Marc Pollefeys

Marc Pollefeys

Auto-generated profile, based on publicly available information

Marc Pollefeys

ETH Zurich

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 October 2024
Verified
Book Chapter
Closed access
PDF file
YCYuedong Chen
Yuedong Chen
HXHaofei Xu
Haofei Xu
CZChuanxia Zheng
Chuanxia Zheng
Bohan ZhuangBohan Zhuang
Bohan Zhuang
MPMarc Pollefeys
Marc Pollefeys
JCJianfei Cai
Jianfei Cai

18 March 2016 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
DTDimitrios Tzionas
Dimitrios Tzionas
LBLuca Ballan
Luca Ballan
ASAbhilash Srikantha
Abhilash Srikantha
PAPablo Aponte
Pablo Aponte
MPMarc Pollefeys
Marc Pollefeys
JGJuergen Gall
Juergen Gall

19 October 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
CTCarl Toft
Carl Toft
WMWill Maddern
Will Maddern
ATAkihiko Torii
Akihiko Torii
LHLars Hammarstrand
Lars Hammarstrand
ESErik Stenborg
Erik Stenborg
TSTorsten Sattler
Torsten Sattler
Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds. Practical visual localization approaches need to be robust to a wide variety of viewing conditions, including day-night changes, as well as weather and seasonal variations, while providing highly accurate six degree-of-freedom (6DOF) camera pose estimates. In this paper, we extend three publicly available datasets containing images captured under a wide variety of viewing conditions, but lacking camera pose information, with ground truth pose information, making evaluation of the impact of various factors on 6DOF camera pose estimation accuracy possible. We also discuss the performance of state-of-the-art localization approaches on these datasets. Additionally, we release around half of the poses for all conditions, and keep the remaining half private as a test set, in the hopes that this will stimulate research on long-term visual localization, learned local image features, and related research areas. Our datasets are available at visuallocalization.net, where we are also hosting a benchmarking server for automatic evaluation of results on the test set. The presented state-of-the-art results are to a large degree based on submissions to our server.

8 November 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
HTHajime Taira
Hajime Taira
MOMasatoshi Okutomi
Masatoshi Okutomi
TSTorsten Sattler
Torsten Sattler
MCMircea Cimpoi
Mircea Cimpoi
MPMarc Pollefeys
Marc Pollefeys
ATAkihiko Torii
Akihiko Torii
We seek to predict the 6 degree-of-freedom (6DoF) pose of a query photograph with respect to a large indoor 3D map. The contributions of this work are three-fold. First, we develop a new large-scale visual localization method targeted for indoor spaces. The method proceeds along three steps: (i) efficient retrieval of candidate poses that scales to large-scale environments, (ii) pose estimation using dense matching rather than sparse local features to deal with weakly textured indoor scenes, and (iii) pose verification by virtual view synthesis that is robust to significant changes in viewpoint, scene layout, and occlusion. Second, we release a new dataset with reference 6DoF poses for large-scale indoor localization. Query photographs are captured by mobile phones at a different time than the reference 3D map, thus presenting a realistic indoor localization scenario. Third, we demonstrate that our method significantly outperforms current state-of-the-art indoor localization approaches on this new challenging data. Code and data are publicly available.

11 November 2022
Verified
Book Chapter
Closed access
PDF file
SZSiwei Zhang
Siwei Zhang
QMQianli Ma
Qianli Ma
YZYan Zhang
Yan Zhang
ZQZhiyin Qian
Zhiyin Qian
TKTaein Kwon
Taein Kwon
Siyu TangSiyu Tang
Siyu Tang

16 September 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
ATAkihiko Torii
Akihiko Torii
HTHajime Taira
Hajime Taira
JSJosef Sivic
Josef Sivic
MPMarc Pollefeys
Marc Pollefeys
MOMasatoshi Okutomi
Masatoshi Okutomi
TSTorsten Sattler
Torsten Sattler
Accurate visual localization is a key technology for autonomous navigation. 3D structure-based methods employ 3D models of the scene to estimate the full 6 degree-of-freedom (DOF) pose of a camera very accurately. However, constructing (and extending) large-scale 3D models is still a significant challenge. In contrast, 2D image retrieval-based methods only require a database of geo-tagged images, which is trivial to construct and to maintain. They are often considered inaccurate since they only approximate the positions of the cameras. Yet, the exact camera pose can theoretically be recovered when enough relevant database images are retrieved. In this paper, we demonstrate experimentally that large-scale 3D models are not strictly necessary for accurate visual localization. We create reference poses for a large and challenging urban dataset. Using these poses, we show that combining image-based methods with local reconstructions results in a pose accuracy similar to the state-of-the-art structure-based methods. Our results suggest that we might want to reconsider the current approach for accurate large-scale localization.