# An Implicit Physical Face Model Driven by Expression and Style

arXiv: https://arxiv.org/abs/2401.15414 · HTML: https://mlsanity.com/paper/2401.15414/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 59 references that are in the map.
- First posted on arXiv 27 Jan 2024.

## Builds on (most cited first, 21 of 21)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [MakeItTalk: Speaker-Aware Talking-Head Animation](https://mlsanity.com/paper/2004.12992/) (2020)
- [3D Morphable Face Models -- Past, Present and Future](https://mlsanity.com/paper/1909.01815/) (2019)
- [Capture, Learning, and Synthesis of 3D Speaking Styles](https://mlsanity.com/paper/1905.03079/) (2019)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [RigNeRF: Fully Controllable Neural 3D Portraits](https://mlsanity.com/paper/2206.06481/) (2022)
- [Unpaired Motion Style Transfer from Video to Animation](https://mlsanity.com/paper/2005.05751/) (2020)
- [Learning Smooth Neural Functions via Lipschitz Regularization](https://mlsanity.com/paper/2202.08345/) (2022)
- [Dynamic Instance Normalization for Arbitrary Style Transfer](https://mlsanity.com/paper/1911.06953/) (2019)
- [Imitator: Personalized Speech-driven 3D Facial Animation](https://mlsanity.com/paper/2301.00023/) (2022)
- [LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization](https://mlsanity.com/paper/2106.04185/) (2021)
- [Motion Puzzle: Arbitrary Motion Style Transfer by Body Part](https://mlsanity.com/paper/2202.05274/) (2022)
- [DiffPD: Differentiable Projective Dynamics](https://mlsanity.com/paper/2101.05917/) (2021)
- [Riggable 3D Face Reconstruction via In-Network Optimization](https://mlsanity.com/paper/2104.03493/) (2021)
- [Joint Face Detection and Facial Motion Retargeting for Multiple Faces](https://mlsanity.com/paper/1902.10744/) (2019)
- [Facial Expression Retargeting from Human to Avatar Made Easy](https://mlsanity.com/paper/2008.05110/) (2020)
- [High-Quality Face Capture Using Anatomical Muscles](https://mlsanity.com/paper/1812.02836/) (2018)
- [Implicit Neural Representation for Physics-driven Actuated Soft Bodies](https://mlsanity.com/paper/2401.14861/) (2024)
- [Style Transfer for 2D Talking Head Animation](https://mlsanity.com/paper/2303.09799/) (2023)

## Built on by (most cited first, 3 of 3)

- [BFSM: 3D Bidirectional Face-Skull Morphable Model](https://mlsanity.com/paper/2509.24577/) (2025)
- [GNM Head: A Generative aNthropometric Model of the human head](https://mlsanity.com/paper/2607.23687/) (2026)
- [Improving Facial Rig Semantics for Tracking and Retargeting](https://mlsanity.com/paper/2508.08429/) (2025)

## Abstract (arXiv)

3D facial animation is often produced by manipulating facial deformation models (or rigs), that are traditionally parameterized by expression controls. A key component that is usually overlooked is expression 'style', as in, how a particular expression is performed. Although it is common to define a semantic basis of expressions that characters can perform, most characters perform each expression in their own style. To date, style is usually entangled with the expression, and it is not possible to transfer the style of one character to another when considering facial animation. We present a new face model, based on a data-driven implicit neural physics model, that can be driven by both expression and style separately. At the core, we present a framework for learning implicit physics-based actuations for multiple subjects simultaneously, trained on a few arbitrary performance capture sequences from a small set of identities. Once trained, our method allows generalized physics-based facial animation for any of the trained identities, extending to unseen performances. Furthermore, it grants control over the animation style, enabling style transfer from one character to another or blending styles of different characters. Lastly, as a physics-based model, it is capable of synthesizing physical effects, such as collision handling, setting our method apart from conventional approaches.