Huamin Wang

Huamin Wang

Chief Scientist

Style3D Research

Bio

Huamin Wang is the chief scientist at Style3D and he leads Style3D’s global research team. His research interests revolve around physics-based simulation and modeling, with a specific focus on high-performance and high-fidelity simulation of digital human by GPU and generative AI.

Before joining Style3D, he was a tenured associate professor in the CSE department at the Ohio State University (2011 – 2021), and a postdoctoral researcher at UC Berkeley (2009 – 2011). He has served on the technical committees of numerous conferences and chaired the papers programs of CASA 2017 and SCA 2023. He is an associate editor of IEEE TVCG and the Visual Computer.

Interests
  • Physics-Based Simulation
  • Physics-Based Modeling
  • Generative AI
  • Numerical Analysis
  • Nonlinear Optimization
Education

  • PhD in Computer Science, 2009

    Georgia Institute of Technology

  • MS in Computer Science, 2004

    Stanford University

  • BSc in Computer Science, 2002

    Zhejiang University

Recent Publications

Quickly discover relevant content by filtering publications.
GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details
Boqian Li, Xuan Li, Ying Jiang, Tianyi Xie, Feng Gao, Huamin Wang, Yin Yang, Chenfanfu Jiang
March, 2025 International Conference on 3D Vision (3DV)
We propose GarmentDreamer, a novel method that leverages 3D Gaussian Splatting (GS) as guidance to generate wearable, simulation-ready 3D garment meshes from text prompts.
Cite Code Page
GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details
FashionR2R: Texture-Preserving Rendered-to-Real Image Translation with Diffusion Models
Rui Hu, Qian He, Jiedong Zhuang, Huang Chen, Huafeng Liu, Huamin Wang
December, 2024 Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems (NeurIPS)
We introduce a novel diffusion-based framework that effectively translates rendered images into realistic counterparts, ensuring the preservation of texture details.
PDF Cite Page
FashionR2R: Texture-Preserving Rendered-to-Real Image Translation with Diffusion Models
Efficient GPU Cloth Simulation with Non-Distance Barriers and Subspace Reuse
Lei Lan, Zixuan Lu, Jingyi Long, Chun Yuan, Xuan Li, Xiaowei He, Huamin Wang, Chenfanfu Jiang, Yin Yang
December, 2024 ACM Trans. Graph. (SIGGRAPH Asia)
This paper pushes the performance of cloth simulation, making the simulation interactive even for high-resolution garment models while keeping every triangle untangled.
PDF Cite Video DOI
Efficient GPU Cloth Simulation with Non-Distance Barriers and Subspace Reuse
Volumetric Homogenization for Knitwear Simulation
Chun Yuan, Haoyang Shi, Lei Lan, Yuxing Qiu, Cem Yuksel, Huamin Wang, Chenfanfu Jiang, Kui Wu, Yin Yang
December, 2024 ACM Trans. Graph. (SIGGRAPH Asia)
This paper presents volumetric homogenization, a spatially varying homogenization scheme for knitwear simulation.
PDF Cite Video DOI More Video
Volumetric Homogenization for Knitwear Simulation
Projective Peridynamic Modeling of Hyperelastic Membranes With Contact
Zixuan Lu, Xiaowei He, Yuzhong Guo, Xuehui Liu, Huamin Wang
August, 2024 IEEE Transactions on Visualization and Computer Graphics, 30(8)
In this paper, we propose projective peridynamics that uses a local-global strategy to enable fast and robust simulation of hyperelastic membranes with contact.
PDF Cite Code DOI
Projective Peridynamic Modeling of Hyperelastic Membranes With Contact
A Dynamic Duo of Finite Elements and Material Points
Xuan Li, Minchen Li, Xuchen Han, Huamin Wang, Yin Yang, Chenfanfu Jiang
July, 2024 ACM SIGGRAPH 2024 Conference Papers
We present a novel method to couple Finite Element Methods (FEM), typically employed for modeling flesh, cloth, hair, and rigid bodies, with Material Point Methods (MPM), which are well-suited for simulating Newtonian/non-Newtonian fluid, granular materials, and fracturing materials.
PDF Cite DOI
A Dynamic Duo of Finite Elements and Material Points
Automatic Digital Garment Initialization from Sewing Patterns
Chen Liu, Weiwei Xu, Yin Yang, Huamin Wang
July, 2024 ACM Trans. Graph. (SIGGRAPH)
We develop an innovative hybrid system for fast initialization of garment pieces with minimal user intervention, by harnessing AI classification, heuristics, and numerical optimization.
PDF Cite Dataset Video DOI More Video
Automatic Digital Garment Initialization from Sewing Patterns
High-quality Surface Reconstruction using Gaussian Surfels
Pinxuan Dai, Jiamin Xu, Wenxiang Xie, Xinguo Liu, Huamin Wang, Weiwei Xu
July, 2024 ACM SIGGRAPH 2024 Conference Papers
We propose a point-based representation, Gaussian surfels, to combine the advantages of the flexible optimization procedure in 3D Gaussian points and the surface alignment property of surfels.
PDF Cite Video DOI
High-quality Surface Reconstruction using Gaussian Surfels
Neural-Assisted Homogenization of Yarn-Level Cloth
Xudong Feng, Huamin Wang, Yin Yang, Weiwei Xu
July, 2024 ACM SIGGRAPH 2024 Conference Papers
We propose a neural-assisted homogenized constitutive model for simulating yarn-level cloth. This model is trained using strain energy datasets and is validated through qualitative and quantitative experiments.
PDF Cite Video DOI
Neural-Assisted Homogenization of Yarn-Level Cloth
VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality
Ying Jiang, Chang Yu, Tianyi Xie, Xuan Li, Yutao Feng, Huamin Wang, Minchen Li, Henry Lau, Feng Gao, Yin Yang, Chenfanfu Jiang
July, 2024 ACM SIGGRAPH 2024 Conference Papers
We present a human-centered 3D content interaction system called VR-GS. VR-GS ensures real-time execution with highly realistic dynamic responses.
Cite DOI Page
VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality
See all publications

Popular Topics

3D Printing Chebyshev Semi-Iterative Method Cloth Simulation Collision Detection Collision Handling Computational Modeling Deep Learning Deformable Models Domain Decomposition Finite Element Method GPU Acceleration Hyperelasticity Nonlinear Elasticity Nonlinear Optimization Parallel Computing Physics-Based Simulation Position-Based Dynamics Projective Dynamics Quasistatic Simulation Surface Tension

Contact

  • wanghmin 'at' gmail 'dot' com
  • 99 Shuanglong Street, Hangzhou, Zhejiang, China 310000
  • Enter Building A of Sanshen International and take an elevator to Floor 3