1 code implementation • ECCV 2020 • Luca Cavalli, Viktor Larsson, Martin Ralf Oswald, Torsten Sattler, Marc Pollefeys
As a result, outlier detection is a fundamental problem in computer vision and a wide range of approaches, from simple checks based on descriptor similarity to geometric verification, have been proposed over the last decades.
no code implementations • 16 Apr 2024 • Gabriele Trivigno, Carlo Masone, Barbara Caputo, Torsten Sattler
This involves training an implicit scene representation or learning features while optimizing a camera pose-based loss.
1 code implementation • 16 Apr 2024 • Zehao Yu, Torsten Sattler, Andreas Geiger
Recently, 3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results, while allowing the rendering of high-resolution images in real-time.
no code implementations • 2 Dec 2023 • Aikaterini Adam, Konstantinos Karantzalos, Lazaros Grammatikopoulos, Torsten Sattler
Through scene comparison over time, information about objects in the scene and their changes is inferred.
1 code implementation • 27 Nov 2023 • Zehao Yu, Anpei Chen, Binbin Huang, Torsten Sattler, Andreas Geiger
Recently, 3D Gaussian Splatting has demonstrated impressive novel view synthesis results, reaching high fidelity and efficiency.
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 • ICCV 2023 • Jonas Kulhanek, Torsten Sattler
A popular scene representation used by NeRFs is to combine a uniform, voxel-based subdivision of the scene with an MLP.
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 • CVPR 2023 • Maxime Pietrantoni, Martin Humenberger, Torsten Sattler, Gabriela Csurka
Inspired by properties of semantic segmentation, in this paper we investigate how to leverage robust image segmentation in the context of privacy-preserving visual localization.
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.
no code implementations • 21 Aug 2022 • Aikaterini Adam, Torsten Sattler, Konstantinos Karantzalos, Tomas Pajdla
AR/VR applications and robots need to know when the scene has changed.
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.
1 code implementation • 1 Jun 2022 • Zehao Yu, Songyou Peng, Michael Niemeyer, Torsten Sattler, Andreas Geiger
Motivated by recent advances in the area of monocular geometry prediction, we systematically explore the utility these cues provide for improving neural implicit surface reconstruction.
1 code implementation • 31 May 2022 • Martin Humenberger, Yohann Cabon, Noé Pion, Philippe Weinzaepfel, Donghwan Lee, Nicolas Guérin, Torsten Sattler, Gabriela Csurka
In order to investigate the consequences for visual localization, this paper focuses on understanding the role of image retrieval for multiple visual localization paradigms.
no code implementations • 5 May 2022 • Vladimir Guzov, Julian Chibane, Riccardo Marin, Yannan He, Yunus Saracoglu, Torsten Sattler, Gerard Pons-Moll
In order for widespread adoption of such emerging applications, the sensor setup used to capture the interactions needs to be inexpensive and easy-to-use for non-expert users.
1 code implementation • CVPR 2022 • Gabriele Berton, Riccardo Mereu, Gabriele Trivigno, Carlo Masone, Gabriela Csurka, Torsten Sattler, Barbara Caputo
In this paper, we propose a new open-source benchmarking framework for Visual Geo-localization (VG) that allows to build, train, and test a wide range of commonly used architectures, with the flexibility to change individual components of a geo-localization pipeline.
1 code implementation • 18 Mar 2022 • Jonáš Kulhánek, Erik Derner, Torsten Sattler, Robert Babuška
We propose a 2D-only method that maps multiple context views and a query pose to a new image in a single pass of a neural network.
no code implementations • ICCV 2021 • Ara Jafarzadeh, Manuel Lopez Antequera, Pau Gargallo, Yubin Kuang, Carl Toft, Fredrik Kahl, Torsten Sattler
Visual localization is the problem of estimating the position and orientation from which a given image (or a sequence of images) is taken in a known scene.
