Blendshape Facial Animation
Blendshapes are a standard approach for making expressive facial animations in the digital production industry. The blendshape model is represented as a linear weighted sum of the target faces, which exemplify user-defined facial expressions or approximate facial muscle actions. Blendshapes are therefore quite popular because of their simplicity, expressiveness, and interpretability. For example, unlike generic mesh editing tools, blendshapes approximate a space of valid facial expressions.
This article provides the basic concepts and technical development of the blendshape model. First, we briefly describe a general face rig framework and thereafter introduce the concept of blendshapes as an established face rigging approach. Next, we illustrate how to use this model in animation practice, while clarifying the mathematical framework for blendshapes. We also demonstrate a few technical applications developed in the blendshape framework.
KeywordsComputer facial animation Face rig Blendshapes Retarget Deformer Facial motion capture Performance capture
I would like to thank J. P. Lewis for mentoring me over the years in the field of computer facial animation research and practice. Many thanks go to Ayumi Kimura for her fruitful discussions and warm encouragements in preparing and writing this article. I also thank Gengdai Liu and Hideki Todo for their helpful comments and creation of the images in Figs. 1, 2, and 3.
- Bhat K, Goldenthal R, Ye Y, Mallet R, Koperwas M (2013) High fidelity facial animation capture and retargeting with contours. In: Proceedings of the 12th ACM SIG-GRAPH/Eurographics Symposium on Computer Animation, 7–14Google Scholar
- Botsch M, Sumner R, Pauly M, Gross M (2006) Deformation transfer for detail-preserving surface editing. In: Proceedings of Vision, Modeling, and Visualization (VMV), 357–364Google Scholar
- Cantwell B, Warner P, Koperwas M, Bhat K (2016) ILM facial performance capture, In ACM SIGGRAPH2016 Talks, 26:1–26:2Google Scholar
- Ekman P, Friesen W (1978) Facial action coding system: manual. Consulting Psychologists Press, Palo AltoGoogle Scholar
- Fxguide web page (2014) https://www.fxguide.com/featured/voodoo-magic/
- 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), 3:1–3:17Google Scholar
- Lewis JP, Mo Z, Neumann U (2004) Ripple-free local bases by design. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP), 684–688Google Scholar
- Lewis JP, Anjyo K, Rhee T, Zhang M, Poghin F, Deng Z (2014) Practice and theory of blend-shape facial models. Eurographics 2014 (State of the Art Reports), 199–218Google Scholar
- Li H, Weise T, Pauly M (2010) Example-based facial rigging. ACM Trans Graph 29(3), 32:1–32:6Google Scholar
- Mixamo web page (2013) https://www.mixamo.com/faceplus
- Neumann T, Varanasi K, Wenger S, Wacker M, Magnor M, Theobalt C (2013) Sparse localized deformation components. ACM Trans Graph 32(6), 179:1–179:10Google Scholar
- Noh J, Neumann U (2001) Expression Cloning. In: SIGGRAPH2001, Computer Graphics Proceedings, ACM Press/ACM SIGGRAPH, 277–288Google Scholar
- Raitt B (2004) The making of Gollum. Presentation at U. Southern California Institute for Creative Technologies’s Frontiers of Facial Animation Workshop, August 2004Google Scholar
- Saito J (2013) Smooth contact-aware facial blendshape transfer. In: Proceedings of Digital Production Symposium 2013 (DigiPro2013), ACM. 7–12Google Scholar
- Seo J, Irving J, Lewis JP, Noh J (2011) Compression and direct manipulation of complex blendshape models. ACM Trans Graph 30(6), 164:1–164:10Google Scholar
- Seol Y, Lewis JP, Seo J, Choi B, Anjyo K, Noh J (2012) Spacetime expression cloning for blendshapes. ACM Trans Graph 31(2), 14:1–14:12Google Scholar
- Tickoo S (2009) Autodesk maya 2010: a comprehensive guide. CADCIM Technologies, ScherervilleGoogle Scholar