Jan-Michael Frahm

Research Scientist Manager

I am a Research Scientist Manager for the 4DAI group in the CoreAI team within Facebook Reality Labs and a full professor at the University of North Carolina at Chapel Hill. My group focuses on large-scale efficient scene reconstruction focusing on next generation efficient large-scale structure from motion, dense scene reconstruction at scale, improved AR/VR content generation, and visualization.

I lead the 3D Computer vision group at the University of North Carolina at Chapel Hill where I researched on structure from motion for single/multi-camera systems for static and dynamic scenes to create 3D models of the scene; real-time multi-view stereo to create a dense scene geometry from camera images; the use of camera-sensor systems for 3D scene reconstruction with fusion of multiple orthogonal sensors; improved robust and fast estimation methods from noisy data to compensate for highly noisy measurements in various stages of the reconstruction process; high performance feature tracking for salient image-point motion extraction; and the development of data-parallel algorithms for commodity graphics hardware for efficient 3D reconstruction. I was also an editor in chief for the Elsevier Journal of Image and Vision computing and have over 100 publications in computer vision, including publications in the top computer vision conferences and journals. I hold several patents in the area of geometric computer vision. I received my PhD in computer vision in 2005 from the Christian-Albrechts University of Kiel, Germany and my Bachelor’s from the University of L├╝beck in Germany.


Structure from motion, dense depth estimation, image based localization, robust estimation

Related Links

Google Scholar

Latest Publications

SIGGRAPH - August 17, 2020

One Shot 3D Photography

Johannes Kopf, Kevin Matzen, Suhib Alsisan, Ocean Quigley, Francis Ge, Yangming Chong, Josh Patterson, Jan-Michael Frahm, Shu Wu, Matthew Yu, Peizhao Zhang, Zijian He, Peter Vajda, Ayush Saraf, Michael Cohen

CVPR - June 16, 2020

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

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