1 code implementation • ICCV 2023 • Dror Aiger, André Araujo, Simon Lynen
In this paper, we take a step back from this assumption and propose Constrained Approximate Nearest Neighbors (CANN), a joint solution of k-nearest-neighbors across both the geometry and appearance space using only local features.
1 code implementation • NeurIPS 2023 • Paul-Edouard Sarlin, Eduard Trulls, Marc Pollefeys, Jan Hosang, Simon Lynen
Semantic 2D maps are commonly used by humans and machines for navigation purposes, whether it's walking or driving.
no code implementations • ICCV 2021 • Dror Aiger, Simon Lynen, Jan Hosang, Bernhard Zeisl
Outlier rejection and equivalently inlier set optimization is a key ingredient in numerous applications in computer vision such as filtering point-matches in camera pose estimation or plane and normal estimation in point clouds.
no code implementations • 10 Dec 2019 • Grzegorz Kurzejamski, Jacek Komorowski, Lukasz Dabala, Konrad Czarnota, Simon Lynen, Tomasz Trzcinski
In this paper, we present a framework for computing dense keypoint correspondences between images under strong scene appearance changes.
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.
no code implementations • 28 Sep 2018 • Tomasz Trzcinski, Jacek Komorowski, Lukasz Dabala, Konrad Czarnota, Grzegorz Kurzejamski, Simon Lynen
Numerous computer vision applications rely on local feature descriptors, such as SIFT, SURF or FREAK, for image matching.
no code implementations • 28 Sep 2018 • Jacek Komorowski, Konrad Czarnota, Tomasz Trzcinski, Lukasz Dabala, Simon Lynen
In the recent years, a number of novel, deep-learning based, interest point detectors, such as LIFT, DELF, Superpoint or LF-Net was proposed.
no code implementations • 12 Jul 2018 • Marcin Dymczyk, Igor Gilitschenski, Juan Nieto, Simon Lynen, Bernhard Zeisl, Roland Siegwart
We propose LandmarkBoost - an approach that, in contrast to the conventional 2D-3D matching methods, casts the search problem as a landmark classification task.
1 code implementation • 28 Nov 2017 • Thomas Schneider, Marcin Dymczyk, Marius Fehr, Kevin Egger, Simon Lynen, Igor Gilitschenski, Roland Siegwart
On the other hand, maplab provides the research community with a collection of multisession mapping tools that include map merging, visual-inertial batch optimization, and loop closure.
Robotics