Search Results for author: Patrik Schmuck

Found 2 papers, 1 papers with code

COVINS: Visual-Inertial SLAM for Centralized Collaboration

1 code implementation12 Aug 2021 Patrik Schmuck, Thomas Ziegler, Marco Karrer, Jonathan Perraudin, Margarita Chli

Collaborative SLAM enables a group of agents to simultaneously co-localize and jointly map an environment, thus paving the way to wide-ranging applications of multi-robot perception and multi-user AR experiences by eliminating the need for external infrastructure or pre-built maps.

Learning Deep Descriptors With Scale-Aware Triplet Networks

no code implementations CVPR 2018 Michel Keller, Zetao Chen, Fabiola Maffra, Patrik Schmuck, Margarita Chli

Research on learning suitable feature descriptors for Computer Vision has recently shifted to deep learning where the biggest challenge lies with the formulation of appropriate loss functions, especially since the descriptors to be learned are not known at training time.

Cannot find the paper you are looking for? You can Submit a new open access paper.