Dr. Hyewon Seo – CNRS-University of Strasbourg, France
Bio: Hyewon Seo is a permanently posted CNRS (French National Scientific Research Center) Research director affiliated at the Université de Strasbourg. She holds BSc and MSc degrees in Computer Science from KAIST. After completing her PhD at MIRALab, she worked as an assistant professor at the Chungnam National University, before she moved to France. Her research interest centers primarily around 3D/4D shape analysis and modeling, with focus on human data. So far, she has authored about 70 published articles in international journals and conferences, 4 book chapters, and 3 patents. She has served several editorial boards for international journals, among them is The Visual Computer journal where she have been an associate editor-in-chief (2016-2020). She also participated in the organization of several international conferences including Eurographics 2014 (local organization member), Computer Graphics International 2015 (conference co-chair), Symposium on Solid and Physical Modeling 2020 (conference co-chair), and Shape Modeling International 2021 (local chair). During 2012-2016, she worked for the national committee of CNRS as an elected member. Since 2021, she is the co-head of a new research team Machine Learning, Modeling & Simulation (MLMS) at the University of Strasbourg.
THE PRESENTATION
Title: Inverse Garment and Pattern Modeling with a Differentiable Simulator
Abstract: The capability to generate simulation-ready garment models from 3D shapes of clothed humans will significantly enhance the interpretability of captured geometry of real garments, as well as their faithful reproduction in the virtual world. This will have notable impact on fields like shape capture in social VR, and virtual try-on in the fashion industry. To align with the garment modeling process standardized by the fashion industry as well as cloth simulation softwares, it is required to recover 2D patterns. This involves an inverse garment design problem, which is the focus of our work here: Starting with an arbitrary target garment geometry, our system estimates an animatable garment model by automatically adjusting its corresponding 2D template pattern, along with the material parameters of the physics-based simulation (PBS). Built upon a differentiable cloth simulator, the optimization process is directed towards minimizing the deviation of the simulated garment shape from the target geometry. Moreover, our produced patterns meet manufacturing requirements such as left-to-right-symmetry, making them suited for reverse garment fabrication.