Ladislav Kavan

Ladislav Kavan

Auto-generated profile, based on publicly available information

Ladislav Kavan

Meta Reality Labs

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 November 2024 in ACM Transactions on Graphics
Verified
Journal Article
Open access
PHPhilipp Herholz
Philipp Herholz
TSTuur Stuyck
Tuur Stuyck
LKLadislav Kavan
Ladislav Kavan
Optimized parallel implementations on GPU or CPU have dramatically enhanced the fidelity, resolution and accuracy of physical simulations and mesh-based algorithms. However, attaining optimal performance requires expert knowledge and might demand complex code and memory layout optimizations. This adds to the fact that physical simulation algorithms require the implementation of derivatives, which can be a tedious and error-prone process. In recent years, researchers and practitioners have investigated the concept of designing systems that allow for a more expressive definition of mesh-based simulation code. These systems leverage domain-specific languages (DSL), automatic differentiation or symbolic computing to enhance readability of implementations without compromising performance. We follow this line of work and propose a symbolic code generation approach tailored to mesh-based computations on parallel devices. Our system extends related work by incorporating collision handling and a data access synchronization approach, enabling rapid sparse matrix assembly.

8 August 2025 in Proceedings of the ACM on Computer Graphics and Interactive Techniques
Verified
Journal Article
Open access
HCHsiao-Yu Chen
Hsiao-Yu Chen
ELEgor Larionov
Egor Larionov
LKLadislav Kavan
Ladislav Kavan
GLGene Lin
Gene Lin
DRDoug Roble
Doug Roble
TSTuur Stuyck
Tuur Stuyck
Well-fitted clothing is essential for both real and virtual garments to enable self-expression and accurate representation for a large variety of body types. Common practice in the industry is to provide a pre-made selection of distinct garment sizes such as small, medium and large. While these may cater to certain groups of individuals that fall within this distribution, they often exclude large sections of the population. In contrast, individually tailored clothing offers a solution to obtain custom-fit garments that are tailored to each individual. However, manual tailoring is time-consuming and requires specialized knowledge, prohibiting the approach from being applied to produce fitted clothing at scale. To address this challenge, we propose a novel method leveraging differentiable simulation for refitting and draping 3D garments and their corresponding 2D pattern panels onto a new body shape. This enables a workflow where garments only need to be designed once, in a single size, and they can be automatically refitted to support numerous body size and shape variations. Our method enables downstream applications, where our optimized 3D drape can be directly ingested into game engines or other applications. Our 2D sewing patterns allow for accurate physics-based simulations and enables manufacturing clothing for the real world.

8 August 2025 in Proceedings of the ACM on Computer Graphics and Interactive Techniques
Verified
Journal Article
Open access
YLYue Li
Yue Li
GLGene Wei-Chin Lin
Gene Wei-Chin Lin
ELEgor Larionov
Egor Larionov
ABAljaz Bozic
Aljaz Bozic
DRDoug Roble
Doug Roble
HCHsiao-Yu Chen
Hsiao-Yu Chen
Modeling the dynamic behavior of deformable objects is crucial for creating realistic digital worlds. While conventional simulations produce high-quality motions, their computational costs are often prohibitive. Subspace simulation techniques address this challenge by restricting deformations to a lower-dimensional space, improving performance while maintaining visually compelling results. However, even subspace methods struggle to meet the stringent performance demands of portable devices such as virtual reality headsets and mobile platforms. To overcome this limitation, we introduce a novel subspace simulation framework powered by a neural latent-space integrator. Our approach leverages self-supervised learning to enhance inference stability and generalization. By operating entirely within latent space, our method eliminates the need for full-space computations, resulting in a highly efficient method well-suited for deployment on portable devices. We demonstrate the effectiveness of our approach on challenging examples involving rods, shells, and solids, showcasing its versatility and potential for widespread adoption.

13 July 2024
Verified
Conference Paper
Open access
LKLadislav Kavan
Ladislav Kavan
JDJohn Doublestein
John Doublestein
MPMartin Prazak
Martin Prazak
MCMatthew Cioffi
Matthew Cioffi
DRDoug Roble
Doug Roble
We present a new method to bake classical facial animation blendshapes into a fast linear blend skinning representation. Previous work explored skinning decomposition methods that approximate general animated meshes using a dense set of bone transformations; these optimizers typically alternate between optimizing for the bone transformations and the skinning weights. We depart from this alternating scheme and propose a new approach based on proximal algorithms, which effectively means adding a projection step to the popular Adam optimizer. This approach is very flexible and allows us to quickly experiment with various additional constraints and/or loss functions. Specifically, we depart from the classical skinning paradigms and restrict the transformation coefficients to contain only about 90% non-zeros, while achieving similar accuracy and visual quality as the state-of-the-art. The sparse storage enables our method to deliver significant savings in terms of both memory and run-time speed. We include a compact implementation of our new skinning decomposition method in PyTorch, which is easy to experiment with and modify to related problems.

8 August 2025 in Proceedings of the ACM on Computer Graphics and Interactive Techniques
Verified
Journal Article
Open access
JFJosé Antonio Fernández-Fernández
José Antonio Fernández-Fernández
RGRyan Goldade
Ryan Goldade
LKLadislav Kavan
Ladislav Kavan
JBJan Bender
Jan Bender
PHPhilipp Herholz
Philipp Herholz
Demand for high-quality virtual 3D characters continues to grow in both entertainment and communication, and with it, the desire for interactive avatars. This presents unique challenges for high-fidelity interactive solutions that must be quick to set up, efficient to run in real-time on consumer hardware, and work well, not only on human characters, but also on fantastical and heavily stylized ones. We present Interactive Facial Animation (IFA), a novel approach to augment facial animation rigs with shell simulation and contact without requiring anatomical priors or artist intervention. Our method uses an efficient shell model that tracks the output of a face rig in real-time and incorporates realistic contact. By designing our shell model to be differentiable, we can use inverse simulation to reconstruct realistic non-uniform stiffness that captures both stiff (ears, nose) and soft (cheeks, lips) areas, based on the rig’s deformation space. The reconstruction process imposes hard limits on acceptable errors, which ensures that IFA preserves the resolution and expressiveness of the source material, a common shortcoming in many face simulation pipelines. With performance in mind, we demonstrate IFA using a variant of the Fast Mass-Springs method. However, the presented concept can be realized with any differentiable physics solver that provides reliable convergence. We showcase our method in four different character rigs, achieving simulation update runtimes between 0.39 and 1.27 milliseconds (787-2564 FPS) on a single CPU thread. Unlike existing methods that require lengthy preparation times, our pipeline can be ready to use within minutes, also on the CPU.