GSLAM: Initialization-robust Monocular Visual SLAM via Global Structure-from-Motion
This addresses robustness and speed issues in visual SLAM for robotics and AR/VR applications, though it is incremental as it builds on existing global SfM techniques.
The paper tackles the problem of monocular visual SLAM being sensitive to initialization errors and false loops by integrating global structure-from-motion, resulting in a method that is 4x faster and more robust than state-of-the-art systems.
Many monocular visual SLAM algorithms are derived from incremental structure-from-motion (SfM) methods. This work proposes a novel monocular SLAM method which integrates recent advances made in global SfM. In particular, we present two main contributions to visual SLAM. First, we solve the visual odometry problem by a novel rank-1 matrix factorization technique which is more robust to the errors in map initialization. Second, we adopt a recent global SfM method for the pose-graph optimization, which leads to a multi-stage linear formulation and enables L1 optimization for better robustness to false loops. The combination of these two approaches generates more robust reconstruction and is significantly faster (4X) than recent state-of-the-art SLAM systems. We also present a new dataset recorded with ground truth camera motion in a Vicon motion capture room, and compare our method to prior systems on it and established benchmark datasets.