Professor Aaron Hertzmann

Aaron Hertzmann, Ph.D. is Associate Professor, Department of Computer Science, University of Toronto.
 
Broadly speaking, Aaron is interested in all areas of computer graphics and computer vision. His work seeks to address the following high-level questions:

• Computer Graphics: What powerful tools can we provide to artists, designers, scientists, and novice users for creating beautiful, expressive, artistic, and/or illustrative imagery and animation?
• Computer Vision: How can we visually understand the world, extract meaning from images, and model the human visual system?

Moreover, he is increasingly interested in applications of Machine Learning — especially Bayesian inference — to these two areas. Computer vision and graphics both rely heavily on analysis and generation of data, and Bayesian learning provides extremely powerful tools for interpreting data. He collaborates actively with his colleagues at UofT. UofT has some of the strongest groups around in the areas of computer vision, machine learning, and graphics/HCI. He also collaborates with a number of labs internationally, including University of Washington’s GRAIL lab.
 
Aaron coauthored Feature-Based Locomotion Controllers, Robust Physics-Based Locomotion Using Low-Dimensional Planning, Optimizing Walking Controllers for Uncertain Inputs and Environments, Learning 3D Mesh Segmentation and Labeling, Learning Physics-Based Motion Style with Nonlinear Inverse Optimization, and Example-Based Photometric Stereo: Shape Reconstruction with General, Varying BRDFs. Read the full list of his publications!
 
His patents include Method and system for generating an image having a hand-painted appearance, Stateless remote environment navigation, and Removing camera shake from a single photograph using statistics of a natural image.
 
Aaron earned his B.A. in Computer Science and Art & Art History at Rice University in 1996, his M.S. in Computer Science at New York University in 1998, and his Ph.D. in Computer Science at New York University in 2001 with the thesis Algorithms for Rendering in Artistic Styles. He is also winner of the 2004 MIT Technology Review’s 100 Top Young Innovators Under 35 and winner of the $200,000 2006 Microsoft Research Faculty Fellowship Award.
 
Watch Style-based Inverse Kinematics and Active Learning for Real-Time Motion Controllers. Read Virtual walkers lead the way for robots, Prototype: Auto Animator, and Computer mimics great masters’ style. Visit his Facebook page.