EECS Joint Colloquium Distinguished Lecture Series  
Wednesday, December 1st 2004 Pat Hanrahan Computer Science Department 

Inverse Vision 

Abstract: 

The fields of computer graphics and computer vision may be considered duals of each other. In graphics, rendering is the process of generating an image from a model of the world. In vision, a model of the world is formed from an image. Rendering is normally considered the forward problem; that is, a mathematical procedure for simulating the physics of light and its interactions with the environment. And vision is considered an inverse problem; that is, the more challenging problem of ondoing the effects of image formation and light transport to infer information about the environment. As is wellknown, inverse problems often do not have unique solutions or are illconditioned. Inverse problems require regularization or a prior model. In this talk I will explore this duality. I will discuss briefly the state of the art in rendering, illustrating the talk with recent research on lighting simulation and material models. Based on this research, I will then discuss the relationship between rendering and vision, and suggest that it is often better to think of rendering as the inverse of vision (the inverse of inverse rendering).


Biography:  
Pat Hanrahan is the CANON USA Professor of Computer Science and Electrical Engineering at Stanford University where he teaches computer graphics. His current research involves visualization, graphics systems and architectures, and image synthesis. He was a founding employee of Pixar, where he developed volume rendering software and was the chief architect of the RenderMan(TM) Interface  a protocol that allows modeling programs to describe scenes to high quality rendering programs. Professor Hanrahan has received three university teaching awards, two Academy Awards for Science and Technology, the SIGGRAPH Computer Graphics Achievement Award, and the SIGGRAPH Stephen Coons Award. He was recently elected to the National Academy of Engineering. 