When is a Rendered Image Good Enough: Perceptually-Based Realistic Rendering
Kavita Bala, Associate Professor, Computer Science and Program of Computer Graphics, Cornell University
Friday, April 23, 2010
This seminar is part of the Jones Seminars on Science, Technology, and Society series
Producing realistic images is a fundamental challenge in computer graphics. But physically accurate realism is far too expensive — the key is to cheat the human eye by focusing computation only where it is needed to affect perceived image quality. But when is a rendered image a good enough representation of a scene's appearance? In this talk I will describe our work on a new standard of image quality, visual equivalence, that aims to characterize when an object's appearance is faithfully reproduced in an image. I will also describe scalable algorithms that exploit knowledge of human perception to efficiently render complex materials and lighting. Applications of this research include ecommerce, cultural heritage, virtual training, games, and movies.
About the Speaker
Kavita Bala is an Associate Professor in the Computer Science Department at Cornell University. She received her S.M. and Ph.D. from the Massachusetts Institute of Technology (MIT), and her B.Tech. from the Indian Institute of Technology (IIT, Bombay). Bala has co-authored the graduate textbook "Advanced Global Illumination" (A K Peters publisher, second edition), and has served on more than 30 program committees. She has co-chaired the Eurographics Symposium on Rendering (EGSR), 2005, and Pacific Graphics, 2010. Bala has received the NSF CAREER award, Cornell's College of Engineering James and Mary Tien Excellence in Teaching Award (2006 and 2009), and the Affinito-Stewart award.