We work on computer vision and machine learning. Particular areas of interest for the lab include:
  • physical properties: How do we recover a rich 3D world from a 2D image? I am especially interested in representations -- the answers that are obvious are also obviously defective -- as well as how we should reconcile our strong prior knowledge about this structure of the problem with data-driven techniques.
    Lately, I've become interested in applying this more broadly with the hope that we can develop AI systems that can learn how the physical world works from observation, including work on solar physics.
  • functional properties: How do we infer and understand opportunities for interaction? I am interested how an agent (e.g., human or robot) can interact with the world, including in terms of what this implies for 3D understanding.


  • (September 2020) 3 new PhD students start!
  • (August 2020) Among some other publications, we've published 3 papers at CVPR, 2 at ECCV, 1 at MLHC.
  • (August 2019) 3 new PhD students start!
  • (July 2019) Stop using contrived versions of MNIST to test your algorithms! Check out our new dataset of 8 years of solar data here, including 60K observations in 512x512 glory across 12 modalities (plus 14 scalar labels too).