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.
2 code implementations • ICCV 2023 • Philipp Lindenberger, Paul-Edouard Sarlin, Marc Pollefeys
We introduce LightGlue, a deep neural network that learns to match local features across images.
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 • CVPR 2023 • Paul-Edouard Sarlin, Daniel DeTone, Tsun-Yi Yang, Armen Avetisyan, Julian Straub, Tomasz Malisiewicz, Samuel Rota Bulo, Richard Newcombe, Peter Kontschieder, Vasileios Balntas
We bridge this gap by introducing OrienterNet, the first deep neural network that can localize an image with sub-meter accuracy using the same 2D semantic maps that humans use.
no code implementations • 19 Oct 2022 • Paul-Edouard Sarlin, Mihai Dusmanu, Johannes L. Schönberger, Pablo Speciale, Lukas Gruber, Viktor Larsson, Ondrej Miksik, Marc Pollefeys
To close this gap, we introduce LaMAR, a new benchmark with a comprehensive capture and GT pipeline that co-registers realistic trajectories and sensor streams captured by heterogeneous AR devices in large, unconstrained scenes.
1 code implementation • ICCV 2021 • Philipp Lindenberger, Paul-Edouard Sarlin, Viktor Larsson, Marc Pollefeys
Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction.
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.
18 code implementations • CVPR 2020 • Paul-Edouard Sarlin, Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich
This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points.
Ranked #2 on Visual Place Recognition on Berlin Kudamm
1 code implementation • 5 Apr 2019 • Hermann Blum, Paul-Edouard Sarlin, Juan Nieto, Roland Siegwart, Cesar Cadena
Deep learning has enabled impressive progress in the accuracy of semantic segmentation.
Ranked #13 on Anomaly Detection on Fishyscapes L&F (using extra training data)
3 code implementations • CVPR 2019 • Paul-Edouard Sarlin, Cesar Cadena, Roland Siegwart, Marcin Dymczyk
In this paper we propose HF-Net, a hierarchical localization approach based on a monolithic CNN that simultaneously predicts local features and global descriptors for accurate 6-DoF localization.
Ranked #3 on Visual Place Recognition on Berlin Kudamm
1 code implementation • 4 Sep 2018 • Paul-Edouard Sarlin, Frédéric Debraine, Marcin Dymczyk, Roland Siegwart, Cesar Cadena
Many robotics applications require precise pose estimates despite operating in large and changing environments.