I am an incoming Assistant Professor at MIT EECS, where I will be leading the
Scene Representation Group. Currently, I am a Postdoc at MIT's CSAIL with
Josh Tenenbaum, Bill Freeman, and Fredo Durand. Previously, I finished a Ph.D. at Stanford University.
My research interest lies in neural scene representations - the way neural networks learn to represent information on our world.
My goal is to allow independent agents to reason about our world given visual observations,
such as inferring a complete model of a scene with information on geometry, material, lighting etc.
from only few observations, a task that is simple for humans, but currently impossible for AI.
Hiring graduate students!
I am hiring graduate students to join my lab at MIT in July 2022. If you want to push what's
possible with neural scene representations, inverse graphics and neural rendering
and apply them to problems across computer vision, graphics, and robotics, please apply here -
deadline is December 15th 2021!
News
June 2021
I am thrilled to announce that I will be joining MIT as tenure-track assistant professor in July
2022! My lab will investigate neural scene representations, inverse graphics,
neural rendering, and their applications in vision, graphics, robotics, and AI.
June 2021
I have created a slideshare account and will start uploading slides for some of my presentations
/ talks / courses, starting with the slides for the introduction to novel view synthesis at SIGGRAPH
2021. Feel free to re-use them - I only ask that you keep some form of acknowledgement :) Find them
here.
January 2021
I published a
reading list on neural implicit representations on github that I give students to get started in this area, inspired by the awesome-computer-vision list with extra commentary & notes. Check it out!
Our CVPR tutorial on Neural Rendering is on youtube, free to watch for everyone!
Here's the link to the morning session -
at 2:20:00, I'm giving an overview over Novel View Synthesis.
Here's the link to the afternoon session.
November 2019
Our paper "Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations" wins an honorable mention for "Outstanding New Directions" at NeurIPS 2019! Watch my talk here.
May 2019
I will join Prof. Noah Snavely's group at the Google NYC office over the summer and continue working
on deep learning for scene understanding and novel view synthesis.
Publications
Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation
arXiv 2021
Anthony Simeonov*, Yilun Du*, Andrea Tagliasacchi, Alberto Rodriguez, Pulkit Agrawal†, Vincent Sitzmann†
Computer Graphics Forum 2020 - EG 2020 (STAR Report)
Ayush Tewari*, Ohad Fried*, Justus Thies*, Vincent Sitzmann*, Stephen Lombardi, Kalyan Sunkavalli, Ricardo Martin-Brualla, Tomas Simon, Jason Saragih, Matthias Nießner, Rohit Pandey, Sean Fanello, Gordon Wetzstein, Jun-Yan Zhu, Christian Theobalt, Maneesh Agrawala, Eli Shechtman, Dan B Goldman, Michael Zollhöfer