I am a professor at EECS Department at UC Berkeley, where I am part of the Berkeley Artificial Intelligence Research Lab (BAIR). Before that, I spent nine years on the faculty of the Robotics Institute at CMU. I am also still remembered in lovely Oxford, where I did a post-doc with Andrew Zisserman. Starting in 2007, I have also been closely collaborating with Team WILLOW at École Normale Supérieure / INRIA in beautiful Paris. Over the years, I was lucky to have some amazing officemates.

    The central goal of my research is to use vast amounts of visual data to understand, model, and recreate the visual world around us. My research has been mainly in data-driven computer vision, as well as its projection onto computer graphics and computational photography. Other interests include human vision, unsupervised learning, visual data mining, robotics, and the applications of computer vision to the visual arts and the humanities. I also enjoy making scientific bets.
    For a high-level overview of my research, see a recent Heidelberg Forum talk on "Self-Supervised Visual Learning and Synthesis", or, for a more technical talk, see "Self-supervision, Meta-supervision, Curiosity: Making Computers Study Harder". Or, for something completely different, check out a recent New Yorker article about some of our work.