no code implementations • 27 Sep 2023 • Shengze Jin, Daniel Barath, Marc Pollefeys, Iro Armeni
Point cloud registration has seen recent success with several learning-based methods that focus on correspondence matching and, as such, optimize only for this objective.
no code implementations • 27 Sep 2023 • Petr Hruby, Shaohui Liu, Rémi Pautrat, Marc Pollefeys, Daniel Barath
We propose an approach for estimating the relative pose between calibrated image pairs by jointly exploiting points, lines, and their coincidences in a hybrid manner.
1 code implementation • 26 Sep 2023 • Yang Miao, Iro Armeni, Marc Pollefeys, Daniel Barath
We introduce an online 2D-to-3D semantic instance mapping algorithm aimed at generating comprehensive, accurate, and efficient semantic 3D maps suitable for autonomous agents in unstructured environments.
1 code implementation • ICCV 2023 • Rémi Pautrat, Shaohui Liu, Petr Hruby, Marc Pollefeys, Daniel Barath
We tackle the problem of estimating a Manhattan frame, i. e. three orthogonal vanishing points, and the unknown focal length of the camera, leveraging a prior vertical direction.
no code implementations • 28 Jul 2023 • Daniel Barath, Dmytro Mishkin, Luca Cavalli, Paul-Edouard Sarlin, Petr Hruby, Marc Pollefeys
Moreover, we derive a new minimal solver for homography estimation, requiring only a single affine correspondence (AC) and a gravity prior.
1 code implementation • 26 Jul 2023 • Luca Cavalli, Daniel Barath, Marc Pollefeys, Viktor Larsson
The proposed attention mechanism and one-step transformer provide an adaptive behavior that enhances the performance of RANSAC, making it a more effective tool for robust estimation.
no code implementations • 21 Jun 2023 • Shuzhe Wang, Juho Kannala, Daniel Barath
Direct matching of 2D keypoints in an input image to a 3D point cloud of the scene without requiring visual descriptors has garnered increased interest due to its lower memory requirements, inherent privacy preservation, and reduced need for expensive 3D model maintenance compared to visual descriptor-based methods.
1 code implementation • 28 Apr 2023 • Sayan Deb Sarkar, Ondrej Miksik, Marc Pollefeys, Daniel Barath, Iro Armeni
We propose SGAligner, the first method for aligning pairs of 3D scene graphs that is robust to in-the-wild scenarios (ie, unknown overlap -- if any -- and changes in the environment).
Ranked #1 on
Point Cloud Registration
on 3RScan
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 additional virtual point correspondence in two views by using the information from the locations of the four input correspondences in the three views.
1 code implementation • CVPR 2023 • Ganlin Zhang, Viktor Larsson, Daniel Barath
In this paper, we revisit the rotation averaging problem applied in global Structure-from-Motion pipelines.
2 code implementations • 20 Feb 2023 • Daniel Barath, Dmytro Mishkin, Michal Polic, Wolfgang Förstner, Jiri Matas
We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D.
no code implementations • ICCV 2023 • Sayan Deb Sarkar, Ondrej Miksik, Marc Pollefeys, Daniel Barath, Iro Armeni
We propose SGAligner, the first method for aligning pairs of 3D scene graphs that is robust to in-the-wild scenarios (i. e., unknown overlap - if any - and changes in the environment).
no code implementations • CVPR 2023 • Daniel Barath, Dmytro Mishkin, Michal Polic, Wolfgang Förstner, Jiri Matas
We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D.
no code implementations • ICCV 2023 • Levente Hajder, Lajos Lóczi, Daniel Barath
The proposed approach provides a new globally optimal solution for this over-determined problem and proves that it reduces to a linear system that can be solved extremely efficiently.
no code implementations • ICCV 2023 • Shuzhe Wang, Juho Kannala, Marc Pollefeys, Daniel Barath
We propose a new method, named curvature similarity extractor (CSE), for improving local feature matching across images.
2 code implementations • ICCV 2023 • Tong Wei, Yash Patel, Alexander Shekhovtsov, Jiri Matas, Daniel Barath
We propose $\nabla$-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline.
1 code implementation • CVPR 2023 • Rémi Pautrat, Daniel Barath, Viktor Larsson, Martin R. Oswald, Marc Pollefeys
Their learned counterparts are more repeatable and can handle challenging images, but at the cost of a lower accuracy and a bias towards wireframe lines.
1 code implementation • 16 Jul 2022 • Luca Cavalli, Marc Pollefeys, Daniel Barath
We tested NeFSAC on more than 100k image pairs from three publicly available real-world datasets and found that it leads to one order of magnitude speed-up, while often finding more accurate results than USAC alone.
