CS6630: Realistic Image Synthesis
Spring 2012

About CS6630

Steve Marschner, srm at cs.cornell.edu
  ofc hrs Tu 2:15–3:15, Th 3:15–4:15 in 5159 Upson

Wenzel Jakob, wenzel at cs.cornell.edu
  ofc hrs W 1:30–2:30 in 5156 Upson

Time and place:
Lectures: T/Th 10:10–11:25, 205 Upson

Electronic communication:
We are using Piazza to handle questions, answers, and announcements. Please sign yourself up.


CS6630 is an introduction to physics-based rendering at the graduate level. Starting from the fundamentals of light transport we will look at formulations of the Rendering Equation, and a series of Monte Carlo methods, from sequential sampling to multiple importance sampling to Markov Chains, for solving the equation to make pictures. We'll look at light reflection from surfaces and scattering in volumes, illumination from luminaires and environments, and diffusion models for translucent materials. We will build working implementations of many of the algorithms we study, and learn how to make sure they are actually working correctly. It's fun to watch integrals and probability distributions transform into photographs of a slightly too perfect synthetic world.

Coursework will include some written homeworks, some implementation projects, reading and presenting research papers, and a final project of your choosing. A previous graphics course is expected, although not strictly required; talk to me first. A certain level of mathematical sophistication, particularly in probability and multivariable calculus, will be needed.