Real-Time Dense 3D Mapping of Underwater Environments
It addresses obstacle avoidance and path planning for underwater operations in domains like environmental monitoring and archaeology, but is incremental as it builds on existing VIO and reconstruction methods.
This paper tackles real-time dense 3D mapping for autonomous underwater vehicles in challenging conditions like limited visibility and no GPS, achieving comparable reconstruction quality to the offline state-of-the-art method COLMAP at high frame rates on a single CPU.
This paper addresses real-time dense 3D reconstruction for a resource-constrained Autonomous Underwater Vehicle (AUV). Underwater vision-guided operations are among the most challenging as they combine 3D motion in the presence of external forces, limited visibility, and absence of global positioning. Obstacle avoidance and effective path planning require online dense reconstructions of the environment. Autonomous operation is central to environmental monitoring, marine archaeology, resource utilization, and underwater cave exploration. To address this problem, we propose to use SVIn2, a robust VIO method, together with a real-time 3D reconstruction pipeline. We provide extensive evaluation on four challenging underwater datasets. Our pipeline produces comparable reconstruction with that of COLMAP, the state-of-the-art offline 3D reconstruction method, at high frame rates on a single CPU.