Home
Kavita Bala, Cornell
When is a rendered image good enough? Perceptually-Based Realistic Rendering
| What |
|
|---|---|
| When |
Nov 12, 2009 from 04:00 pm to 05:00 pm |
| Where | Maxwell Dworkin G125 |
| Contact Name | gioia@pacific.harvard.edu |
| Contact Phone | (617) 495-2919 |
| Add event to calendar |
 vCal iCal
|
Abstract
Producing realistic images is a fundamental challenge of computer graphics. But physically accurate realism is still far too expensive -- the key is to focus 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?
This is an open problem. 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. Our goal is to use such perceptual standards of quality to drive efficient, realistic rendering. In this talk I will describe new scalable algorithms for rendering complex materials and lighting, and demonstrate their application to ecommerce. Other
applications include cultural heritage, virtual training, games and movies.
Speaker Bio
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 specializes in computer graphics, leading research projects in scalable graphics, perceptually-based rendering, and image-based modeling and texturing. She co-authored the graduate-level textbook "Advanced Global Illumination" (A K Peters publisher, second edition). She co-chaired the Eurographics Symposium on Rendering and Pacific Graphics.Bala received the NSF CAREER award and Cornell's College of Engineering James and Mary Tien Excellence in Teaching Award (2006 and 2009).