Toward Geometric Deep SLAM
This work addresses SLAM for robotics and AR/VR by offering a fast, lean system that reduces reliance on expensive ground truth data, though it is incremental as it builds on deep learning methods for geometric tasks.
The authors tackled the problem of point tracking in SLAM by introducing MagicPoint for detecting salient 2D points and MagicWarp for estimating homographies without descriptors, achieving a system that runs at 30+ FPS on a single CPU.
We present a point tracking system powered by two deep convolutional neural networks. The first network, MagicPoint, operates on single images and extracts salient 2D points. The extracted points are "SLAM-ready" because they are by design isolated and well-distributed throughout the image. We compare this network against classical point detectors and discover a significant performance gap in the presence of image noise. As transformation estimation is more simple when the detected points are geometrically stable, we designed a second network, MagicWarp, which operates on pairs of point images (outputs of MagicPoint), and estimates the homography that relates the inputs. This transformation engine differs from traditional approaches because it does not use local point descriptors, only point locations. Both networks are trained with simple synthetic data, alleviating the requirement of expensive external camera ground truthing and advanced graphics rendering pipelines. The system is fast and lean, easily running 30+ FPS on a single CPU.