“Modeling Character Canvases From Cartoon Drawings” by Bessmeltsev, Chang, Vining, Sheffer and Singh

  • ©Mikhail Bessmeltsev, Will Chang, Nicholas Vining, Alla Sheffer, and Karan Singh




    Modeling Character Canvases From Cartoon Drawings

Session/Category Title:   EXPRESSIVE ANIMATION




    We introduce a novel technique for the construction of a 3D character proxy, or canvas, directly from a 2D cartoon drawing and a user-provided correspondingly posed 3D skeleton. Our choice of input is motivated by the observation that traditional cartoon characters are well approximated by a union of generalized surface of revolution body parts, anchored by a skeletal structure. While typical 2D character contour drawings allow ambiguities in 3D interpretation, our use of a 3D skeleton eliminates such ambiguities and enables the construction of believable character canvases from complex drawings. Our canvases conform to the 2D contours of the input drawings, and are consistent with the perceptual principles of Gestalt continuity, simplicity, and contour persistence. We first segment the input 2D contours into individual body-part outlines corresponding to 3D skeletal bones using the Gestalt continuation principle to correctly resolve inter-part occlusions in the drawings. We then use this segmentation to compute the canvas geometry, generating 3D generalized surfaces of revolution around the skeletal bones that conform to the original outlines and balance simplicity against contour persistence. The combined method generates believable canvases for characters drawn in complex poses with numerous inter-part occlusions, variable contour depth, and significant foreshortening. Our canvases serve as 3D geometric proxies for cartoon characters, enabling unconstrained 3D viewing, articulation, and non-photorealistic rendering. We validate our algorithm via a range of user studies and comparisons to ground-truth 3D models and artist-drawn results. We further demonstrate a compelling gallery of 3D character canvases created from a diverse set of cartoon drawings with matching 3D skeletons.


