I. Introduction
Simultaneous localization and mapping (SLAM) is a critical component in the mobile robotics field, which enables robots to estimate their position in an unknown environment and generate a map of the surroundings. Depending on the robot’s sensors, SLAM can be classified into two categories: visual SLAM based on vision cameras and laser SLAM based on LiDAR. Visual SLAM is a popular research area in computer vision and robotics, and its accuracy in localizing and mapping has a significant impact on various applications such as autonomous navigation of mobile robots, augmented reality (AR), virtual reality (VR), and autonomous driving [1], [2], [3], [4], [5], [6].