arXiv subjects

Hsiao-yu Chen

Publications and source records attributed to Hsiao-yu Chen.

12 recordsLinked to original sources

arXiv2026

PhySkin: Physics-based Bone-driven Neural Garment Simulation

Recent advances in digital avatar technology have enabled the generation of compelling virtual characters, but deploying these avatars on compute-constrained devices poses significant challenges for achieving realistic garment deformations. While physics-based simulations yield accurate results, they are computationally prohibitive for real-time applications. Conversely, linear blend skinning offers efficiency but fails to capture the complex dynamics of loose-fitting garments, resulting in unrealistic motion and visual artifacts. Neural methods have shown promise, yet they struggle to animate loose clothing plausibly under strict performance constraints. In this work, we present a novel approach for fast and physically plausible garment draping tailored for resource-constrained environments. Our method leverages a reduced-space quasi-static neural simulation, mapping the garment's full degrees of freedom to a set of bone handles that drive deformation. A neural deformation model is trained in a fully self-supervised manner, eliminating the need for costly simulation data. At runtime, a lightweight neural network modulates the handle deformations based on body shape and pose, enabling realistic garment behavior that respects physical properties such as gravity, fabric stretching, bending, and collision avoidance. Experimental results demonstrate that our method achieves physically plausible garment drapes while generalizing across diverse poses and body shapes, supporting zero-shot evaluation and mesh topology independence. Our method's runtime significantly outperforms past works, as it runs in microseconds per frame using single-threaded CPU inference, offering a practical solution for real-time avatar animation on low-compute devices.

cs.GR↗

arXiv2026

SkinCells: Sparse Skinning using Voronoi Cells

For decades, real-time skinning has been the cornerstone of character animation in visual effects and games. Despite its importance, the creation of animatable digital assets remains a labor-intensive manual process. Existing automated tools frequently struggle with intricate geometries, often necessitating significant manual refinement to reach production standards. We present a robust, fully automated method for generating high-quality skinning weights from a standard mesh and skeleton in a canonical A- or T-pose. Unlike traditional approaches, our framework offers direct sparsity controls to limit bone influences per vertex -- a critical requirement for maintaining performance in large-scale mobile environments. Furthermore, we address the challenge of Level-of-Detail (LoD) management by optimizing weights within a continuous spatial volume rather than on discrete vertices. This allows a single optimization pass to be applied seamlessly across multiple asset resolutions and variations. Central to our approach is a novel parameterized family of functions, we call SkinCells. We demonstrate that our method consistently produces stable, high-quality results even in complex scenarios where standard biharmonic weight computations fail.

cs.GR↗

arXiv2025

Self-supervised Learning of Latent Space Dynamics

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.

cs.GR↗

arXiv2025

Neuralocks: Real-Time Dynamic Neural Hair Simulation

Real-time hair simulation is a vital component in creating believable virtual avatars, as it provides a sense of immersion and authenticity. The dynamic behavior of hair, such as bouncing or swaying in response to character movements like jumping or walking, plays a significant role in enhancing the overall realism and engagement of virtual experiences. Current methods for simulating hair have been constrained by two primary approaches: highly optimized physics-based systems and neural methods. However, state-of-the-art neural techniques have been limited to quasi-static solutions, failing to capture the dynamic behavior of hair. This paper introduces a novel neural method that breaks through these limitations, achieving efficient and stable dynamic hair simulation while outperforming existing approaches. We propose a fully self-supervised method which can be trained without any manual intervention or artist generated training data allowing the method to be integrated with hair reconstruction methods to enable automatic end-to-end methods for avatar reconstruction. Our approach harnesses the power of compact, memory-efficient neural networks to simulate hair at the strand level, allowing for the simulation of diverse hairstyles without excessive computational resources or memory requirements. We validate the effectiveness of our method through a variety of hairstyle examples, showcasing its potential for real-world applications.

cs.GR↗

arXiv2025

Quaffure: Real-Time Quasi-Static Neural Hair Simulation

Realistic hair motion is crucial for high-quality avatars, but it is often limited by the computational resources available for real-time applications. To address this challenge, we propose a novel neural approach to predict physically plausible hair deformations that generalizes to various body poses, shapes, and hairstyles. Our model is trained using a self-supervised loss, eliminating the need for expensive data generation and storage. We demonstrate our method's effectiveness through numerous results across a wide range of pose and shape variations, showcasing its robust generalization capabilities and temporally smooth results. Our approach is highly suitable for real-time applications with an inference time of only a few milliseconds on consumer hardware and its ability to scale to predicting the drape of 1000 grooms in 0.3 seconds. Please see our project page here following https://tuurstuyck.github.io/quaffure/quaffure.html

cs.CV↗

arXiv2025

PGC: Physics-Based Gaussian Cloth from a Single Pose

We introduce a novel approach to reconstruct simulation-ready garments with intricate appearance. Despite recent advancements, existing methods often struggle to balance the need for accurate garment reconstruction with the ability to generalize to new poses and body shapes or require large amounts of data to achieve this. In contrast, our method only requires a multi-view capture of a single static frame. We represent garments as hybrid mesh-embedded 3D Gaussian splats, where the Gaussians capture near-field shading and high-frequency details, while the mesh encodes far-field albedo and optimized reflectance parameters. We achieve novel pose generalization by exploiting the mesh from our hybrid approach, enabling physics-based simulation and surface rendering techniques, while also capturing fine details with Gaussians that accurately reconstruct garment details. Our optimized garments can be used for simulating garments on novel poses, and garment relighting. Project page: https://phys-gaussian-cloth.github.io .

