While modeling people wearing tight-fitting clothes is fast becoming a mature field, handling subjects wearing looser garments remains an open problem when it is to be done in everyday settings where people may hide each other, precise outlines are hard to estimate, and shadows often complicate matters.
Our goal is therefore to develop robust and accurate 3D human pose estimation algorithms that can handle people wearing loose clothing in everyday settings, which is still beyond the state-of-the-art. In the process, we will also develop new approaches to representing complex surfaces whose topology can change and to modeling their interactions. This will be a joint effort by several PhD students.
Some knowledge of machine learning, deep-learning.
Basics of computer vision.
Proficiency in Python.