ACM Trans. Graph., 26(1):1-es.

[11]Hoyer, P.O., 2002. Non-negative Sparse Coding. Proc. 12th IEEE Workshop on Neural Networks for Signal Processing, p.557-565.

[12]Hsu, E., Pulli, K., Popović, J., 2005. Style translation for human motion. ACM Trans. Graph., 24(3):1082-1089.

[13]Igarashi, T., Moscovich, T., Hughes, J.F., 2005. As-rigid-as-possible shape manipulation. ACM Trans. Graph., 24(3):1134-1141.

[14]Jonker, R., Volgenant, A., 1987. A shortest augmenting path algorithm for dense and sparse linear assignment problems. Computing, 38(4):325-340.

[15]Kuo, P., Makris, D., Megherbi, N., Nebel, J.C., 2008. Integration of local image cues for probabilistic 2D pose recovery. LNCS, 5359:214-223.

[16]Kwon, J., Lee, I.K., 2008. Exaggerating character motions using sub-joint hierarchy. Comput. Graph. Forum, 27(6):1677-1686.

[17]Lau, M., Chai, J., Xu, Y.Q., Shum, H.Y., 2009. Face poser: interactive modeling of 3D facial expressions using facial priors. ACM Trans. Graph., 29(1):1-17.

[18]Lee, D.D., Seung, H.S., 2001. Algorithms for Non-negative Matrix Factorization. Proc. NIPS, 13:556-562.

[19]Li, Y., Gleicher, M., Xu, Y.Q., Shum, H.Y., 2003. Stylizing Motion with Drawings. Proc. SCA, p.309-319.

[20]Ma, X., Le, B.H., Deng, Z., 2009. Style Learning and Transferring for Facial Animation Editing. Proc. SCA, p.123-132.

[21]Moeslund, T.B., Hilton, A., Krüger, V., 2006. A survey of advances in vision-based human motion capture and analysis. Comput. Vis. Image Understand., 104(2-3):90-126.

[22]Pullen, K., Bregler, C., 2002. Motion capture assisted animation: texturing and synthesis. ACM Trans. Graph., 21(3):501-508.

[23]Rogez, G., Orrite-Uruñuela, C., Martínez-del-Rincón, J., 2008. A spatio-temporal 2D-models framework for human pose recovery in monocular sequences. Pattern Recogn., 41(9):2926-2944.

[24]Schaefer, S., McPhail, T., Warren, J., 2006. Image deformation using moving least squares. ACM Trans. Graph., 25(3):533-540.

[25]Sýkora, D., Sedlacek, D., Jinchao, S., Dingliana, J., Collins, S., 2010. Adding depth to cartoons using sparse depth (in)equalities. Comput. Graph. Forum, 29(2):615-623.

[26]Tenenbaum, J.B., Freeman, W.T., 2000. Separating style and content with bilinear models. Neur. Comput., 12(6):1247-1283.

[27]Tenenbaum, J.B., Silva, V., Langford, J.C., 2000. A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500):2319-2323.

[28]Torresani, L., Hackney, P., Bregler, C., 2007. Learning Motion Style Synthesis from Perceptual Observations. Proc. NIPS, 19:1393-1400.

[29]Wang, H., Li, H., 2002. Cartoon Motion Capture by Shape Matching. Proc. Conf. on Computer Graphics and Applications, p.454-456.

[30]Wang, J., Drucker, S.M., Agrawala, M., Cohen, M.F., 2006. The cartoon animation filter. ACM Trans. Graph., 25(3):1169-1173.

[31]Wang, J.M., Fleet, D.J., Hertzmann, A., 2007. Multifactor Gaussian Process Models for Style-Content Separation. Proc. ICML, p.975-982.

[32]Weng, Y., Xu, W., Wu, Y., Zhou, K., Guo, B., 2006. 2D shape deformation using nonlinear least squares optimization. Vis. Comput., 22(9-11):653-660.

[33]Yan, H.B., Hu, S., Martin, R.R., Yang, Y.L., 2008. Shape deformation using a skeleton to drive simplex transformations. IEEE Trans. Visual. Comput. Graph., 14(3):693-706.

[34]Yang, Y., Zhuang, Y., Xu, D., Pan, Y., Tao, D., Maybank, S., 2009. Retrieval Based Interactive Cartoon Synthesis via Unsupervised Bi-distance Metric Learning. Proc. Conf. on Multimedia, p.311-320.

[35]Zhou, S., Fu, H., Liu, L., Cohen-Or, D., Han, X., 2010. Parametric Reshaping of Human Bodies in Images. Proc. SIGGRAPH, p.1-10.

Open peer comments: Debate/Discuss/Question/Opinion


Please provide your name, email address and a comment

Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE