Modelling Clothed Humans via Neural Implicit Representations

Shaofei Wang (Ph.D. Student)

This project aims at registration and generation of clothed humans in 3D. The first part of this project concerns registering parametric human body models, e.g. poses and shapes, to sensor inputs such as RGBD images. The second part of this project will tackle the problem of building a controllable neural implicit representation of clothed humans, using the registration information obtained in the first part. The final goal of the project is to enable generation of personalised animatable avatars of clothed humans, given only a few RGBD images of a person.

Primary Host:	Siyu Tang (ETH Zürich)
Exchange Host:	Andreas Geiger (University of Tübingen & Max Planck Institute for Intelligent Systems)
PhD Duration:	01 September 2020 - 30 June 2024
Exchange Duration:	01 May 2022 - 30 November 2022 - Ongoing