Toward Geometric Deep SLAM
arXiv:1707.07410
Abstract
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.
References in corpus (5)
Cited by in corpus (12)
- Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters
- A Survey of Simultaneous Localization and Mapping with an Envision in 6G Wireless Networks
- Flash Photography for Data-Driven Hidden Scene Recovery
- Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar
- Image Based Camera Localization: an Overview
- Trustable and Automated Machine Learning Running with Blockchain and Its Applications
- Deep Spectral Correspondence for Matching Disparate Image Pairs
- On Machine Learning and Structure for Mobile Robots
- Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networks
- Advances in Inference and Representation for Simultaneous Localization and Mapping
- Enhancing Multi-Robot Perception via Learned Data Association
- Matching Disparate Image Pairs Using Shape-Aware ConvNets