Barbara Solenthaler
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Barbara Solenthaler has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Markus Gross
ETH Zurich, Zurich, Switzerland
4 shared publications - Bernhard Thomaszewski
ETH Zurich, Zurich, Switzerland
3 shared publications - Daniel Peter
ETH Zürich, Zurich, Switzerland and Align Technology, Zurich, Switzerland
3 shared publications - Davide Corigliano
ETH Zurich, Zurich, Switzerland
3 shared publications - Lingchen Yang
ETH Zurich, Switzerland
3 shared publications - Derek Bradley
DisneyResearch|Studios Switzerland
2 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Neural Face Manifolds: A Learned Space for Simulation-Ready Anatomical Face Models
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessNeural Face Manifolds: A Learned Space for Simulation-Ready Anatomical Face Models
- Open Access
- 24 August 2026
- Published by Wiley in Computer Graphics Forum
LORAMI: Low‐Rank Adaptation for Multi‐Identity Physics‐Based Face Rigs
Physics‐based simulation can augment facial rigs with high‐quality deformations, but at steep computational costs. While neural surrogates can substantially reduce computation time, existing methods do not generalize across identity variations and instead require expensive per‐case retraining. In this work, we present LORAMI—a method for learning physics‐based face rigs over a continuous space of identities using low‐rank adaptation. LORAMI addresses the challenge of identity variation through a novel architecture that combines a shared neural surrogate with low‐rank weight adaptations. Instead of training a dense model across identity space, we modulate a shared base network using low‐rank factors. These factors are scaled by diagonal matrices predicted from identity parameters. This design enables efficient modeling of identity‐dependent variations while preserving the generic deformation behavior of the underlying physics‐based rig. Our experiments show that LORAMI achieves deformation accuracy on par with single‐identity models and outperforms fully dense identity‐conditioned networks. As a result, our method enables real‐time physics‐based facial animation with continuous identity control.
- 24 August 2026
- Published by Wiley in Computer Graphics Forum
Open AccessLORAMI: Low‐Rank Adaptation for Multi‐Identity Physics‐Based Face Rigs
Physics‐based simulation can augment facial rigs with high‐quality deformations, but at steep computational costs. While neural surrogates can substantially reduce computation time, existing methods do not generalize across identity variations and instead require expensive per‐case retraining. In this work, we present LORAMI—a method for learning physics‐based face rigs over a continuous space of identities using low‐rank adaptation. LORAMI addresses the challenge of identity variation through a novel architecture that combines a shared neural surrogate with low‐rank weight adaptations. Instead of training a dense model across identity space, we modulate a shared base network using low‐rank factors. These factors are scaled by diagonal matrices predicted from identity parameters. This design enables efficient modeling of identity‐dependent variations while preserving the generic deformation behavior of the underlying physics‐based rig. Our experiments show that LORAMI achieves deformation accuracy on par with single‐identity models and outperforms fully dense identity‐conditioned networks. As a result, our method enables real‐time physics‐based facial animation with continuous identity control.
- Open Access
- 2 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
PhonemeNet: A Transformer Pipeline for Text-Driven Facial Animation
- 2 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessPhonemeNet: A Transformer Pipeline for Text-Driven Facial Animation
- Open Access
- 8 August 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 8 (4) , 1-18
NeuRiPhy: Neural Baking of Physics-Based Deformations for Facial Rigs 59
We introduce a self-supervised neural approach for real-time, physically-principled facial rigs that incorporate soft tissue deformations and contact interactions. Traditional artist-crafted blendshapes lack the capacity to produce realistic tissue deformations, while physics-based models, despite their accuracy, are computationally prohibitive for interactive applications. Our method addresses these limitations by learning a neural map from a set of rig controls to corresponding deformations that minimize the mechanical energy of an anatomically-based face model, including soft tissue, skull, and teeth layers. This self-supervised framework eliminates the need for predefined simulation data and supports unsupervised handling of collisions between rigid and soft bodies, streamlining the computational process. We demonstrate that, for the first time, our approach achieves real-time performance of physics-based face rigs with complex non-linear deformations and contact handling.
- 8 August 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 8 (4) , 1-18
Open AccessNeuRiPhy: Neural Baking of Physics-Based Deformations for Facial Rigs 59
We introduce a self-supervised neural approach for real-time, physically-principled facial rigs that incorporate soft tissue deformations and contact interactions. Traditional artist-crafted blendshapes lack the capacity to produce realistic tissue deformations, while physics-based models, despite their accuracy, are computationally prohibitive for interactive applications. Our method addresses these limitations by learning a neural map from a set of rig controls to corresponding deformations that minimize the mechanical energy of an anatomically-based face model, including soft tissue, skull, and teeth layers. This self-supervised framework eliminates the need for predefined simulation data and supports unsupervised handling of collisions between rigid and soft bodies, streamlining the computational process. We demonstrate that, for the first time, our approach achieves real-time performance of physics-based face rigs with complex non-linear deformations and contact handling.
