1 code implementation • 8 May 2023 • Kunal Chelani, Torsten Sattler, Fredrik Kahl, Zuzana Kukelova
In this paper, we show that an attacker can learn about details of a scene without any access by simply querying a localization service.
1 code implementation • CVPR 2023 • Vojtech Panek, Zuzana Kukelova, Torsten Sattler
An interesting, and underexplored, source of data for building scene representations are 3D models that are readily available on the Internet, e. g., hand-drawn CAD models, 3D models generated from building footprints, or from aerial images.
no code implementations • 28 Mar 2023 • Charalambos Tzamos, Daniel Barath, Torsten Sattler, Zuzana Kukelova
Our solutions are based on the simple idea of generating one or two additional virtual point correspondences in two views by using the information from the locations of the four input correspondences in the three views.
no code implementations • 16 Jan 2023 • Snehal Bhayani, Janne Heikkilä, Zuzana Kukelova
Most state-of-the-art efficient polynomial solvers are based on the action matrix method that has been automated and highly optimized in recent years.
1 code implementation • CVPR 2023 • Kunal Chelani, Torsten Sattler, Fredrik Kahl, Zuzana Kukelova
In this paper, we show that an attacker can learn about details of a scene without any access by simply querying a localization service.
no code implementations • 29 Sep 2022 • Snehal Bhayani, Viktor Larsson, Torsten Sattler, Janne Heikkila, Zuzana Kukelova
In this paper we study the problem of estimating the semi-generalized pose of a partially calibrated camera, i. e., the pose of a perspective camera with unknown focal length w. r. t.
1 code implementation • 21 Jul 2022 • Vojtech Panek, Zuzana Kukelova, Torsten Sattler
In this work, we thus explore a more flexible alternative based on dense 3D meshes that does not require features matching between database images to build the scene representation.
no code implementations • 15 Mar 2022 • Daniel Barath, Zuzana Kukelova
This paper proposes the geometric relationship of epipolar geometry and orientation- and scale-covariant, e. g., SIFT, features.
no code implementations • CVPR 2022 • Yaqing Ding, Daniel Barath, Jian Yang, Zuzana Kukelova
In this paper, we propose a new minimal and a non-minimal solver for estimating the relative camera pose together with the unknown focal length of the second camera.
1 code implementation • ICCV 2021 • Snehal Bhayani, Torsten Sattler, Daniel Barath, Patrik Beliansky, Janne Heikkila, Zuzana Kukelova
In this paper, we propose the first minimal solutions for estimating the semi-generalized homography given a perspective and a generalized camera.
no code implementations • ICCV 2021 • Yaqing Ding, Daniel Barath, Zuzana Kukelova
When capturing panoramas, people tend to align their cameras with the vertical axis, i. e., the direction of gravity.
no code implementations • CVPR 2021 • Yaqing Ding, Daniel Barath, Jian Yang, Hui Kong, Zuzana Kukelova
Smartphones, tablets and camera systems used, e. g., in cars and UAVs, are typically equipped with IMUs (inertial measurement units) that can measure the gravity vector accurately.
1 code implementation • ICCV 2023 • Jonathan Ventura, Zuzana Kukelova, Torsten Sattler, Dániel Baráth
We introduce the first general solution to the problem of estimating the pose of a calibrated camera given a single observation of an oriented point and an affine correspondence.
1 code implementation • ECCV 2020 • Yukai Lin, Viktor Larsson, Marcel Geppert, Zuzana Kukelova, Marc Pollefeys, Torsten Sattler
In particular, our approach is more robust than the naive approach of first estimating intrinsic parameters and pose per camera before refining the extrinsic parameters of the system.
1 code implementation • ECCV 2020 • Daniel Barath, Michal Polic, Wolfgang Förstner, Torsten Sattler, Tomas Pajdla, Zuzana Kukelova
The main advantage of such solvers is that their sample size is smaller, e. g., only two instead of four matches are required to estimate a homography.
no code implementations • 17 Jul 2020 • Snehal Bhayani, Zuzana Kukelova, Janne Heikkilä
The existing state-of-the-art methods for solving such systems are either based on Gr\"obner bases and the action matrix method, which have been extensively studied and optimized in the recent years or recently proposed approach based on a sparse resultant computation using an extra variable.
no code implementations • CVPR 2020 • Cenek Albl, Zuzana Kukelova, Viktor Larsson, Tomas Pajdla, Konrad Schindler
Most consumer cameras are equipped with electronic rolling shutter, leading to image distortions when the camera moves during image capture.
no code implementations • ECCV 2020 • Zuzana Kukelova, Cenek Albl, Akihiro Sugimoto, Konrad Schindler, Tomas Pajdla
The internal geometry of most modern consumer cameras is not adequately described by the perspective projection.
1 code implementation • CVPR 2020 • Snehal Bhayani, Zuzana Kukelova, Janne Heikkilä
Our new method can be fully automatized and incorporated into existing tools for automatic generation of efficient polynomial solvers and as such it represents a competitive alternative to popular Gr\"obner basis methods for minimal problems in computer vision.
