Multimedia Tools and Applications

, Volume 74, Issue 13, pp 4873–4889 | Cite as

Correspondence specification learned from master frames for automatic inbetweening

  • Bingwen Jin
  • Weidong Geng


We present a new approach to automatically specify the correspondences between hand-drawn keyframes for automatic inbetweening in 2D facial cartoon animation. Recent techniques are not robust to occlusion as they mainly rely on the information provided by the keyframes, which are 2D drawings lacking 3D information. Our approach creates a hybrid face model to learn the prior knowledge about the approximate 3D geometry and multi-view appearances of an individual character’s face from master frames to overcome the lack of information. Based on the hybrid model, we combine our example-based stroke annotating method with our example-based viewpoint recognition method to automatically specify accurate stroke correspondences, even when there is occlusion. Our approach facilitates auto-inbetweening much.


Facial cartoon animation Inbetweening Keyframe Correspondence specification 



This work was supported by a grant from National Program on Key Basic Research Project of China (973 Program, 2013CB329504), National High Technology Research and Development Program of China (863 Program, 2013AA013705), National Natural Science Foundation of China (N0. 61379067), and National Key Technology R&D Program of the Ministry of Science and Technology (2012BAH03F03).


  1. 1.
    Baxter WV III, Barla P, Anjyo K-i (2009) Compatible embedding for 2d shape animation. IEEE Trans Vis Comput Graph 15(5):867–879CrossRefGoogle Scholar
  2. 2.
    Bregler C, Loeb L, Chuang E, Deshpande H (2002) Turning to the masters: motion capturing cartoons. In: SIGGRAPH ’02. ACM, New York, pp 399–407Google Scholar
  3. 3.
    Catmull E (1978) The problems of computer-assisted animation. SIGGRAPH Comput Graph 12:348–353CrossRefGoogle Scholar
  4. 4.
    Chang C-W, Lee S-Y (1997) Automatic cel painting in computer-assisted cartoon production using similarity recognition. J Vis Comput Animat 8(3):165–185CrossRefGoogle Scholar
  5. 5.
    Chang C-C, Lin C-J (2001) LIBSVM: a library for support vector machines. Software available at
  6. 6.
    Huang J, Shao X, Wechsler Harry (1998) Face pose discrimination using support vector machines (SVM). In: Proceedings of the 14th international conference on pattern recognition, vol 1. IEEE, pp 154–156,Google Scholar
  7. 7.
    Isenberg T, Freudenberg B, Halper N, Schlechtweg S, Strothotte T (2003) A developer’s guide to silhouette algorithms for polygonal models. IEEE Comput Graph Appl 23(4):28–37CrossRefGoogle Scholar
  8. 8.
    Jun Y, Wei B, Mingli S, Jun C, Dacheng T (2012) Graph based transductive learning for cartoon correspondence construction. Neurocomputing 79:105–114CrossRefGoogle Scholar
  9. 9.
    Knerr S, Personnaz L, Dreyfus G (1990) Single-layer learning revisited: a stepwise procedure for building and training a neural network. In: Neurocomputing, Springer, pp 41–50Google Scholar
  10. 10.
    Kort A (2002) Computer aided inbetweening. In: NPAR ’02. ACM, New York, pp 125–132Google Scholar
  11. 11.
    Li X, Xu J, Ren Y, Geng W (2010) Animating cartoon faces by multi-view drawings. Animat Virtual Worlds 21(3–4):193–201Google Scholar
  12. 12.
    Li SZ, Fu Q, Gu L, Scholkopf B, Cheng Y, Zhang H (2001) Kernel machine based learning for multi-view face detection and pose estimation. In: Proceedings of the 8th IEEE international conference on computer vision, vol 2. IEEEGoogle Scholar
