MBA-SLAM: A Novel AI Framework for Robust Dense Visual RGB-D SLAM, Implementing both an Implicit Radiance Fields Version and an Explicit Gaussian Splatting Version

SLAM (Simultaneous Localization and Mapping) is one of the important techniques used in robotics and computer vision. It helps machines understand where they are and create a map of their surroundings. Motion-blurred images face difficulties in dense visual SLAM systems for two reasons: 1) Inaccurate pose estimation during tracking: Current photo-realistic dense visual SLAM algorithms […]

The post .