In the past few years, significant progress has been made on shape modeling of human body, face, and hands. Yet clothing shape is currently not well presented. Modeling clothing using physics-based simulation can sometimes involve tedious manual work and heavy computation. Therefore, a data-driven learning approach has emerged in the community.
In this talk, I will present a stream of work that targeted to learn the shape of clothed human from captured data. It involves 3D body estimation, clothing surface registration and clothing deformation modeling. I will conclude this talk by outlining the current challenges and some promising research directions in this field.
Biography: Jinlong has obtained his PhD from Inria Grenoble Rhône-Alpes, France in 2019. His PhD thesis, done in Morpheo team and supervised by Franck Hétroy-Wheeler and Stefanie Wuhrer, is focused on learning shape space of clothed human. He also worked recently as a research intern for 6 months in Facebook with Tony Tung. His master degree was obtained in Technical University Munich where he studied robotics and focused on robotic vision. His research interest lies in human body estimation, non-rigid surface registration, shape modeling and deep learning.