Sophisticated computer graphics applications require complex models of appearance, motion, natural phenomena, and even artistic style. Such models are often difficult or impossible to design by hand. Recent research demonstrates that, instead, we can "learn" a dynamical and/or appearance model from captured data, and then synthesize realistic new data from the model. For example, we can capture the motions of a human actor and then generate new motions as they might be performed by that actor. Bayesian reasoning is a fundamental tool of machine learning and statistics, and it provides powerful tools for solving otherwise-difficult problems of learning about the world from data. Beginning from first principles, this course develops the general methodologies for designing learning algorithms and describes their application to several problems in graphics.
Organizer and Lecturer
Aaron Hertzmann
University of Toronto
Course slides
Information Theory, Inference, and Learning Algorithms, by David MacKay, available online
Probability Theory: The Logic of Science, by Edwin T. Jaynes. An older draft is available online.
Neural Networks for Pattern Recognition, by Chris Bishop.
Zoubin Ghahramani's Tutorial on Bayesian Methods for Machine Learning.
Wikipedia entries on Bayesian Probability, Bayesian inference, Cox axioms
Michiel van de Panne's list of Applications of Machine Learning in Computer Graphics and Animation
Conferences in learning: NIPS, UAI/ICML/CoLT 2004. Proceedings of past NIPS conferences.
3:45pm-4:00pm: Introduction
4:00pm-4:45pm: Fundamentals of Bayesian probabilistic reasoning
4:45pm-5:15pm: Statistical shape and appearance models
5:15pm-5:30pm: Summary and Conclusions