CP-SLAM: Collaborative Neural Point-based SLAM System
This work addresses SLAM for robotics or AR/VR applications, but it appears incremental as it builds on existing neural SLAM methods with new modules and optimization.
The paper tackles the problem of collaborative simultaneous localization and mapping (SLAM) by proposing a neural point-based system with front-end and back-end modules, achieving improved camera tracking and mapping accuracy as demonstrated on various datasets.
This paper presents a collaborative implicit neural simultaneous localization and mapping (SLAM) system with RGB-D image sequences, which consists of complete front-end and back-end modules including odometry, loop detection, sub-map fusion, and global refinement. In order to enable all these modules in a unified framework, we propose a novel neural point based 3D scene representation in which each point maintains a learnable neural feature for scene encoding and is associated with a certain keyframe. Moreover, a distributed-to-centralized learning strategy is proposed for the collaborative implicit SLAM to improve consistency and cooperation. A novel global optimization framework is also proposed to improve the system accuracy like traditional bundle adjustment. Experiments on various datasets demonstrate the superiority of the proposed method in both camera tracking and mapping.