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 • Daniel Barath, Luca Cavalli, Marc Pollefeys
We propose the Model Quality Network, MQ-Net in short, for predicting the quality, e. g. the pose error of essential matrices, of models generated inside RANSAC.
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 2023 • Tong Wei, Jiri Matas, Daniel Barath
We propose a new sampler for robust estimators that always selects the sample with the highest probability of consisting only of inliers.
1 code implementation • 24 Nov 2021 • Daniel Barath, Gabor Valasek
A new algorithm is proposed to accelerate RANSAC model quality calculations.
no code implementations • ICCV 2021 • Maksym Ivashechkin, Daniel Barath, Jiri Matas
Experiments on four standard datasets show that VSAC is significantly faster than all its predecessors and runs on average in 1-2 ms, on a CPU.
no code implementations • 11 Apr 2021 • Maksym Ivashechkin, Daniel Barath, Jiri Matas
We review the most recent RANSAC-like hypothesize-and-verify robust estimators.
1 code implementation • CVPR 2023 • Daniel Barath, Denys Rozumny, Ivan Eichhardt, Levente Hajder, Jiri Matas
Dominant instances are found via a RANSAC-like sampling and a consolidation process driven by a model quality function considering previously proposed instances.
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 • CVPR 2021 • Daniel Barath, Dmytro Mishkin, Ivan Eichhardt, Ilia Shipachev, Jiri Matas
We propose ways to speed up the initial pose-graph generation for global Structure-from-Motion algorithms.
no code implementations • 13 Aug 2020 • Istan Gergo Gal, Daniel Barath, Levente Hajder
For the first class of solvers, the sought plane is expected to be perpendicular to one of the camera axes.
no code implementations • ICCV 2021 • Banglei Guan, Ji Zhao, Daniel Barath, Friedrich Fraundorfer
We propose three novel solvers for estimating the relative pose of a multi-camera system from affine correspondences (ACs).
1 code implementation • ECCV 2020 • Ivan Eichhardt, Daniel Barath
We propose a new approach for combining deep-learned non-metric monocular depth with affine correspondences (ACs) to estimate the relative pose of two calibrated cameras from a single correspondence.
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.
1 code implementation • CVPR 2020 • Tomas Hodan, Daniel Barath, Jiri Matas
A data-dependent number of corresponding 3D locations is selected per pixel, and poses of possibly multiple object instances are estimated using a robust and efficient variant of the PnP-RANSAC algorithm.
no code implementations • 13 Dec 2019 • Levente Hajder, Daniel Barath
A new closed-form solver is proposed minimizing the algebraic error optimally, in the least-squares sense, to estimate the relative planar motion of two calibrated cameras.
no code implementations • 13 Dec 2019 • Levente Hajder, Daniel Barath
A new minimal solver is proposed for the semi-calibrated case, i. e. the camera parameters are known except a common focal length.
no code implementations • CVPR 2020 • Daniel Barath, Jana Noskova, Maksym Ivashechkin, Jiri Matas
A new method for robust estimation, MAGSAC++, is proposed.
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 • 5 Jun 2019 • Daniel Barath, Maksym Ivashechkin, Jiri Matas
We propose Progressive NAPSAC, P-NAPSAC in short, which merges the advantages of local and global sampling by drawing samples from gradually growing neighborhoods.
2 code implementations • ICCV 2019 • Daniel Barath, Jiri Matas
The Progressive-X algorithm, Prog-X in short, is proposed for geometric multi-model fitting.
1 code implementation • 1 May 2019 • Ivan Eichhardt, Daniel Barath
The technique requires the epipolar geometry to be pre-estimated between each image pair.
1 code implementation • 10 Jul 2018 • Daniel Barath
An approach is proposed for recovering affine correspondences (ACs) from orientation- and scale-invariant, e. g. SIFT, features.
2 code implementations • CVPR 2019 • Daniel Barath, Jana Noskova, Jiri Matas
A method called, sigma-consensus, is proposed to eliminate the need for a user-defined inlier-outlier threshold in RANSAC.
no code implementations • CVPR 2018 • Daniel Barath
We aim at estimating the fundamental matrix in two views from five correspondences of rotation invariant features obtained by e. g.\ the SIFT detector.
no code implementations • CVPR 2017 • Daniel Barath, Tekla Toth, Levente Hajder
To select the best one out of the remaining candidates, a root selection technique is proposed outperforming the recent ones especially in case of high-level noise.
1 code implementation • CVPR 2018 • Daniel Barath, Jiri Matas
A novel method for robust estimation, called Graph-Cut RANSAC, GC-RANSAC in short, is introduced.
1 code implementation • ECCV 2018 • Daniel Barath, Jiri Matas
The move replaces a set of labels with the corresponding density mode in the model parameter domain, thus achieving fast and robust optimization.