1 code implementation • ICCV 2021 • Eric Brachmann, Martin Humenberger, Carsten Rother, Torsten Sattler
This begs the question whether the choice of the reference algorithm favours a certain family of re-localisation methods.
1 code implementation • CVPR 2021 • Vladimir Guzov, Aymen Mir, Torsten Sattler, Gerard Pons-Moll
We introduce (HPS) Human POSEitioning System, a method to recover the full 3D pose of a human registered with a 3D scan of the surrounding environment using wearable sensors.
2 code implementations • CVPR 2021 • Paul-Edouard Sarlin, Ajaykumar Unagar, Måns Larsson, Hugo Germain, Carl Toft, Viktor Larsson, Marc Pollefeys, Vincent Lepetit, Lars Hammarstrand, Fredrik Kahl, Torsten Sattler
In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms.
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.
1 code implementation • CVPR 2021 • Kunal Chelani, Fredrik Kahl, Torsten Sattler
To address the resulting potential privacy risks for user-generated content, it was recently proposed to lift point clouds to line clouds by replacing 3D points by randomly oriented 3D lines passing through these points.
1 code implementation • CVPR 2021 • Qunjie Zhou, Torsten Sattler, Laura Leal-Taixe
In this work, we propose a new perspective to estimate correspondences in a detect-to-refine manner, where we first predict patch-level match proposals and then refine them.
1 code implementation • 24 Nov 2020 • Noé Pion, Martin Humenberger, Gabriela Csurka, Yohann Cabon, Torsten Sattler
This paper focuses on understanding the role of image retrieval for multiple visual localization tasks.
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 • 21 Aug 2020 • Carl Toft, Daniyar Turmukhambetov, Torsten Sattler, Fredrik Kahl, Gabriel Brostow
Good local features improve the robustness of many 3D re-localization and multi-view reconstruction pipelines.
1 code implementation • ECCV 2020 • Johanna Wald, Torsten Sattler, Stuart Golodetz, Tommaso Cavallari, Federico Tombari
In this paper, we adapt 3RScan - a recently introduced indoor RGB-D dataset designed for object instance re-localization - to create RIO10, a new long-term camera re-localization benchmark focused on indoor scenes.
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.
3 code implementations • 7 Jun 2020 • Luca Cavalli, Viktor Larsson, Martin Ralf Oswald, Torsten Sattler, Marc Pollefeys
Local feature matching is a critical component of many computer vision pipelines, including among others Structure-from-Motion, SLAM, and Visual Localization.
1 code implementation • 11 May 2020 • Zichao Zhang, Torsten Sattler, Davide Scaramuzza
Visual Localization is one of the key enabling technologies for autonomous driving and augmented reality.
1 code implementation • 10 Feb 2020 • Peidong Liu, Joel Janai, Marc Pollefeys, Torsten Sattler, Andreas Geiger
Motion blurry images challenge many computer vision algorithms, e. g, feature detection, motion estimation, or object recognition.
2 code implementations • 5 Dec 2019 • Thomas Schöps, Viktor Larsson, Marc Pollefeys, Torsten Sattler
In contrast, generic camera models allow for very accurate calibration due to their flexibility.
1 code implementation • 18 Aug 2019 • Måns Larsson, Erik Stenborg, Carl Toft, Lars Hammarstrand, Torsten Sattler, Fredrik Kahl
In this paper, we propose a new neural network, the Fine-Grained Segmentation Network (FGSN), that can be used to provide image segmentations with a larger number of labels and can be trained in a self-supervised fashion.
no code implementations • ICCV 2019 • Hajime Taira, Ignacio Rocco, Jiri Sedlar, Masatoshi Okutomi, Josef Sivic, Tomas Pajdla, Torsten Sattler, Akihiko Torii
The pose with the largest geometric consistency with the query image, e. g., in the form of an inlier count, is then selected in a second stage.
