🤖 AI Summary
To address the failure of conventional frame-based SLAM under the asynchronous, sparse output of event cameras, this paper proposes the first tightly coupled event-inertial SLAM framework. Our method introduces adaptive event window selection and event-driven motion-compensated imaging to generate grayscale intensity images suitable for direct visual odometry. Leveraging these images, we integrate IMU preintegration with event-stream-based bundle adjustment (BA) to achieve real-time 6-DoF pose estimation and dense scene reconstruction—without relying on conventional frames. We pioneer event-driven motion-compensated imaging and establish an end-to-end joint optimization pipeline for events and inertial measurements. Evaluated on two public event-camera datasets, our approach achieves trajectory accuracy closely aligned with ground truth, with localization performance matching or surpassing state-of-the-art methods.
📝 Abstract
Compared to regular cameras, Dynamic Vision Sensors or Event Cameras can output compact visual data based on a change in the intensity in each pixel location asynchronously. In this paper, we study the application of current image-based SLAM techniques to these novel sensors. To this end, the information in adaptively selected event windows is processed to form motion-compensated images. These images are then used to reconstruct the scene and estimate the 6-DOF pose of the camera. We also propose an inertial version of the event-only pipeline to assess its capabilities. We compare the results of different configurations of the proposed algorithm against the ground truth for sequences of two publicly available event datasets. We also compare the results of the proposed event-inertial pipeline with the state-of-the-art and show it can produce comparable or more accurate results provided the map estimate is reliable.