LaMAR: Benchmarking Localization and Mapping for Augmented Reality

Autor: Paul-Edouard Sarlin, Mihai Dusmanu, Johannes L. Schönberger, Pablo Speciale, Lukas Gruber, Viktor Larsson, Ondrej Miksik, Marc Pollefeys

Publikováno v: Lecture Notes in Computer Science ISBN: 9783031200700

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::3ce54be70323d18880eb9601b24fdfdb
https://doi.org/10.1007/978-3-031-20071-7_40

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose

Autor: Hugo Germain, Torsten Sattler, Fredrik Kahl, Paul-Edouard Sarlin, Vincent Lepetit, Marc Pollefeys, Viktor Larsson, Ajaykumar Unagar, Lars Hammarstrand, Måns Larsson, Carl Toft

Publikováno v: CVPR
Conference on Computer Vision and Pattern Recognition
Conference on Computer Vision and Pattern Recognition, 2021, Online, United States
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms. Many regress precise geometric quantities, like poses or 3D points, from an input image. This either fails to generalize to new viewpoints

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22b78e02039e0f35d7f53b3be98d1f3a

Fishyscapes: A Benchmark for Safe Semantic Segmentation in Autonomous Driving

Autor: Juan Nieto, Roland Siegwart, Paul-Edouard Sarlin, Cesar Cadena, Hermann Blum

Publikováno v: ICCV Workshops

Deep learning has enabled impressive progress in the accuracy of semantic segmentation. Yet, the ability to estimate uncertainty and detect anomalies is key for safety-critical applications like autonomous driving. Existing uncertainty estimates have

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::10ac2ad3a013e7b965f875ca134ea8d2
https://doi.org/10.1109/iccvw.2019.00294

From Coarse to Fine: Robust Hierarchical Localization at Large Scale

Autor: Cesar Cadena, Paul-Edouard Sarlin, Marcin Dymczyk, Roland Siegwart

Publikováno v: CVPR

Robust and accurate visual localization is a fundamental capability for numerous applications, such as autonomous driving, mobile robotics, or augmented reality. It remains, however, a challenging task, particularly for large-scale environments and i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ce88eef7260d59aaa75707b1811a64b0
https://hdl.handle.net/20.500.11850/318867

The Evolution of Distributed Systems for Graph Neural Networks and Their Origin in Graph Processing and Deep Learning: A Survey.

Autor: VATTER, JANA¹ jana.vatter@tum.de, MAYER, RUBEN² ruben.mayer@uni-bayreuth.de, JACOBSEN, HANS-ARNO³ jacobsen@eecg.toronto.edu

Publikováno v: ACM Computing Surveys. Jan2024, Vol. 56 Issue 1, p1-37. 37p.