1 code implementation • 4 Aug 2019 • Qunjie Zhou, Torsten Sattler, Marc Pollefeys, Laura Leal-Taixe
Using a classical feature-based approach within this framework, we show state-of-the-art performance.
no code implementations • 30 Jun 2019 • Simon Lynen, Bernhard Zeisl, Dror Aiger, Michael Bosse, Joel Hesch, Marc Pollefeys, Roland Siegwart, Torsten Sattler
Our approach spans from offline model building to real-time client-side pose fusion.
4 code implementations • 9 May 2019 • Mihai Dusmanu, Ignacio Rocco, Tomas Pajdla, Marc Pollefeys, Josef Sivic, Akihiko Torii, Torsten Sattler
In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions.
Ranked #8 on Image Matching on IMC PhotoTourism
1 code implementation • CVPR 2019 • Torsten Sattler, Qunjie Zhou, Marc Pollefeys, Laura Leal-Taixe
We furthermore use our model to show that pose regression is more closely related to pose approximation via image retrieval than to accurate pose estimation via 3D structure.
1 code implementation • 16 Mar 2019 • Måns Larsson, Erik Stenborg, Lars Hammarstrand, Torsten Sattler, Mark Pollefeys, Fredrik Kahl
We show that adding the correspondences as extra supervision during training improves the segmentation performance of the convolutional neural network, making it more robust to seasonal changes and weather conditions.
5 code implementations • 4 Mar 2019 • Antoni Rosinol, Torsten Sattler, Marc Pollefeys, Luca Carlone
We propose instead to tightly couple mesh regularization and state estimation by detecting and enforcing structural regularities in a novel factor-graph formulation.
no code implementations • 13 Jan 2019 • Andrin Jenal, Nikolay Savinov, Torsten Sattler, Gaurav Chaurasia
Through quantitative and perceptual experiments, we show that our model outperforms previous work and that our dataset is a valuable benchmark for generative models.
4 code implementations • 19 Oct 2018 • Iaroslav Melekhov, Aleksei Tiulpin, Torsten Sattler, Marc Pollefeys, Esa Rahtu, Juho Kannala
This paper addresses the challenge of dense pixel correspondence estimation between two images.
Ranked #2 on Dense Pixel Correspondence Estimation on HPatches
Dense Pixel Correspondence Estimation Optical Flow Estimation +1
1 code implementation • 1 Oct 2018 • Thomas Schöps, Torsten Sattler, Marc Pollefeys
In contrast to most existing approaches, we do not fuse depth measurements in a volume but in a dense surfel cloud.
1 code implementation • 26 Sep 2018 • Asha Anoosheh, Torsten Sattler, Radu Timofte, Marc Pollefeys, Luc van Gool
We then compare the daytime and translated night images to obtain a pose estimate for the night image using the known 6-DOF position of the closest day image.
no code implementations • 17 Sep 2018 • Marcel Geppert, Peidong Liu, Zhaopeng Cui, Marc Pollefeys, Torsten Sattler
This results in a system that provides reliable and drift-less pose estimations for high speed autonomous driving.
Robotics
no code implementations • ECCV 2018 • Carl Toft, Erik Stenborg, Lars Hammarstrand, Lucas Brynte, Marc Pollefeys, Torsten Sattler, Fredrik Kahl
Robust and accurate visual localization across large appearance variations due to changes in time of day, seasons, or changes of the environment is a challenging problem which is of importance to application areas such as navigation of autonomous robots.
no code implementations • CVPR 2019 • Federico Camposeco, Andrea Cohen, Marc Pollefeys, Torsten Sattler
Besides outperforming previous compression techniques in terms of pose accuracy under the same memory constraints, our compression scheme itself is also more efficient.
no code implementations • CVPR 2018 • Federico Camposeco, Andrea Cohen, Marc Pollefeys, Torsten Sattler
A number of these new hybrid minimal solvers are also presented in this paper.
