The workshop will be held on the 15th of June.
Tutorial 1: Virtual Humans in Virtual Reality
Prof. Nadia Magnenat-Thalmann
Director, Institute for Media Innovation, Nanyang Technological University, Singapore
Prof. Daniel Thalmann
Institute for Media Innovation, Nanyang Technological University, Singapore
This tutorial will explain:
- How to model 3D Virtual Humans (head and bodies) interactively for real-time applications. We will show our recent work on how to define any body size from dimensions and also how we can take pictures to get our personalized head.
- How these Virtual Humans (VH) are animated in real-time.
- How we can define VH that have an emotional behavior (personality and mood and emotions) and how to allow them to remember us and have a believable relationship with us. This tutorial will also address the modelling of long-term and short-term memory. We will also explain interactions between users and virtual humans based on gaze and how to model visual attention. In addition to the character gaze behaviors, we will show how to allow VH to respond to gestures (e.g. waving). We will explain different methods to identify user actions and how to allow VH to answer to them.
- We will also show how we can create and animate a group and a crowd of people, and show how we can model VH differently from each other. We will present the concepts of behavioral animation, group simulation, intercommunication between virtual humans, and interaction between real humans and autonomous virtual humans.
Applications will be shown in the area of
- a virtual teacher that has good and bad students,
- social phobia,
- virtual rehabilitation and
- emergency situations.
Tutorial 2: Spatial-temporal Surface Acquisition Before and After the Kinect
Spatial-temporal surface acquisition has a wide variety of applications. To mention a few: in the entertainment industry it is widely used for face and garment capture, in engineering to observe the geometric behavior of materials under stress and in tele-presence to generate footage for 3D displays. In the first part this tutorial will discuss some of the challenges of spatial-temporal reconstruction using multiple video-camera setups, presenting in detail several state-of the art solutions.
With the recent availability of inexpensive hybrid depth/color cameras such as the Kinect, that provide real-time geometric and texture information, the spatial-temporal surface acquisition problem enters a new chapter. However, many challenges still remain to be solved and new challenges emerged. In the second part, this tutorial will discuss hybrid setups that mix video-cameras with depth-cameras for real-time spatial-temporal acquisition with applications in telepresence.
Prof. Daniel Thalmann is with the Institute for Media Innovation at the Nanyang Technological University in Singapore. He is a pioneer in research on Virtual Humans. His current research interests include Real-time Virtual Humans in Virtual Reality, crowd simulation, and 3D Interaction. Daniel Thalmann has been the Founder of The Virtual Reality Lab (VRlab) at EPFL. He is coeditor-in-chief of the Journal of Computer Animation and Virtual Worlds, and member of the editorial board of 6 other journals. Daniel Thalmann was member of numerous Program Committees, Program Chair and CoChair of several conferences including IEEE VR, ACM VRST, and ACM VRCAI. Daniel Thalmann has published more than 500 papers in Graphics, Animation, and Virtual Reality. He is coeditor of 30 books, and coauthor of several books including ”Crowd Simulation” and “Stepping Into Virtual Reality”, published in 2007 by Springer. He received his PhD in Computer Science in 1977 from the University of Geneva and an Honorary Doctorate (Honoris Causa) from University Paul- Sabatier in Toulouse, France, in 2003. He also received the Eurographics Distinguished Career Award in 2010. |
Prof. Nadia Magnenat Thalmann has pioneered research into virtual humans over the last 30 years. She obtained several Bachelor’s and Master’s degrees in various disciplines (Psychology, Biology and Biochemistry) and a PhD in Quantum Physics from the University of Geneva in 1977. From 1977 to 1989, she was a Professor at the University of Montreal in Canada. From 1989 to 2010, she has been a Professor at the University of Geneva where she founded the interdisciplinary research group MIRALab. Together with her PhD students, she has published more than 550 papers on virtual humans and virtual worlds with applications in 3D clothes, hair, body modelling, emotional virtual humans and social robots and medical simulation of articulations. In 2009, she received a Dr Honoris Causa from the Leibniz University of Hanover in Germany and iIn May 2010, the Distinguished Career Award from the Eurographics. In June 2010, she received an Honorary Doctorate of the University in Ottawa in Canada. She is presently Professor and Director of the Institute for Media Innovation (IMI) at Nanyang Technological University, Singapore and Director of MIRALab at the University of Geneva, Switzerland. She is a life member of the Swiss Academy of Engineering Sciences (SATW). |
Dr. Tiberiu Popa is a postdoctoral researcher in the Computer Graphics Lab at ETH Zurich. He completed his Bachelor of Mathematics in 2001 and Master of Mathematics in 2003, both at the University of Waterloo in Canada. In 2010, Tiberiu obtained a PhD from the University of British Columbia in Canada that received the Alain Fournier annual thesis award, and then started at ETH in January 2010. Tiberiu’s main research interests are in spatial-temporal surface acquisition, free viewpoint video, geometry from sketches, etc. |
The CGI workshops will be held on the last day of the conference, 15 June 2012.