1 code implementation • 4 Nov 2019 • James Pritts, Zuzana Kukelova, Viktor Larsson, Yaroslava Lochman, Ondřej Chum
This paper introduces minimal solvers that jointly solve for radial lens undistortion and affine-rectification using local features extracted from the image of coplanar translated and reflected scene texture, which is common in man-made environments.
1 code implementation • 25 Jul 2019 • James Pritts, Zuzana Kukelova, Viktor Larsson, Yaroslava Lochman, Ondřej Chum
The proposed solvers use the affine invariant that coplanar repeats have the same scale in rectified space.
1 code implementation • ICCV 2019 • Daniel Barath, Zuzana Kukelova
Two new general constraints are derived on the scales and rotations which can be used in any geometric model estimation tasks.
no code implementations • CVPR 2019 • Zuzana Kukelova, Viktor Larsson
It is iterative in nature, yet in practice, it converges in no more than five iterations.
no code implementations • 30 Dec 2018 • Zuzana Kukelova, Cenek Albl, Akihiro Sugimoto, Tomas Pajdla
Our best 6-point solver, based on the new alternation technique, shows an identical or even better performance than the state-of-the-art R6P solver and is two orders of magnitude faster.
3 code implementations • 26 Jul 2018 • Filip Šrajer, Zuzana Kukelova, Andrew Fitzgibbon
However, it is important for the success of algorithmic differentiation that such `simple' objective functions are handled efficiently, as so many problems in computer vision and machine learning are of this form.
1 code implementation • 16 Jul 2018 • James Pritts, Zuzana Kukelova, Viktor Larsson, Ondrej Chum
This paper introduces the first minimal solvers that jointly estimate lens distortion and affine rectification from repetitions of rigidly transformed coplanar local features.
no code implementations • CVPR 2018 • Viktor Larsson, Magnus Oskarsson, Kalle Astrom, Alge Wallis, Zuzana Kukelova, Tomas Pajdla
In this paper we show how we can make polynomial solvers based on the action matrix method faster, by careful selection of the monomial bases.
no code implementations • CVPR 2018 • Viktor Larsson, Zuzana Kukelova, Yinqiang Zheng
To estimate the 6-DoF extrinsic pose of a pinhole camera with partially unknown intrinsic parameters is a critical sub-problem in structure-from-motion and camera localization.
no code implementations • 12 Mar 2018 • Viktor Larsson, Magnus Oskarsson, Kalle Åström, Alge Wallis, Zuzana Kukelova, Tomas Pajdla
In this paper we show how we can make polynomial solvers based on the action matrix method faster, by careful selection of the monomial bases.
1 code implementation • CVPR 2018 • James Pritts, Zuzana Kukelova, Viktor Larsson, Ondrej Chum
The solvers are derived from constraints induced by the conjugate translations of an imaged scene plane, which are integrated with the division model for radial lens distortion.
no code implementations • ICCV 2017 • Viktor Larsson, Zuzana Kukelova, Yinqiang Zheng
In this paper we present new techniques for constructing compact and robust minimal solvers for absolute pose estimation.
2 code implementations • CVPR 2017 • Cenek Albl, Zuzana Kukelova, Andrew Fitzgibbon, Jan Heller, Matej Smid, Tomas Pajdla
We present new methods for simultaneously estimating camera geometry and time shift from video sequences from multiple unsynchronized cameras.
no code implementations • CVPR 2017 • Zuzana Kukelova, Joe Kileel, Bernd Sturmfels, Tomas Pajdla
We present a new insight into the systematic generation of minimal solvers in computer vision, which leads to smaller and faster solvers.
no code implementations • 6 Oct 2016 • Joe Kileel, Zuzana Kukelova, Tomas Pajdla, Bernd Sturmfels
The distortion varieties of a given projective variety are parametrized by duplicating coordinates and multiplying them with monomials.
no code implementations • CVPR 2016 • Cenek Albl, Zuzana Kukelova, Tomas Pajdla
We compare our R5Pup to the state of the art RS and perspective methods and demonstrate that it outperforms them when vertical direction is known in the range of accuracy available on modern mobile devices.
no code implementations • CVPR 2016 • Zuzana Kukelova, Jan Heller, Andrew Fitzgibbon
In this paper, we present a new algorithm for finding all intersections of three quadrics.
no code implementations • ICCV 2015 • Zuzana Kukelova, Jan Heller, Martin Bujnak, Andrew Fitzgibbon, Tomas Pajdla
In this paper, we present a new efficient solution to this problem that uses 10 image correspondences.
no code implementations • CVPR 2015 • Zuzana Kukelova, Jan Heller, Martin Bujnak, Tomas Pajdla
The importance of precise homography estimation is often underestimated even though it plays a crucial role in various vision applications such as plane or planarity detection, scene degeneracy tests, camera motion classification, image stitching, and many more.
no code implementations • CVPR 2015 • Cenek Albl, Zuzana Kukelova, Tomas Pajdla
Therefore we can use the standard P3P algorithm to estimate camera orientation and to bring the camera rotation matrix close to the identity.