cs.GR↗

arXiv2024

Dress Anyone : Automatic Physically-Based Garment Pattern Refitting

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, enabling 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.

cs.GR↗

arXiv2024

DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation

The realism of digital avatars is crucial in enabling telepresence applications with self-expression and customization. While physical simulations can produce realistic motions for clothed humans, they require high-quality garment assets with associated physical parameters for cloth simulations. However, manually creating these assets and calibrating their parameters is labor-intensive and requires specialized expertise. Current methods focus on reconstructing geometry, but don't generate complete assets for physics-based applications. To address this gap, we propose \papername,~a novel approach that performs body and garment co-optimization using differentiable simulation. By integrating physical simulation into the optimization loop and accounting for the complex nonlinear behavior of cloth and its intricate interaction with the body, our framework recovers body and garment geometry and extracts important material parameters in a physically plausible way. Our experiments demonstrate that our approach generates realistic clothing and body shape suitable for downstream applications. We provide additional insights and results on our webpage: https://people.csail.mit.edu/liyifei/publication/diffavatar/

cs.CV↗

arXiv2024

Estimating Cloth Elasticity Parameters From Homogenized Yarn-Level Models

Virtual garment simulation has become increasingly important with applications in garment design and virtual try-on. However, reproducing garments faithfully remains a cumbersome process. We propose an end-to-end method for estimating parameters of shell material models corresponding to real fabrics with minimal priors. Our method determines yarn model properties from information directly obtained from real fabrics, unlike methods that require expensive specialized capture systems. We use an extended homogenization method to match yarn-level and shell-level hyperelastic energies with respect to a range of surface deformations represented by the first and second fundamental forms, including bending along the diagonal to warp and weft directions. We optimize the parameters of a shell deformation model involving uncoupled bending and membrane energies. This allows the simulated model to exhibit nonlinearity and anisotropy seen in real cloth. Finally, we validate our results with quantitative and visual comparisons against real world fabrics through stretch tests and drape experiments. Our homogenized shell models not only capture the characteristics of underlying yarn patterns, but also exhibit distinct behaviors for different yarn materials.

cs.GR↗

arXiv2023

DiffXPBD : Differentiable Position-Based Simulation of Compliant Constraint Dynamics

We present DiffXPBD, a novel and efficient analytical formulation for the differentiable position-based simulation of compliant constrained dynamics (XPBD). Our proposed method allows computation of gradients of numerous parameters with respect to a goal function simultaneously leveraging a performant simulation model. The method is efficient, thus enabling differentiable simulations of high resolution geometries and degrees of freedom (DoFs). Collisions are naturally included in the framework. Our differentiable model allows a user to easily add additional optimization variables. Every control variable gradient requires the computation of only a few partial derivatives which can be computed using automatic differentiation code. We demonstrate the efficacy of the method with examples such as elastic material parameter estimation, initial value optimization, optimizing for underlying body shape and pose by only observing the clothing, and optimizing a time-varying external force sequence to match sparse keyframe shapes at specific times. Our approach demonstrates excellent efficiency and we demonstrate this on high resolution meshes with optimizations involving over 26 million degrees of freedom. Making an existing solver differentiable requires only a few modifications and the model is compatible with both modern CPU and GPU multi-core hardware.

cs.GR↗

arXiv2022

Virtual Elastic Objects

We present Virtual Elastic Objects (VEOs): virtual objects that not only look like their real-world counterparts but also behave like them, even when subject to novel interactions. Achieving this presents multiple challenges: not only do objects have to be captured including the physical forces acting on them, then faithfully reconstructed and rendered, but also plausible material parameters found and simulated. To create VEOs, we built a multi-view capture system that captures objects under the influence of a compressed air stream. Building on recent advances in model-free, dynamic Neural Radiance Fields, we reconstruct the objects and corresponding deformation fields. We propose to use a differentiable, particle-based simulator to use these deformation fields to find representative material parameters, which enable us to run new simulations. To render simulated objects, we devise a method for integrating the simulation results with Neural Radiance Fields. The resulting method is applicable to a wide range of scenarios: it can handle objects composed of inhomogeneous material, with very different shapes, and it can simulate interactions with other virtual objects. We present our results using a newly collected dataset of 12 objects under a variety of force fields, which will be shared with the community.

cs.CV↗

arXiv2019

Locking-free Simulation of Isometric Thin Plates

To efficiently simulate very thin, inextensible materials like cloth or paper, it is tempting to replace force-based thin-plate dynamics with hard isometry constraints. Unfortunately, naive formulations of the constraints induce membrane locking---artificial stiffening of bending modes due to the inability of discrete kinematics to reproduce exact isometries. We propose a simple set of meshless isometry constraints, based on moving-least-squares averaging of the strain tensor, which do not lock, and which can be easily incorporated into standard constrained Lagrangian dynamics integration.

cs.GR↗