Data-Efficient Collaborative Decentralized Thermal-Inertial Odometry

1 code implementation • 14 Sep 2022 • Vincenzo Polizzi, Robert Hewitt, Javier Hidalgo-Carrió, Jeff Delaune, Davide Scaramuzza

Our system back-end uses a covariance-intersection fusion strategy to neglect the cross-correlation between agents so as to lower memory usage and computational cost.

Event-aided Direct Sparse Odometry

no code implementations • CVPR 2022 • Javier Hidalgo-Carrió, Guillermo Gallego, Davide Scaramuzza

This opens the door to low-power motion-tracking applications where frames are sparingly triggered "on demand" and our method tracks the motion in between.

Monocular Visual Odometry

Learning Monocular Dense Depth from Events

1 code implementation • 16 Oct 2020 • Javier Hidalgo-Carrió, Daniel Gehrig, Davide Scaramuzza

Event cameras are novel sensors that output brightness changes in the form of a stream of asynchronous events instead of intensity frames.

Depth Estimation Depth Prediction +1

Video to Events: Recycling Video Datasets for Event Cameras

1 code implementation • CVPR 2020 • Daniel Gehrig, Mathias Gehrig, Javier Hidalgo-Carrió, Davide Scaramuzza

Event cameras are novel sensors that output brightness changes in the form of a stream of asynchronous "events" instead of intensity frames.

Object Recognition Semantic Segmentation