I am the Eliot Horowitz Assistant Professor of Computer Science at Brown University, where I co-lead the Brown Visual Computing group. My research sits at the intersection of computer graphics, artificial intelligence, and machine learning: I build intelligent machines that understand the visual world and help people be visually creative. Much of my group's current work focuses on analyzing, synthesizing, and manipulating 3D scenes and the 3D objects that comprise them. My research is funded by gifts from Adobe, Autodesk, Pixar, and NVIDIA, as well as grants from DARPA and the National Science Foundation, including an NSF CAREER Award.

I received my PhD from Stanford University, where I worked with Pat Hanrahan in the Graphics Lab and with Noah Goodman in the Computation and Cognition Lab. I received my undergraduate degree from the University of California, Berkeley.

My Erdős number is 4 (Daniel Ritchie → Niloy Mitra → Leonidas Guibas → Boris Aronov → Paul Erdős). My Bacon number is 3, though only if you count all film credits, not just cast appearances (Daniel Ritchie → John Lasseter → Tom Hanks → Kevin Bacon). This (debatably) makes my Erdős-Bacon number 7.

News
October 2021
I'll be giving an invited talk on "Learning to Infer and Generate Programs for 3D Shapes and Scenes" at two ICCV workshops: Holistic Structures for 3D Vision and Structural and Compositional Learning on 3D Data.
October 2021
Applications are now open for the 2021-2022 edition of our exploreCSR program, Socially-Responsible AI for Computational Creativity!
June 2021
One new paper conditionally accepted to SGP 2021!
March 2021
One new paper conditionally accepted to SIGGRAPH 2021!
March 2021
Xianghao Xu's paper (with Autodesk research) on inferring CAD modeling sequences was accepted to CVPR 2021.
Archive
Publications