Training Deep SLAM on Single Frames
This addresses the data scarcity issue for researchers and practitioners in robotics and autonomous systems, though it is incremental as it builds on existing unsupervised and synthetic data approaches.
The authors tackled the problem of expensive ground truth pose collection for training deep visual odometry and SLAM methods by generating synthetic optical flow data from depth maps, enabling unsupervised training. They achieved state-of-the-art results among unsupervised methods on the KITTI dataset and promising results on EuRoC.
Learning-based visual odometry and SLAM methods demonstrate a steady improvement over past years. However, collecting ground truth poses to train these methods is difficult and expensive. This could be resolved by training in an unsupervised mode, but there is still a large gap between performance of unsupervised and supervised methods. In this work, we focus on generating synthetic data for deep learning-based visual odometry and SLAM methods that take optical flow as an input. We produce training data in a form of optical flow that corresponds to arbitrary camera movement between a real frame and a virtual frame. For synthesizing data we use depth maps either produced by a depth sensor or estimated from stereo pair. We train visual odometry model on synthetic data and do not use ground truth poses hence this model can be considered unsupervised. Also it can be classified as monocular as we do not use depth maps on inference. We also propose a simple way to convert any visual odometry model into a SLAM method based on frame matching and graph optimization. We demonstrate that both the synthetically-trained visual odometry model and the proposed SLAM method build upon this model yields state-of-the-art results among unsupervised methods on KITTI dataset and shows promising results on a challenging EuRoC dataset.