# High-Quality Face Capture Using Anatomical Muscles

arXiv: https://arxiv.org/abs/1812.02836 · HTML: https://mlsanity.com/paper/1812.02836/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2018.

## Built on by (most cited first, 8 of 8)

- [I M Avatar: Implicit Morphable Head Avatars from Videos](https://mlsanity.com/paper/2112.07471/) (2021)
- [Learning a Generalized Physical Face Model From Data](https://mlsanity.com/paper/2402.19477/) (2024)
- [Implicit Neural Representation for Physics-driven Actuated Soft Bodies](https://mlsanity.com/paper/2401.14861/) (2024)
- [Leveraging Deepfakes to Close the Domain Gap between Real and Synthetic Images in Facial Capture Pipelines](https://mlsanity.com/paper/2204.10746/) (2022)
- [An Implicit Physical Face Model Driven by Expression and Style](https://mlsanity.com/paper/2401.15414/) (2024)
- [RendNet: Unified 2D/3D Recognizer With Latent Space Rendering](https://mlsanity.com/paper/2206.10066/) (2022)
- [Near-realtime Facial Animation by Deep 3D Simulation Super-Resolution](https://mlsanity.com/paper/2305.03216/) (2023)
- [Improving Facial Rig Semantics for Tracking and Retargeting](https://mlsanity.com/paper/2508.08429/) (2025)

## Abstract (arXiv)

Muscle-based systems have the potential to provide both anatomical accuracy and semantic interpretability as compared to blendshape models; however, a lack of expressivity and differentiability has limited their impact. Thus, we propose modifying a recently developed rather expressive muscle-based system in order to make it fully-differentiable; in fact, our proposed modifications allow this physically robust and anatomically accurate muscle model to conveniently be driven by an underlying blendshape basis. Our formulation is intuitive, natural, as well as monolithically and fully coupled such that one can differentiate the model from end to end, which makes it viable for both optimization and learning-based approaches for a variety of applications. We illustrate this with a number of examples including both shape matching of three-dimensional geometry as as well as the automatic determination of a three-dimensional facial pose from a single two-dimensional RGB image without using markers or depth information.