A Computer Graphics Grand Challenge: How Real is Real Enough?

Speaker: James D. Foley,

School of Interactive Computing, College of Computing,   

Georgia Institute of Technology

Time: 10:00 am, Oct.9, 2014

Venue: Lecture Hall, Office Building, Software Campus

Host：Baoquan Chen

Abstract: A major challenge facing computer graphics researchers is knowing how much realism is enough realism. It is tempting to always create the very most realistic images using the latest and greatest techniques. Technically, we can create many images that fool the eye.  But is that the goal?  Is it necessary? The answer is “it depends” – on the purpose for which the graphics are being created – for entertainment, for training, for conveying specific information, for carrying out a task.  Fool-the-eye realism is not always the right answer. Sometimes “less is more;” other times, “more is more.”

In this talk I categorize some of the purposes for which we create graphics images, survey experimental work and approaches to help assess the relationship between image realism and image effectiveness, and discuss my own early work using the Shepherd-Metzler mental rotation task with computer graphics images having varying degrees of realism. The talk is illustrated with images and videos.

Bio: Jim Foley is a professor in the College of Computing at Georgia Tech. He is a member of the National Academy of Engineering, and a Fellow of AAAS, ACM and IEEE.  He has received two lifetime achievement awards, from ACM/SIGGRAPH and ACM/SIGCHI. Foley is co-author of five books: Fundamentals of Interactive Computer Graphics, Three editions of Computer Graphics: Principles and Practice, and Introduction to Computer Graphics.

Foley joined Georgia Tech in 1991 as the founding director of the Graphics, Visualization and Usability Center in the College of Computing. In 1996, US News and World Report ranked the Center number one for graduate computer science work in graphics and user interaction. On leave from Georgia Tech from 1996-99, he was CEO and Chairman of Mitsubishi Electric Information Technology Center America, where he was responsible for Mitsubishi's corporate R&D in North America, and before that, Director of MERL - Mitsubishi Electric Research Laboratory. He was chairman (2001-2005) of the Computing Research Association - an organization of over 250 computer science and computer engineering departments, professional societies and research labs. From 2008 to 2011 he served as Vice President of ACM SIGGRAPH; from 2008-2010 as Interim Dean of the College of Computing.