Raqamli Transformatsiya va Sun’iy Intellekt
A REVIEW OF FACIAL RIGGING TECHNIQUES IN 3D CHARACTER ANIMATION: FROM MUSCLE MODELS TO NEURAL APPROACHES
1 Tashkent University of Information Technologies
Zenodo DOI: 10.5281/zenodo.20152031
Keywords
Abstract
Three-dimensional facial rigging is a core process in character animation for film, gaming, and virtual reality. This paper presents a systematic review of facial rigging techniques developed from the 1970s to the present. Beginning with early physically based muscle models and linear blendshape parameterizations, the review traces the progression through Facial Action Coding System (FACS)-based approaches, example-based rigging, and data-driven machine learning methods including inverse rig mappings and neural network architectures. Key contributions from SIGGRAPH, IEEE, and ACM publications are synthesized and classified according to their methodological basis: geometric, muscle-based, blendshape, motion capture, and neural. The strengths and limitations of each category are identified. Findings indicate that while neural approaches increasingly dominate recent literature, blendshape-based methods remain dominant in production pipelines due to their artist-friendliness and real-time performance. The paper concludes with an analysis of open challenges including automated rig transfer, real-time neural inference, and cross-platform compatibility.
References
- [17] Wen, L., Zhou, J., Huang, W., & Chen, F. (2022). A survey of facial capture for VR. IEEE Access, 10, 6042–6052. https://doi.org/10.1109/ACCESS.2021.3138200
- [10] Osipa, J. (2010). Stop staring: Facial modeling and animation done right (3rd ed.). Wiley.
- [11] Parke, F. I. (1972). Computer generated animation of faces. ACM Annual Conference, 1, 451–457.
- [3] Baran, I., & Popović, J. (2007). Automatic rigging and animation of 3D characters. ACM Transactions on Graphics, 26(3), 72. https://doi.org/10.1145/1276377.1276467
- [6] Holden, D., Saito, J., & Komura, T. (2015). Learning an inverse rig mapping for character animation. ACM SCA, 165–173. https://doi.org/10.1145/2786784.2786797
- [5] Ekman, P., & Friesen, W. V. (1978). Facial action coding system. Consulting Psychologists Press.
- [13] Sayed, M., Bhatti, Z., & Ismaili, I. A. (2019). Facial animation using covariance matrix and Mahalanobis distance. iCoMET 2019. https://doi.org/10.1109/ICOMET.2019.8673493
- [16] Waters, K. (1987). A muscle model for animating 3D facial expressions. ACM SIGGRAPH CG, 21(4), 17–24. https://doi.org/10.1145/37402.37405
- [2] Bergeron, P., & Lachapelle, P. (1985). Controlling facial expressions and body movements. SIGGRAPH '85 Tutorial Notes.
- [4] Deng, Y., Zhang, Y., Geng, C., Wu, S., & Wu, J. (2025). Anymate: A dataset and baselines for learning 3D object rigging. SIGGRAPH '25. https://doi.org/10.1145/3721238.3730743
- [8] Nendya, M. B., Herumurti, D., & Yuniarti, A. (2014). Facial rigging for 3D character. IC3INA, 111–115. https://doi.org/10.1109/IC3INA.2014.7042605
- [15] Tewari, A., et al. (2020). StyleRig: Rigging StyleGAN for 3D control over portrait images. CVPR 2020, 6141–6150.
- [12] Razzaq, A., Wu, Z., Zhou, M., & Ali, S. (2014). Automatic generation of skeleton animation from 3D mesh. CW 2014, 131–135. https://doi.org/10.1109/CW.2014.26
- [14] Terzopoulos, D., & Waters, K. (1990). Physically-based facial modelling, analysis, and animation. J. Vis. Comp. Anim., 1(2), 73–80.
- [1] Alexander, O., Rogers, M., Lambeth, W., Chiang, M., & Debevec, P. (2009). The digital Emily project: Photoreal facial modeling and animation. SIGGRAPH '09 Courses.
- [9] Orvalho, V., Bastos, P., Parke, F., Oliveira, B., & Alvarez, X. (2012). A facial rigging survey. Eurographics 2012 STAR, 183–204.
- [7] Li, H., Weise, T., & Pauly, M. (2010). Example-based facial rigging. ACM TOG, 29(4), 1–6. https://doi.org/10.1145/1778765.1778769