Marc Pollefeys | Swiss Federal Institute of Technology (ETH) (original) (raw)
Papers by Marc Pollefeys
Bookmarks Related papers MentionsView impact
Recovering motion information from input camera image sequences is a classic problem of computer ... more Recovering motion information from input camera image sequences is a classic problem of computer vision. Conventional approaches estimate motion from either dense optical flow or sparse feature correspondences identified across successive image frames. Among other things, performance depends on the accuracy of the feature detection, which can be problematic in scenes that exhibit view-dependent geometric or photometric behaviors such as occlusion, semitransparancy, specularity and curved reflections. Beyond feature measurements, researchers have also developed approaches that directly utilize appearance (intensity) measurements. Such appearance-based approaches eliminate the need for feature extraction and avoid the difficulty of identifying correspondences. However the simplicity of on-line processing of image features is usually traded for complexity in off-line modeling of the appearance function. Because the appearance function is typically very nonlinear, learning it usually re...
Bookmarks Related papers MentionsView impact
2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010
Bookmarks Related papers MentionsView impact
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Bookmarks Related papers MentionsView impact
Image and Vision Computing, 2017
Bookmarks Related papers MentionsView impact
IEEE transactions on pattern analysis and machine intelligence, Jan 23, 2016
In this paper, we explore the different minimal solutions for egomotion estimation of a camera ba... more In this paper, we explore the different minimal solutions for egomotion estimation of a camera based on homography knowing the gravity vector between calibrated images. These solutions depend on the prior knowledge about the reference plane used by the homography. We then demonstrate that the number of matched points can vary from two to three and that a direct closed-form solution or a Gr¨obner basis based solution can be derived according to this plane. Many experimental results on synthetic and real sequences in indoor and outdoor environments show the efficiency and the robustness of our approach compared to standard methods.
Bookmarks Related papers MentionsView impact
Lecture Notes in Computer Science, 2014
Bookmarks Related papers MentionsView impact
2014 2nd International Conference on 3D Vision, 2014
Bookmarks Related papers MentionsView impact
2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013
Bookmarks Related papers MentionsView impact
2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008
Bookmarks Related papers MentionsView impact
2009 IEEE 12th International Conference on Computer Vision, 2009
Bookmarks Related papers MentionsView impact
IPSJ Transactions on Computer Vision and Applications, 2010
Bookmarks Related papers MentionsView impact
2008 IEEE Workshop on Applications of Computer Vision, 2008
Bookmarks Related papers MentionsView impact
Lecture Notes in Computer Science, 2004
Bookmarks Related papers MentionsView impact
Computer Vision – ECCV 2010, 2010
Bookmarks Related papers MentionsView impact
2009 Ieee 12th International Conference on Computer Vision (Iccv), 2009
Bookmarks Related papers MentionsView impact
2010 44th Annual Conference on Information Sciences and Systems (CISS), 2010
Bookmarks Related papers MentionsView impact
2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011
Bookmarks Related papers MentionsView impact
ISPRS Journal of Photogrammetry and Remote Sensing, 2010
Bookmarks Related papers MentionsView impact
International Journal of Image and Graphics, 2004
We present a new method for using commodity graphics hardware to achieve real-time, on-line, 2D v... more We present a new method for using commodity graphics hardware to achieve real-time, on-line, 2D view synthesis or 3D depth estimation from two or more calibrated cameras. Our method combines a 3D plane-sweeping approach with 2D multi-resolution color consistency tests. We project camera imagery onto each plane, compute measures of color consistency throughout the plane at multiple resolutions, and then choose the color or depth (corresponding plane) that is most consistent. The key to achieving real-time performance is our use of the advanced features included with recent commodity computer graphics hardware to implement the computations simultaneously (in parallel) across all reference image pixels on a plane. Our method is relatively simple to implement, and flexible in term of the number and placement of cameras. With two cameras and an NVIDIA GeForce4 graphics card we can achieve 50–70 M disparity evaluations per second, including image download and read-back overhead. This perf...
