Day 1 :
Keynote Forum
Jos Stam
Adjunct Professor, University of Toronto, Canada
Keynote: Art of Fluid Animation
Time : 10:00-10:45
Biography:
Jos Stam was born in the Netherlands and educated in Geneva, Switzerland, where he received dual Bachelor degrees in Computer Science and Pure Mathematics. In 1989, he moved to Toronto where he completed his Masters and Ph.D. degrees in computer science. After that, he pursued postdoctoral studies as an ERCIM fellow at INRIA in France and at VTT in Finland. In 1997 he joined the Alias Seattle office as a researcher and stayed there until 2003 to relocate to Alias' main office in Toronto. He is now employed with Autodesk as a Senior Principal Research Scientist as part of Autodesk's acquisition of Alias in 2006. He is also affiliated with the University of Toronto as an Adjunct Professor in the Department of Computer Science. His research spans several areas of computer graphics: natural phenomena, physics-based simulation, rendering and surface modeling, especially subdivision surfaces.His latest creation is a unified dynamics solver called Nucleus, which is embedded in MAYA and has been used in many movies to create special effects.e has published papers in all of these areas in journals and at conferences, most notably at the annual SIGGRAPH conference. In 2005, he was awarded one of the most prestigious awards in Computer Graphics: the SIGGRAPH Computer Graphics Achievement Award. He also won two Technical Achievement Awards from the Academy of Motion Picture Arts and Sciences: in 2005 for his work on Subdivision Surfaces and in 2007 for his work on fluid dynamics. He was also featured in a January 2008 Wired magazine article.
Abstract:
In this talk, I present my work on fluid dynamics for the entertainment industry. The talk will introduce basic concepts of fluids and a brief history of computational fluid dynamics. Subsequently I will talk about my contributions of applying computational fluid dynamics to the entertainment industry like games and movies. I will also discuss our implementation of this technology into our MAYA animation software. In 2008 I received a Technical Achievement Award from the Academy of Motion Picture Arts and Sciences ("tech Oscar") for this work. I will also mention my work on bringing fluid dynamics to mobile devices like the Pocket PC in 2001 and the iPhone in 2008. In 2010 we released FluidFX and MotionFX for iOS and MacOS. The talk will feature many live demonstrations and animations. The talk is basically a condensed version of my book "The Art of Fluid Animation".
Networking & Refreshment Break: 10:45-11:00
Keynote Forum
Paul Kruszewski
CEO & Founder, Wrnch Inc., Canada
Keynote: Using AI to create frictionless motion capture
Time : 11:00-11:45
Biography:
Dr. Paul has been at the bleeding intersection of real-time AI and Computer Graphics since 2000 when he founded AI.implant to use AI (flocking behaviours and path finding) to create and simulate huge crowds of interacting autonomous characters. Customers included Disney and Lucas Film for visual effects; Bioware and EA for game development; and L3 and Lockheed Martin for military simulation. AI.implant was acquired in 2005 by Presagis, the world’s leading developer of software tools for military simulation and training. In 2007, he founded GRIP to use AI (behaviour trees) to create high fidelity autonomous characters capable of rich and complex behaviours. Customers included Bioware, Disney, EA and Eidos. GRIP was acquired in 2011 by Autodesk, the world’s leading developer of software tools for digital entertainment. In 2014, he founded wrnch to use AI to make the world safer, healthier and more fun by turning ordinary cameras into frictionless motion capture systems. Customers include Softbank and NVIDIA
Abstract:
Motion Capture has revolutionized computer graphics by making 3D animation incredibly lifelike. Not withstanding this enormous success, the prohibitly high set up and operating costs of traditional motion capture techniques, limits its use only the largest 3D content creators. In this talk, we describe how deep learning can overcome these barriers and turn any cell phone camera into a production ready motion capture system.