1 code implementation • CVPR 2018 • Hajime Taira, Masatoshi Okutomi, Torsten Sattler, Mircea Cimpoi, Marc Pollefeys, Josef Sivic, Tomas Pajdla, 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.
no code implementations • CVPR 2018 • Johannes L. Schönberger, Marc Pollefeys, Andreas Geiger, Torsten Sattler
Robust visual localization under a wide range of viewing conditions is a fundamental problem in computer vision.
1 code implementation • 31 Aug 2017 • Christian Häne, Lionel Heng, Gim Hee Lee, Friedrich Fraundorfer, Paul Furgale, Torsten Sattler, Marc Pollefeys
To minimize the number of cameras needed for surround perception, we utilize fisheye cameras.
2 code implementations • CVPR 2018 • Torsten Sattler, Will Maddern, Carl Toft, Akihiko Torii, Lars Hammarstrand, Erik Stenborg, Daniel Safari, Masatoshi Okutomi, Marc Pollefeys, Josef Sivic, Fredrik Kahl, Tomas Pajdla
Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds.
no code implementations • CVPR 2017 • Torsten Sattler, Akihiko Torii, Josef Sivic, Marc Pollefeys, Hajime Taira, Masatoshi Okutomi, Tomas Pajdla
3D structure-based methods employ 3D models of the scene to estimate the full 6DOF pose of a camera very accurately.
no code implementations • CVPR 2017 • Federico Camposeco, Torsten Sattler, Andrea Cohen, Andreas Geiger, Marc Pollefeys
Adding the knowledge of direction of triangulation, we are able to approximate the position of the camera from two matches alone.
1 code implementation • Conference on Computer Vision and Pattern Recognition 2017 • Johannes L. Sch¨onberger, Hans Hardmeier, Torsten Sattler, Marc Pollefeys
In terms of matching performance, we evaluate the different descriptors regarding standard criteria. However, considering matching performance in isolation only provides an incomplete measure of a descriptor’s quality.
no code implementations • CVPR 2017 • Thomas Schops, Johannes L. Schonberger, Silvano Galliani, Torsten Sattler, Konrad Schindler, Marc Pollefeys, Andreas Geiger
Motivated by the limitations of existing multi-view stereo benchmarks, we present a novel dataset for this task.
no code implementations • ICCV 2017 • Maros Blaha, Mathias Rothermel, Martin R. Oswald, Torsten Sattler, Audrey Richard, Jan D. Wegner, Marc Pollefeys, Konrad Schindler
We present a method to jointly refine the geometry and semantic segmentation of 3D surface meshes.
no code implementations • ICCV 2017 • Florian Walch, Caner Hazirbas, Laura Leal-Taixé, Torsten Sattler, Sebastian Hilsenbeck, Daniel Cremers
In this work we propose a new CNN+LSTM architecture for camera pose regression for indoor and outdoor scenes.
no code implementations • CVPR 2017 • Nikolay Savinov, Akihito Seki, Lubor Ladicky, Torsten Sattler, Marc Pollefeys
In this paper, we ask a fundamental question: can we learn such detectors from scratch?
1 code implementation • CVPR 2016 • Torsten Sattler, Michal Havlena, Konrad Schindler, Marc Pollefeys
Visual location recognition is the task of determining the place depicted in a query image from a given database of geo-tagged images.
no code implementations • ICCV 2015 • Chris Sweeney, Torsten Sattler, Tobias Hollerer, Matthew Turk, Marc Pollefeys
The viewing graph represents a set of views that are related by pairwise relative geometries.
no code implementations • ICCV 2015 • Andrea Cohen, Torsten Sattler, Marc Pollefeys
An important variant of this problem is the case in which individual sides of a building can be reconstructed but not joined due to the missing visual overlap.
no code implementations • ICCV 2015 • Federico Camposeco, Torsten Sattler, Marc Pollefeys
As a second step, we obtain the calibration by finding the translation of the camera center using an ordering constraint.
no code implementations • ICCV 2015 • Bernhard Zeisl, Torsten Sattler, Marc Pollefeys
Image-based localization approaches aim to determine the camera pose from which an image was taken.