Marc Pollefeys' homepage (original) (raw)

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](2021%5FCV%5FMarc Pollefeys%5F2pages.pdf)] extended version[[pdf]](CVmp.pdf-webpage%5Fnew - extended.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] [CrowdSourcing.org]

Some cool stuff with helicopters [PixHawk]

Video from a 2007 talk at Google [video]

Postdoctoral researchers & senior researchers

• Lubor Ladicky, 2013-
• Torsten Sattler, 2013-
• Martin Oswald, 2014-

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

• Olivier Saurer, Ph.D. 2016, Immersive Environments: From Virtual Indoor Tours to Outdoor Modelling, now working on start-up project.
• Petri Tanskanen, Ph.D. 2016, Live 3D Reconstruction on Mobile Phones, now working on start-up project.
• Bernhard Zeisl, Ph.D. 2015, Leveraging Geometric Priors and Measurements in 3D Modeling, Calibration and Registration, now at Google Zurich.
• Aparna Taneja, Ph.D. 2014, Geometric Change Detection and Image Registration in Large Scale Urban Environments, now at Google Zurich.
• Lionel Heng, Ph.D. 2014, Toward Full Autonomy for Vision-Guided Robots: From Self-Calibration to Self-Directed Exploration, now at DSO Singapore.
• Jens Puwein, Ph.D. 2014, Computer Vision for Sports Broadcasts and Human Performances, now at VizRT.
• Gim Hee Lee, Ph.D. 2014, Visual Mapping and Pose Estimation for Self-Driving Cars, now assistant professor at NUS.
• Alexander Schwing, Ph.D. 2013, Inference and Learning Algorithms with Applications to 3D Indoor Scene Understanding, now postdoc at University of Toronto.
• Georges Baatz, Ph.D. 2012, Visual Location Recognition in Man-Made and Natural Environments, now at Google Zurich.
• Roland Angst, Ph.D. 2012, Subspaces in Geometric Computer Vision: Models and Algorithms, now Junior Group Leader at MPI Saarbruecken.
• Rahul Raguram, Ph.D. 2012, co-advised with Jan-Michael Frahm, efficient algorithms for robust estimation, now at Apple.
• David Gallup, Ph.D. 2010, efficient 3D reconstruction of large-scale urban environments from street-level video, now at Google.
• Brian Clipp, Ph.D. 2010, Multi-Camera Simultaneous Localization and Mapping, now at UCR Ventures
• Changchang Wu, Ph.D. 2010, Geometry-driven Feature Detection, now at Google.
• Li Guan, Ph.D. 2009, Multi-view Dynamic Scene Modeling, now at Zillow.
• Sudipta Sinha, Ph.D. 2008, Silhouettes for calibration and reconstruction from multiple views, now researcher at MSR (Redmond)
• Seon Joo Kim, Ph.D. 2008, Radiometric Calibration Methods from Image Sequences, assistant professor at Yonsei University (Korea)
• Jingyu Yan, Ph.D. 2006, Articulated Non-Rigid Shape, Motion and Kinematic Chain Recovery from Video, now at Amazon
• Luca Ballan, 2009-2015, now senior researcher at Apple.
• Amael Delaunoy, 2012-2015, now senior research engineer at Apple.
• Kalin Kolev, 2012-2015, now senior developer at Seene.
• Jean-Charles Bazin, 2011-present, 3D tele-presence
• Friedrich Fraundorfer, 2007-2012, now assistant professor at TUGraz.
• Kevin Koeser, 2009-2013, now senior researcher at GEOMAR.
• Roland Memisevic, 2010-2010, now assistant professor at the Universite de Montreal.
• Christopher Zach, 2008-2011, urban 3D modeling, now researcher at Toshiba Research Cambridge
• Gabriel Brostow, postdoc 2008-2009, 4D event modeling, now senior lecturer at UCL
• Jean-Sebastien Franco, postdoc 2006-2007, multi-view dynamic scene reconstruction, now assistant professor at ENSIMAG/INRIA Grenoble.
• Philippos Mordohai, postdoc 2005-2007, urban 3D modeling, now associate professor at Stevens Institute of Technology.
• Jan-Michael Frahm, postdoc 2005-2007, associate professsor at UNC-Chapel Hill
• Paul Merrell, M.S. 2007, urban 3D modeling, now with the Gamma group at UNC.
• Sriram-Thirthala Venkata, M.S. 2006, multi-view geometry of non-central cameras, now at Google
• Jason Repko, M.S. 2005, 3D-from-video and 3D-TV, now at USPTO (Graphics and Animation group)
• Oisin Mac Aodha, 2008-2009, optical flow and learning
• Pranav Singh, 2009-2011, multi-view object reconstruction
• Olga Diamanti, 2008-2010 (ETH MS)
• Golnoosh Samei, 2008-2010 (ETH MS)

Main collaborators

• Jan-Michael Frahm ( University of North Carolina )
• Otmar Hilliges, Markus Gross (ETH Zurich)

Data

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]