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Recovering motion information from input camera image sequences is a classic problem of computer ... more Recovering motion information from input camera image sequences is a classic problem of computer vision. Conventional approaches estimate motion from either dense optical flow or sparse feature correspondences identified across successive image frames. Among other things, performance depends on the accuracy of the feature detection, which can be problematic in scenes that exhibit view-dependent geometric or photometric behaviors such as occlusion, semitransparancy, specularity and curved reflections. Beyond feature measurements, researchers have also developed approaches that directly utilize appearance (intensity) measurements. Such appearance-based approaches eliminate the need for feature extraction and avoid the difficulty of identifying correspondences. However the simplicity of on-line processing of image features is usually traded for complexity in off-line modeling of the appearance function. Because the appearance function is typically very nonlinear, learning it usually re...
Bookmarks Related papers MentionsView impact
2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010
Bookmarks Related papers MentionsView impact
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Bookmarks Related papers MentionsView impact
Image and Vision Computing, 2017
Bookmarks Related papers MentionsView impact
IEEE transactions on pattern analysis and machine intelligence, Jan 23, 2016
In this paper, we explore the different minimal solutions for egomotion estimation of a camera ba... more In this paper, we explore the different minimal solutions for egomotion estimation of a camera based on homography knowing the gravity vector between calibrated images. These solutions depend on the prior knowledge about the reference plane used by the homography. We then demonstrate that the number of matched points can vary from two to three and that a direct closed-form solution or a Gr¨obner basis based solution can be derived according to this plane. Many experimental results on synthetic and real sequences in indoor and outdoor environments show the efficiency and the robustness of our approach compared to standard methods.
Bookmarks Related papers MentionsView impact
Lecture Notes in Computer Science, 2014
Bookmarks Related papers MentionsView impact
2014 2nd International Conference on 3D Vision, 2014
Bookmarks Related papers MentionsView impact
2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013
Bookmarks Related papers MentionsView impact
2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008
Bookmarks Related papers MentionsView impact
2009 IEEE 12th International Conference on Computer Vision, 2009
Bookmarks Related papers MentionsView impact
IPSJ Transactions on Computer Vision and Applications, 2010
Bookmarks Related papers MentionsView impact
2008 IEEE Workshop on Applications of Computer Vision, 2008
Bookmarks Related papers MentionsView impact
Lecture Notes in Computer Science, 2004
Bookmarks Related papers MentionsView impact
Computer Vision – ECCV 2010, 2010
Bookmarks Related papers MentionsView impact
2009 Ieee 12th International Conference on Computer Vision (Iccv), 2009
Bookmarks Related papers MentionsView impact
2010 44th Annual Conference on Information Sciences and Systems (CISS), 2010
Bookmarks Related papers MentionsView impact
2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011
Bookmarks Related papers MentionsView impact
ISPRS Journal of Photogrammetry and Remote Sensing, 2010
Bookmarks Related papers MentionsView impact
International Journal of Image and Graphics, 2004
We present a new method for using commodity graphics hardware to achieve real-time, on-line, 2D v... more We present a new method for using commodity graphics hardware to achieve real-time, on-line, 2D view synthesis or 3D depth estimation from two or more calibrated cameras. Our method combines a 3D plane-sweeping approach with 2D multi-resolution color consistency tests. We project camera imagery onto each plane, compute measures of color consistency throughout the plane at multiple resolutions, and then choose the color or depth (corresponding plane) that is most consistent. The key to achieving real-time performance is our use of the advanced features included with recent commodity computer graphics hardware to implement the computations simultaneously (in parallel) across all reference image pixels on a plane. Our method is relatively simple to implement, and flexible in term of the number and placement of cameras. With two cameras and an NVIDIA GeForce4 graphics card we can achieve 50–70 M disparity evaluations per second, including image download and read-back overhead. This perf...
Bookmarks Related papers MentionsView impact