  13. 13.
    Liu D, Chen Q, Jun Y, Huiqin G, Tao D, Seah HS (2011) Stroke correspondence construction using manifold learning. Comput Graph Forum 30(8):2194–2207CrossRefGoogle Scholar
  14. 14.
    Ma B, Zhang W, Shan S, Chen X, Gao W (2006) Robust head pose estimation using LGBP. In: Proceedings of the 18th international conference on pattern recognition, vol 2, pp 512–515. IEEEGoogle Scholar
  15. 15.
    Madeira JS, Stork A, Gross MH (1996) An approach to computer-supported cartooning. Vis Comput 12(1):1–17CrossRefGoogle Scholar
  16. 16.
    Mao X, Isobe S, Anjyo K, Imamiya A (2005) Skethy hairstyles. In: Computer graphics international. IEEE, pp 142–147Google Scholar
  17. 17.
    Peng H, Long F, Ding C (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27(8):1226–1238CrossRefGoogle Scholar
  18. 18.
    Qiu J, Seah HS, Tian F, Chen Q, Melikhov K (2003) Computer-assisted auto coloring by region matching. In: PG ’03. IEEE, Washington, DC, p 17Google Scholar
  19. 19.
    Qiu J, Seah HS, Tian F, Zhongke W, Chen Q (2005) Feature- and region-based auto painting for 2d animation. Vis Comput 21:928–944CrossRefGoogle Scholar
  20. 20.
    Qiu J, Seah HS, Tian F, Chen Q, Zhongke W (2005) Enhanced auto coloring with hierarchical region matching: image, colour and illumination in animation.Comput Animat Virtual Worlds 16:463–473CrossRefGoogle Scholar
  21. 21.
    Qiu J, Seah HS, Tian F, Chen Q, Zhongke W (2008) Auto coloring with enhanced character registration. Int J Comput Games Technol 2008:21–27CrossRefGoogle Scholar
  22. 22.
    Rivers A, Igarashi T, Durand F (2010) 2.5D cartoon models. ACM Trans Graph 29(4):591–597. ACMGoogle Scholar
  23. 23.
    Seah HS, Feng T (2000) Computer-assisted coloring by matching line drawings. Vis Comput 16:289–304CrossRefGoogle Scholar
  24. 24.
    Seitz SM, Dyer CR (1996) View morphing. In: SIGGRAPH ’96. ACM, pp 21–30Google Scholar
  25. 25.
    Song Z, Yu J, Zhou C, Wang M (2013) Automatic cartoon matching in computer-assisted animation production. NeurocomputingGoogle Scholar
  26. 26.
    Sýkora D, Buriánek J, žára J (2005) Colorization of black-and-white cartoons. Image Vis Comput 23(9):767–782CrossRefGoogle Scholar
  27. 27.
    Sýkora D, Dingliana J, Collins S (2009) As-rigid-as-possible image registration for hand-drawn cartoon animations. In: NPAR ’09. pp 25–33Google Scholar
  28. 28.
    Sỳkora D, Ben-Chen M, C~adík M, Whited B, Simmons M (2011) TexToons: practical texture mapping for hand-drawn cartoon animations. In: NPAR ’11. pp 75–84Google Scholar
  29. 29.
    Whited B, Noris G, Simmons M, Sumner RW, Gross M, Betweenit JR (2010) An interactive tool for tight inbetweening. Comput Graphics Forum (Proc Eurographics) 29(2):605–614CrossRefGoogle Scholar
  30. 30.
    Zhenyao M, Lewis JP, Neumann (2005) SmartCanvas: a gesture-driven intelligent drawing desk system. In: Proceedings of the 10th international conference on intelligent user interfaces. ACM, pp 239–243Google Scholar
  31. 31.
    Zhou X-D, Liu C-LText/non-text ink stroke classification in japanese handwriting based on markov random fields. In: ICDAR, vol 1. IEEE, pp 377–381Google Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  1. 1.State Key Lab of CAD&CG, College of Computer Science and TechnologyZhejiang UniversityHangzhouChina

Personalised recommendations