Marc's picture

Marc Pollefeys
Full Professor

Computer Vision and Geometry lab (CVG) - Institute of Visual Computing

Department of Computer Science - ETH Zurich
CNB G105
Universitatstrasse 6
CH-8092 Zurich, Switzerland
Tel: +41 44 632 31 05










Short Bio

Marc Pollefeys is a Professor of Computer Science at ETH Zurich and the Director of the Microsoft Mixed Reality and AI Lab in Zurich where he works with a team of scientists and engineers to develop advanced perception capabilities for HoloLens and Mixed Reality. He was elected Fellow of the IEEE in 2012. He obtained his PhD from the KU Leuven in 1999 and was a professor at UNC Chapel Hill before joining ETH Zurich.

He is best known for his work in 3D computer vision, having been the first to develop a software pipeline to automatically turn photographs into 3D models, but also works on robotics, graphics and machine learning problems. Other noteworthy projects he worked on are real-time 3D scanning with mobile devices, a real-time pipeline for 3D reconstruction of cities from vehicle mounted-cameras, camera-based self-driving cars and the first fully autonomous vision-based drone. Most recently his academic research has focused on combining 3D reconstruction with semantic scene understanding.

Curriculum vitae - short version [pdf] extended version [pdf]

Research interests

Computer vision; 3D-from-video; (self-)calibration; structure-from-motion; simultaneous-localization and mapping (SLAM); camera tracking; camera networks; active vision; robot vision; multiple view geometry; omnidirectional vision; projector-camera systems; image-based modeling and rendering; video-based rendering; computational photography; image and video analysis; applications of computer vision to archaeology, urban modeling, terrain modeling, human-computer interaction, robotics, entertainment, medecine, etc.
[see research page]

EPFL EE Distinguished Lecture, April 2014 [YouTube]

Zurich.Minds 2011 short research presentation [YouTube]

We work with Google on Project Tango [YouTube] [NBC News]

Relive an event from multiple viewpoints: unstructured video-based rendering [webpage] (incudes interactive demo)

Reconstructing Rome: 3 million images, 1 day, 1PC... read more about it [BBC] [Chronicle of Higher Education] [Newswise] [UNC] [ReadWriteWeb] [physorg] [futurity] [smarthouse] []

Some cool stuff with helicopters [PixHawk]

Video from a 2007 talk at Google [video]

Postdoctoral researchers & senior researchers

Current PhD students

Yagız Aksoy, Federico Camposeco, Ian Cherabier, Andrea Cohen, Christian Haene, Dominik Honegger, Bastien Jacquet, Peidong Liu, Fabio Maninchedda, Lorenz Meier, Nikolay Savinov, Thomas Schoeps, Lukas Schneider, Pablo Speciale 

Alumni/Past Group Members


Main collaborators



If you want to refer to 3D modeling results we have obtained on these sequences the following paper is a good reference:
M. Pollefeys, L. Van Gool, M. Vergauwen, F. Verbiest, K. Cornelis, J. Tops, R. Koch, Visual modeling with a hand-held camera, International Journal of Computer Vision 59(3), 207-232, 2004. [IJCV][pdf]