# Toward Geometric Deep SLAM

arXiv: https://arxiv.org/abs/1707.07410 · HTML: https://mlsanity.com/paper/1707.07410/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2017.

## Built on by (most cited first, 30 of 38)

- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [OnePose: One-Shot Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2205.12257/) (2022)
- [Doppelgangers: Learning to Disambiguate Images of Similar Structures](https://mlsanity.com/paper/2309.02420/) (2023)
- [Self-Supervised Equivariant Learning for Oriented Keypoint Detection](https://mlsanity.com/paper/2204.08613/) (2022)
- [Learning Rotation-Equivariant Features for Visual Correspondence](https://mlsanity.com/paper/2303.15472/) (2023)
- [Are Local Features All You Need for Cross-Domain Visual Place Recognition?](https://mlsanity.com/paper/2304.05887/) (2023)
- [DFM: A Performance Baseline for Deep Feature Matching](https://mlsanity.com/paper/2106.07791/) (2021)
- [Advances in Inference and Representation for Simultaneous Localization and Mapping](https://mlsanity.com/paper/2103.05041/) (2021)
- [Overcoming Obstructions via Bandwidth-Limited Multi-Agent Spatial Handshaking](https://mlsanity.com/paper/2107.00771/) (2021)
- [Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints](https://mlsanity.com/paper/2303.02885/) (2023)
- [3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching](https://mlsanity.com/paper/2207.02375/) (2022)
- [Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results](https://mlsanity.com/paper/2212.06759/) (2022)
- [Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networks](https://mlsanity.com/paper/2104.07196/) (2021)
- [GeoFill: Reference-Based Image Inpainting with Better Geometric Understanding](https://mlsanity.com/paper/2201.08131/) (2022)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [A Light Touch Approach to Teaching Transformers Multi-view Geometry](https://mlsanity.com/paper/2211.15107/) (2022)
- [Handbook on Leveraging Lines for Two-View Relative Pose Estimation](https://mlsanity.com/paper/2309.16040/) (2023)
- [Effect of Parameter Optimization on Classical and Learning-based Image Matching Methods](https://mlsanity.com/paper/2108.08179/) (2021)
- [Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Framework](https://mlsanity.com/paper/2108.12159/) (2021)
- [AffineGlue: Joint Matching and Robust Estimation](https://mlsanity.com/paper/2307.15381/) (2023)
- [Occ2Net: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions](https://mlsanity.com/paper/2308.16160/) (2023)
- [SRPose: Two-view Relative Pose Estimation with Sparse Keypoints](https://mlsanity.com/paper/2407.08199/) (2024)
- [Sonar-based Deep Learning in Underwater Robotics: Overview, Robustness and Challenges](https://mlsanity.com/paper/2412.11840/) (2024)
- [MapGlue: Multimodal Remote Sensing Image Matching](https://mlsanity.com/paper/2503.16185/) (2025)
- [OpenGlue: Open Source Graph Neural Net Based Pipeline for Image Matching](https://mlsanity.com/paper/2204.08870/) (2022)
- [3DFill:Reference-guided Image Inpainting by Self-supervised 3D Image Alignment](https://mlsanity.com/paper/2211.04831/) (2022)
- [Learning Probabilistic Coordinate Fields for Robust Correspondences](https://mlsanity.com/paper/2306.04231/) (2023)
- [Minimal Solvers for Full DoF Motion Estimation from Asynchronous Tracks](https://mlsanity.com/paper/2508.17537/) (2025)
- [Learning and Crafting for the Wide Multiple Baseline Stereo](https://mlsanity.com/paper/2112.12027/) (2021)
- [Learning-Based Keypoint Registration for Fetoscopic Mosaicking](https://mlsanity.com/paper/2207.13185/) (2022)

## Abstract (arXiv)

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.