Abstract: Hybrid visual odometry methods achieve state-of-the-art performance by fusing both data-based deep learning networks and model-based localization approaches. However, these methods also ...

Abstract: Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution, offering the potential to handle state ...

This repository contains the code implementation for the paper "ROEVO: Robust Organized Edge Feature-based Visual Odometry Using RGB-D Cameras". It presents a visual odometry system entirely based on ...

Certainly! Here's the revised description with all links and additional text removed: --- Unlock the hidden power of visual ...

LIR-LIVO is a novel lidar-inertial-visual odometry system designed to deliver efficient and robust state estimation in challenging environments with degraded LiDAR signals and significant illumination ...