no code implementations • NeurIPS 2021 • Farhad Ghazvinian Zanjani, Ilia Karmanov, Hanno Ackermann, Daniel Dijkman, Simone Merlin, Max Welling, Fatih Porikli
This work presents a data-driven approach for the indoor localization of an observer on a 2D topological map of the environment.
1 code implementation • 31 May 2021 • Ilia Karmanov, Farhad G. Zanjani, Simone Merlin, Ishaque Kadampot, Daniel Dijkman
Our second contribution is two weakly supervised losses that map this latent space into a Cartesian map, resulting in meter-accuracy position results.