Machine Learning for Computer Graphics: A Manifesto and Tutorial
Pacific Graphics 2003 Invited paper.
I argue that computer graphics can benefit from a
deeper use of machine learning techniques. I give an
overview of what learning has to offer the graphics community, with an
emphasis on Bayesian techniques. I also
attempt to address some misconceptions about
learning, and to give a very brief tutorial on Bayesian reasoning.
(Slides that describe unpublished work are omitted from the online version of the talk).
Citation: A. Hertzmann. Machine Learning for Computer Graphics: A Manifesto and Tutorial. Proc. Pacific Graphics 2003. Invited Paper. Banff, Alberta. October, 2003. pp. 22-36.