Kevin Matzen

Research Scientist

I joined the Facebook Computational Photography group in August 2016 as a research scientist with a focus on computer vision and machine learning. In particular, I work on problems related to understanding our ever-changing world through the enormous number of photos people upload to the internet. Prior to Facebook I received my PhD in computer science from Cornell University in 2016 and my BSE in computer engineering from the University of Michigan in 2010.


Computer vision, deep learning, 3d reconstruction, virtual reality, data science and big data

Latest Publications

VPLNet: Deep Single View Normal Estimation with Vanishing Points and Lines

Rui Wang, David Geraghty, Kevin Matzen, Richard Szeliski, Jan-Michael Frahm

CVPR - June 16, 2020

DeepMVS: Learning Multi-view Stereopsis

Po-Han Huang, Kevin Matzen, Johannes Kopf, Narendra Ahuja, Jia-Bin Huang

CVPR 2018 - June 18, 2018

Low-Cost 360 Stereo Photography and Video Capture

Kevin Matzen, Michael Cohen, Bryce Evans, Johannes Kopf, Richard Szeliski

SIGGRAPH 2017 - July 30, 2017