    1. Adobe Flash. 2013. Professional. Adobe, Inc. https://www.adobe.com/support/flash/downloads.html.
    2. Anime Studio. 2013. Smith micro software. http://my.smithmicro.com/anime-studio-2D-animation-software.html.
    3. O. K.-C. Au, C.-L. Tai, H.-K. Chu, D. Cohen-Or, and T.-Y. Lee. 2008. Skeleton extraction by mesh contraction. ACM Trans. Graph. 27, 3, 44:1–44:10. 
    4. J. A. Bærentzen, R. Abdrashitov, and K. Singh. 2014. Interactive shape modeling using a skeleton-mesh co-representation. ACM Trans. Graph. 33, 4, 132:1–132:10. 
    5. K. Bassett, I. Baran, J. Schmid, M. Gross, and R. W. Sumner. 2013. Authoring and animating painterly characters. ACM Trans. Graph. 32, 5, 156:1–156:12. 
    6. J. Bloomenthal and B. Wyvill, Eds. 1997. Introduction to Implicit Surfaces. Morgan Kaufmann, San Fransisco. 
    7. P. Borosán, M. Jin, D. DeCarlo, Y. Gingold, and A. Nealen. 2012. Rigmesh: Automatic rigging for part-based shape modeling and deformation. ACM Trans. Graph. 31, 6, 198:1–198:9. 
    8. P. Buchanan, R. Mukundan, and M. Doggett. 2013. Automatic single-view character model reconstruction. In Proceedings of the Symposium on Sketch-Based Interfaces and Modeling (SBIM’13). 5–14. 
    9. T. Chen, Z. Zhu, A. Shamir, S.-M. Hu, and D. Cohen-Or. 2013. 3-Sweep: Extracting editable objects from a single photo. ACM Trans. Graph. 32, 6. 
    10. J. J. Cherlin, F. Samavati, M. C. Sousa, and J. A. Jorge. 2005. Sketch-based modeling with few strokes. In Proceedings of the 21st Spring Conference on Computer Graphics (SCCG’05). 
    11. F. Cordier, H. Seo, J. Park, and J. Y. Noh. 2011. Sketching of mirror-symmetric shapes. IEEE Trans. Visual. Comput. Graph. 17, 11. 
    12. N. D. Cornea, D. Silver, X. Yuan, and R. Balasubramanian. 2005. Computing hierarchical curve-skeletons of 3D objects. Vis. Comput. 21, 11, 945–955.
    13. E. Entem, L. Barthe, M.-P. Cani, F. Cordier, and M. Van de Panne. 2014. Modeling 3D animals from a side-view sketch. http://www.irit.fr/recherches/VORTEX/publications/rendu-geometrie/SMI2014_Entem_et_al.pdf.
    14. F. D. Fiore, P. Schaeken, and K. Elens. 2001. Automatic in-betweening in computer assisted animation by exploiting 2.5D modeling techniques. In Proceedings of the Conference on Computer Animation (CA’01). 192–300.
    15. Y. Gingold, T. Igarashi, and D. Zorin. 2009. Structured annotations for 2D-to-3D modeling. ACM Trans. Graph. 28, 5. 
    16. Gurobi Optimization. 2013. http://www.gurobi.com/.
    17. R. Hess and D. Field. 1999. Integration of contours: New insights. Trends Cogn. Sci. 3, 12, 408–486.
    18. D. D. Hoffman. 2000. Visual Intelligence: How to Create What We Are. Norton, New York.
    19. B. Hogarth. 1996. Dynamic Figure Drawing. Watson-Guptill.
    20. A. Hornung, E. Dekkers, and L. Kobbelt. 2007. Character animation from 2D pictures and 3D motion data. ACM Trans. Graph. 26, 1, 1–9. 
    21. T. Igarashi, S. Matsuoka, and H. Tanaka. 1999. Teddy: A sketching interface for 3D freeform design. In Proceedings of the Annual ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’99). 409–416. 
    22. A. Jacobson and O. Sorkine. 2011. Stretchable and twistable bones for skeletal shape deformation. ACM Trans. Graph. 30, 6, 165:1–165:8. 
    23. E. Jain, Y. Sheikh, M. Mahler, and J. Hodgins. 2012. Three-dimensional proxies for hand-drawn characters. ACM Trans. Graph. 31, 1, 1–16. 
    24. O. A. Karpenko and J. F. Hughes. 2006. SmoothSketch: 3D freeform shapes from complex meshes. ACM Trans. Graph. 1, 212, 589–598. 
    25. K. Koffka. 1955. Principles of Gestalt Psychology. International Library of Psychology, Philosophy, and Scientific Method. Routledge and K. Paul.
    26. Z. Levi and C. Gotsman. 2013. ArtiSketch: A system for articulated sketch modeling. Comput. Graph. Forum 32, 2, 235–244.
    27. C. Maraffi. 2003. Maya Character Creation: Modeling and Animation Controls. Voices that Matter. Pearson Education. 
    28. T. B. Moeslund, A. Hilton, and V. Krger. 2006. A survey of advances in vision-based human motion capture and analysis. Comput. Vis. Image Understand. 104, 23, 90–126. 
    29. K. Nakayama and S. Shimojo. 1992. Experiencing and perceiving visual surfaces. Sci. 257, 1357–1363.
    30. A. Nealen, O. Sorkine, and M. Alexa. 2007. FiberMesh: Designing freeform surfaces with 3d curves. In ACM SIGGRAPH Papers. 1–8. 
    31. A. Nealen, O. Sorkine, M. Alexa, and D. Cohen-Or. 2005. A sketch-based interface for detail-preserving mesh editing. ACM Trans. Graph. 24, 3, 1142–1147. 
    32. L. Olsen, F. Samavati, and J. A. Jorge. 2011. NaturaSketch: Modeling from images and natural sketches. IEEE Comput. Graph. Appl. 31, 6, 24–34. 
    33. L. Olsen, F. Samavati, M. Sousa, and J. Jorge. 2009. Sketch-based modeling: A survey. Comput. Graph. 33. 
    34. Paperman. 2012. Walt Disney Animation Studios. http://www.disneyanimation.com/projects/paperman/.
    35. Z. Pizlo and A. Stevenson. 1999. Shape constancy from novel views. Percept. Psychophys. 61, 7, 1299–1307.
    36. A. Rivers, F. Durand, and T. Igarashi. 2010. 2.5D cartoon models. In Proceedings of the Annual ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’10). 
    37. P. Sand, L. McMillan, and J. Popovic. 2003. Continuous capture of skin deformation. In Proceedings of the Annual ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’03). ACM Press, New York, 578–586. 
    38. J. Schmid, M. S. Senn, M. Gross, and R. W. Sumner. 2011. Overcoat: An implicit canvas for D painting. ACM Trans. Graph. 30, 28:1–28:10. 
    39. C. Shao, A. Bousseau, A. Sheffer, and K. Singh. 2012. CrossShade: Shading concept sketches using cross-section curves. ACM Trans. Graph. 31, 4. 
    40. A. Shtof, A. Agathos, Y. Gingold, A. Shamir, and D. Cohen-Or. 2013. Geosemantic snapping for sketch-based modeling. Comput. Graph. Forum 32, 2, 245–253.
    41. D. Sýkora, L. Kavan, M. Čadík, O. Jamriška, A. Jacobson, B. Whited, M. Simmons, and O. Sorkine-Hornung. 2014. Ink-and-ray: Bas-relief meshes for adding global illumination effects to hand-drawn characters. ACM Trans. Graph. 33, 2, 16. 
    42. C.-L. Tai, H. Zhang, and J. C.-K. Fong. 2004. Prototype modeling from sketched silhouettes based on convolution surfaces. Comput. Graph. Forum 23, 1, 71–83.
    43. R. Williams. 2001. The Animator’s Survival Kit. Faber and Faber.
    44. K.-Y. K. Wong, P. R. Medona, and R. Cipolla. 2004. Reconstruction of surfaces of revolution from single uncalibrated views. Image Vis. Comput. 22, 10, 829–836.
    45. B. Xu, W. Chang, A. Sheffer, A. Bousseau, J. McCrae, and K. Singh. 2014. True2form: 3D curve networks from 2D sketches via selective regularization. ACM Trans. Graph. 33, 4. 
    46. G. Ye, Y. Liu, N. Hasler, X. Ji, Q. Dai, and C. Theobalt. 2012. Performance capture of interacting characters with handheld kinects. In Proceedings of the European Conference on Computer Vision (ECCV’12). 828–841. 

ACM Digital Library Publication:

Overview Page: