Speaker: Dr. Stefano Berretti, University of Florence, Italy
Title of Talk: 3D Face Modeling
Biography: Stefano Berretti received his Master and PhD degrees in Computer Engineering from the University of Florence, Italy, where he is currently an Associate Professor at the Media Integration and Communication Center and at the Department of Information Engineering. He was a visiting researcher at the Indian Institute of Technology (IIT) in Mumbai, at the University of Lille, and at the Khalifa University. More recently, he has been also Visiting Professor at the University of Lille, and the University of Edmonton. He is also the Information Director and an Associate Editor of the ACM Transactions on Multimedia Computing, Communications, and Applications(ACM TOMM), and an Associate Editor of the IET Computer Vision journal.
Stefano is interested in the combination of computer vision, machine learning and graphics to investigate new methods for reconstruction, modelling and recognizing human faces and expression in 3D, for human emotion and behavior understanding from 2D and 3D images and videos. He is also interested in manifold-based methods for modeling and recognition in non-Euclidean domains.
Talk description: Though 3D Morphable Models (3DMM) of the face dates to late ’90, in the past few years they have been re-discovered in the context of deep learning and are now incorporated into many state-of-the-art solutions for face analysis. In this talk, I will discuss recent approaches to the problem of 3DMM construction and fitting, focusing on the challenges in building and applying these models, and the main insights that helped us address them. I will additionally mention interesting open problems, highlighting the broad range of current and future applications, and some stepping stones towards unexplored directions.