Abstract
Our research in this paper is a new method for facial expression generation based upon extrinsic and intrinsic information with the advantages of direct processing of Point Clouds (PCs). In our pipeline of facial expression generation, there is no need to set up a face model or facial expression database in advance or to construct any mesh or surface models. The basic idea of our method is that the animation of facial expression is achieved by a combination of Global Face Motion and Local Face Motion. In the former, Global Face Motion can be decided by the ICP algorithm, while the latter takes charge of partial movements on the face. Finding correct corresponding points is important for generating an intermediate face from two different facial expressions. This process yields in a good result of the interpolated PCs for facial expression generation between two different facial PCs. Finally, the experimental result shows fairly satisfactory facial expression generation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
How many muscles are there in the human face? An illustration for good research and writing. http://manna-in-the-wild.hubpages.com/hub/how-many-muscles-are-there-in-the-human-face; 2011.
Gross M, Pfister H. Point-based graphics, Morgan Kaufmann; 2007, p. 3.
Greiner G, Loos J, Wesselink W. Data dependent thin plate energy and its use in interactive surface modeling, Computer graphics forum 15, p. 175–186. ISSN 1067-7055; 1996.
Witkin A, Heckbert P. Using particles to sample and control implicit surfaces. Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques, ACM Press; 1994, p. 269–277.
Pighin F, Hecker J, Lischinskiy D, Szeliskiz R, Salesin DH. Synthesizing realistic facial expressions from photographs, SIGGRAPH ‘98 proceedings of the 25th annual conference on computer graphics and interactive techniques, ACM Press; 1998, p. 75–84.
Honda K, Masuda H. Constrained Laplacian mesh deformation with visual saliency analysis. The Institute of Image Information and Television Engineer (in Japanese).
Kähler K, Haber J, Yamauchi H, Seidel H, Shop H. Generating animated head models with anatomical structure, ACM SIGGRAPH symposium on computer animation; 2002, p. 55–64.
Essa IA. Coding. Analysis, interpretation, and recognition of facial expressions, pattern analysis and machine intelligence. 1997;19(7):757–63.
Guenter B, Grimm C, Wood D, Malvar H, Pighin F. Making faces. Proceedings of the 25th annual conference on computer graphics; 1998, p. 55–66.
Lee W, Kalra P, Thalmann NM. Model based face reconstruction for animation. Proceedings of the multimedia modeling (MMM’97), Singapore; 1997.
Lee W, Thalmann NM. Fast head modeling for animation. J Image Vision Comput. 2000; 18(4), 355–364 (Elsevier).
Bickel B, Botsch M, Angst R, Matusik W, Otaduy M, et al. Multi-scale capture of facial geometry and motion. ACM transactions on graphics (TOG), vol. 26, no. 3; 2007.
Bickel B, Lang M, Botsch M, Otaduy MA, Gross M. Pose-space animation and transfer of facial details. ACM, NY, USA: ACM SIGGRAPH/Eurographics symposium on computer animation; 2008. p. 57–66.
Weise T, Li H, Gool LV, Pauly M. Face/off: live facial puppetry. Proceedings of the eighth ACM SIGGRAPH/Eurographics symposium on computer animation 2009; 2009.
Müller M, Heidelberger B, Teschner M, Gross M. Meshless deformations based on shape matching. Proceedings of ACM SIGGRAPH 2005, vol. 24, no. 3; 2005, p. 471–478.
Ilic S, Fua P. Using Dirichlet free form deformation to fit deformable models to noisy 3-D data. Proceedings of the European conference computer vision; 2002, p. 704–717.
Hoppe H, Derose T, Duchamp T, Mcdonald J, Stuetzle W. Surface reconstruction from unorganized points. Comput Graph. 1992;26:71–8.
Paul B, JainRamesh C. Invariant surface characteristics for 3D object recognition in range images. Comput Vision, Graph Image Process. 1986;33(1):33–80.
Besl P, McKay N. A method for registration of 3-D shapes. IEEE Trans Pattern Anal Mach Intell. 1992;14(2):239–56.
Eggert D, Lorusso A, Fisher R. Estimating 3-D rigid body transformations: a comparison of four major algorithms. Int J Mach Vision Appl. 1997;9:272–90.
Rusinkiewicz S, Levoy M. Efficient variants of the ICP algorithm. Proceedings of the international conference on 3D digital imaging and modeling (3DIM); 2001.
Tevs A, Bokeloh M, Wand M, Schilling A, Seidel HP. Isometric registration of ambiguous and partial data. Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR ’09); 2009.
Sussmuth J, Winter m, Greiner G. Reconstructing animated meshes from time-varying point clouds, Computer graphics forum (Proceedings of SGP 2008), vol. 27, no. 5; 2008, p. 1469–1476.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xue, M., Tokai, S., Hase, H. (2018). Point Clouds Based 3D Facial Expression Generation. In: Tan, J., Gao, F., Xiang, C. (eds) Advances in Mechanical Design. ICMD 2017. Mechanisms and Machine Science, vol 55. Springer, Singapore. https://doi.org/10.1007/978-981-10-6553-8_32
Download citation
DOI: https://doi.org/10.1007/978-981-10-6553-8_32
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6552-1
Online ISBN: 978-981-10-6553-8
eBook Packages: EngineeringEngineering (R0)