GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction
This addresses the challenge of consistent 3D reconstruction for SLAM applications, offering a versatile solution for monocular, stereo, and RGB-D inputs, but it appears incremental as it builds on existing neural implicit SLAM approaches.
The paper tackles the problem of error accumulation and distortion in neural implicit SLAM by proposing GO-SLAM, a framework that globally optimizes camera poses and 3D reconstruction in real-time, outperforming state-of-the-art methods in tracking robustness and reconstruction accuracy on synthetic and real-world datasets.
Neural implicit representations have recently demonstrated compelling results on dense Simultaneous Localization And Mapping (SLAM) but suffer from the accumulation of errors in camera tracking and distortion in the reconstruction. Purposely, we present GO-SLAM, a deep-learning-based dense visual SLAM framework globally optimizing poses and 3D reconstruction in real-time. Robust pose estimation is at its core, supported by efficient loop closing and online full bundle adjustment, which optimize per frame by utilizing the learned global geometry of the complete history of input frames. Simultaneously, we update the implicit and continuous surface representation on-the-fly to ensure global consistency of 3D reconstruction. Results on various synthetic and real-world datasets demonstrate that GO-SLAM outperforms state-of-the-art approaches at tracking robustness and reconstruction accuracy. Furthermore, GO-SLAM is versatile and can run with monocular, stereo, and RGB-D input.