Keynote Speakers

Marie-Paule CANI

Creative AI: Combining knowledge, learning and control for the expressive creation of animated 3D contents

While the use of digital models and simulation has already spread in many disciplines, recent advances in Computer Graphics open the way to a much lighter ways of creating 3D contents.  In this talk, I'll show how the expressive modelling paradigm - namely, the combination of graphical models embedding knowledge with gestural interfaces such as sketching, sculpting or copy-pasting - can allow seamless 3D modelling, progressive refinement, and animation of a variety of models, from individual shapes to full, animated 3D worlds. We will discuss how prior knowledge can be enhanced by learning from examples, and be possibly injected on the fly during a modelling session. As we show through examples, this methodology opens the way to seamless creation and interaction with the mental models we have in mind, opening new horizons of 3D creation to engineers and scientists and well as to the general public.

Short Bio

Marie-PauleCani is a full Professor of Computer Science at EcolePolytechnique, a school she joined in 2017 after 24 years of career at Grenoble-INP &Inria. Her research interests cover both Shape Modelling and Computer Animation. She contributed over the years to a number of high level models for shapes and motion such as implicit surfaces, multi-resolution physically-based animation and hybrid representations for real-time natural scenes. Following a long lasting interest for virtual sculpture, she has been recently searching for more expressive ways to create 3D content such as combining sketch-based interfaces with procedural models based on a combination of knowledge and learning. She received the Eurographics outstanding technical contributions award in 2011 and a Silver medal from CNRS in 2012. She was awarded the ERC advanced EXPRESSIVE (2012-2017) and elected at Academia Europaea in 2013. She served as Technical Paper Chair of SIGGRAPH 2017 and was President of the Eurographics Association in 2017 and 2018.

Thabo BEELER

Digital Humans At Disney Research

Disney Research has been actively pushing the state-of-the-art in digitizing humans over the past decade, impacting both academia and industry. Our longterm vision is to provide technology to acquire the entire likeness of a human at highest quality in order to create the best possible avatars. In this talk I will give an overview of a selected few projects in this area, from research into production. I will be talking about photogrammetric shape acquisition and dense performance capture for faces, eye and teeth scanning and parameterization, as well as physically based capture and modelling for hair and volumetric tissues.

Short Bio

Thabo Beeler is a Principal Research Scientist at Disney Research in Zurich, where he is heading the Capture and Effects group. For his contributions to markerless facial performance capture, he just received a Technical Achievement Award of the Academy of Motion Pictures in 2019. In 2018 he was awarded the Eurographics Young Researcher Award for his research and prior to that he obtained his PhD from ETH Zurich, for which he was awarded with the Eurographics PhD award in 2013. He was also awarded the ETH medal (highest possible distinction) for his master thesis by the Swiss Federal Institute of Technology. Over the past decade, Thabo has been working on digital humans, focusing on high-quality facial geometry reconstruction and dense performance capture. He has published several papers on these topics and has contributed to different feature films, advancing the state-of-the-art on whats considered the holy grail of visual effects.