Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

AERO-VIS: Asynchronous Event-based Real-time Onboard Visual-Inertial SLAM

About

The robustness of event cameras to high dynamic range and motion blur holds the potential to improve visual odometry systems in challenging environments. Although their high temporal resolution does not require synchronous processing, most event-based odometry methods still run at fixed rates, which simplifies system design but restricts latency and throughput. In this work, we present AERO-VIS, a stereo event-inertial SLAM system with an integrated, data-driven, robust, and performance-optimized keypoint detector. By processing the event stream asynchronously, the system dynamically adapts to downstream runtime demands, ensuring low-latency and real-time performance. When deploying AERO-VIS on a UAV, we achieve unprecedented accuracy in onboard event-based SLAM. These unique characteristics enable us to present the first purely event-based inertial SLAM system that demonstrates closed-loop UAV control and large-scale state estimation while relying solely on onboard compute. A video of the experiments and the source code are available at ethz-mrl.github.io/AERO-VIS.

Yannick Burkhardt, Sebasti\'an Barbas Laina, Simon Boche, Leonard Frei{\ss}muth, Stefan Leutenegger• 2026

Related benchmarks

TaskDatasetResultRank
Trajectory Estimationrpg-stereo bin
RMS ATE (cm)0.56
6
Trajectory Estimationrpg-stereo boxes2
RMS ATE (cm)1.6
6
Trajectory Estimationrpg-stereo desk2
RMS ATE (cm)0.81
6
Trajectory Estimationrpg-stereo monitor2
RMS ATE (cm)0.6
6
Trajectory Estimationrpg-stereo
RMS ATE (cm)0.83
6
Trajectory EstimationTUM-VIE 1d-trans
RMS ATE (cm)0.34
5
Trajectory EstimationTUM-VIE 3d-trans
RMS ATE (cm)0.65
5
Trajectory EstimationTUM-VIE 6dof
RMS ATE (cm)0.0038
5
Trajectory EstimationTUM-VIE desk
RMS ATE (cm)0.36
5
Trajectory EstimationTUM-VIE (desk2)
RMS ATE (cm)0.31
5
Showing 10 of 18 rows

Other info

Follow for update