- Open Access
- 21 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
EmoSpaceTime: Decoupling Emotion and Content through Contrastive Learning for Expressive 3D Speech Animation
Equipping stylized conversational characters with facial animations tailored to specific emotions enhances coherence and authenticity. Many data-driven speech animation methods lack dynamic facial expressions since they rely on explicit semantic control signals, leading to static emotional expressions. We present a Transformer-AE for disentangling emotion and content within the facial motion latent space. Our method processes animation control parameters in the frequency domain, enabling a more fine-grained separation of emotion and content based on frequencies. Through contrastive learning, the model is encouraged to learn similar representations for similar emotional states and the same linguistic content. Capturing the full dynamics of an emotional episode spatially and temporally, this approach enables emotion swapping, enhances expressiveness, and gives artists fine control over emotion, e.g., through emotion interpolation. Our analyses show that the Transformer-AE effectively separates emotion from content, enabling more nuanced and realistic facial animation for conversational characters.
- 21 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessEmoSpaceTime: Decoupling Emotion and Content through Contrastive Learning for Expressive 3D Speech Animation
Equipping stylized conversational characters with facial animations tailored to specific emotions enhances coherence and authenticity. Many data-driven speech animation methods lack dynamic facial expressions since they rely on explicit semantic control signals, leading to static emotional expressions. We present a Transformer-AE for disentangling emotion and content within the facial motion latent space. Our method processes animation control parameters in the frequency domain, enabling a more fine-grained separation of emotion and content based on frequencies. Through contrastive learning, the model is encouraged to learn similar representations for similar emotional states and the same linguistic content. Capturing the full dynamics of an emotional episode spatially and temporally, this approach enables emotion swapping, enhances expressiveness, and gives artists fine control over emotion, e.g., through emotion interpolation. Our analyses show that the Transformer-AE effectively separates emotion from content, enabling more nuanced and realistic facial animation for conversational characters.
- Open Access
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-14
Learning a Generalized Physical Face Model From Data
Physically-based simulation is a powerful approach for 3D facial animation as the resulting deformations are governed by physical constraints, allowing to easily resolve self-collisions, respond to external forces and perform realistic anatomy edits. Today's methods are data-driven, where the actuations for finite elements are inferred from captured skin geometry. Unfortunately, these approaches have not been widely adopted due to the complexity of initializing the material space and learning the deformation model for each character separately, which often requires a skilled artist followed by lengthy network training. In this work, we aim to make physics-based facial animation more accessible by proposing a generalized physical face model that we learn from a large 3D face dataset. Once trained, our model can be quickly fit to any unseen identity and produce a ready-to-animate physical face model automatically. Fitting is as easy as providing a single 3D face scan, or even a single face image. After fitting, we offer intuitive animation controls, as well as the ability to retarget animations across characters. All the while, the resulting animations allow for physical effects like collision avoidance, gravity, paralysis, bone reshaping and more.
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-14
Open AccessLearning a Generalized Physical Face Model From Data
Physically-based simulation is a powerful approach for 3D facial animation as the resulting deformations are governed by physical constraints, allowing to easily resolve self-collisions, respond to external forces and perform realistic anatomy edits. Today's methods are data-driven, where the actuations for finite elements are inferred from captured skin geometry. Unfortunately, these approaches have not been widely adopted due to the complexity of initializing the material space and learning the deformation model for each character separately, which often requires a skilled artist followed by lengthy network training. In this work, we aim to make physics-based facial animation more accessible by proposing a generalized physical face model that we learn from a large 3D face dataset. Once trained, our model can be quickly fit to any unseen identity and produce a ready-to-animate physical face model automatically. Fitting is as easy as providing a single 3D face scan, or even a single face image. After fitting, we offer intuitive animation controls, as well as the ability to retarget animations across characters. All the while, the resulting animations allow for physical effects like collision avoidance, gravity, paralysis, bone reshaping and more.
- Open Access
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-12
An Implicit Physical Face Model Driven by Expression and Style
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessAn Implicit Physical Face Model Driven by Expression and Style
- Open Access
- 28 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Efficient Incremental Potential Contact for Actuated Face Simulation
We present a quasi-static finite element simulator for human face animation. We model the face as an actuated soft body, which can be efficiently simulated using Projective Dynamics (PD). We adopt Incremental Potential Contact (IPC) to handle self-intersection. However, directly integrating IPC into the simulation would impede the high efficiency of the PD solver, since the stiffness matrix in the global step is no longer constant and cannot be pre-factorized. We notice that the actual number of vertices affected by the collision is only a small fraction of the whole model, and by utilizing this fact we effectively decrease the scale of the linear system to be solved. With the proposed optimization method for collision, we achieve high visual fidelity at a relatively low performance overhead.
- 28 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessEfficient Incremental Potential Contact for Actuated Face Simulation
We present a quasi-static finite element simulator for human face animation. We model the face as an actuated soft body, which can be efficiently simulated using Projective Dynamics (PD). We adopt Incremental Potential Contact (IPC) to handle self-intersection. However, directly integrating IPC into the simulation would impede the high efficiency of the PD solver, since the stiffness matrix in the global step is no longer constant and cannot be pre-factorized. We notice that the actual number of vertices affected by the collision is only a small fraction of the whole model, and by utilizing this fact we effectively decrease the scale of the linear system to be solved. With the proposed optimization method for collision, we achieve high visual fidelity at a relatively low performance overhead.