Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion

TL;DR

This paper introduces a novel multi-event-camera depth estimation method that fuses disparity information without explicit data association, achieving state-of-the-art results in 3D reconstruction for event-based stereo SLAM.

Contribution

It develops a fusion-based approach for depth estimation from event cameras that bypasses explicit data association, enhancing accuracy and efficiency.

Findings

Achieves state-of-the-art 3D reconstruction accuracy

Outperforms four baseline methods on multiple datasets

Demonstrates robustness across various event camera configurations

Abstract

Event cameras are bio-inspired sensors that offer advantages over traditional cameras. They operate asynchronously, sampling the scene at microsecond resolution and producing a stream of brightness changes. This unconventional output has sparked novel computer vision methods to unlock the camera's potential. Here, the problem of event-based stereo 3D reconstruction for SLAM is considered. Most event-based stereo methods attempt to exploit the high temporal resolution of the camera and the simultaneity of events across cameras to establish matches and estimate depth. By contrast, this work investigates how to estimate depth without explicit data association by fusing Disparity Space Images (DSIs) originated in efficient monocular methods. Fusion theory is developed and applied to design multi-camera 3D reconstruction algorithms that produce state-of-the-art results, as confirmed by comparisons with four baseline methods and tests on a variety of available datasets.