# Global Pose Estimation with an Attention-based Recurrent Network

arXiv: https://arxiv.org/abs/1802.06857 · HTML: https://mlsanity.com/paper/1802.06857/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2018.

## Built on by (most cited first, 10 of 10)

- [SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition](https://mlsanity.com/paper/2102.11603/) (2021)
- [LIFT-SLAM: a deep-learning feature-based monocular visual SLAM method](https://mlsanity.com/paper/2104.00099/) (2021)
- [Visual SLAM: What are the Current Trends and What to Expect?](https://mlsanity.com/paper/2210.10491/) (2022)
- [Unsupervised Joint Learning of Depth, Optical Flow, Ego-motion from Video](https://mlsanity.com/paper/2105.14520/) (2021)
- [Light-SLAM: A Robust Deep-Learning Visual SLAM System Based on LightGlue under Challenging Lighting Conditions](https://mlsanity.com/paper/2407.02382/) (2024)
- [A comparative evaluation of learned feature descriptors on hybrid monocular visual SLAM methods](https://mlsanity.com/paper/2104.00085/) (2021)
- [Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimation](https://mlsanity.com/paper/2208.08892/) (2022)
- [FindView: Precise Target View Localization Task for Look Around Agents](https://mlsanity.com/paper/2303.09054/) (2023)
- [An Attention-Based Deep Learning Architecture for Real-Time Monocular Visual Odometry: Applications to GPS-free Drone Navigation](https://mlsanity.com/paper/2404.17745/) (2024)
- [NeuroLoc: Encoding Navigation Cells for 6-DOF Camera Localization](https://mlsanity.com/paper/2505.01113/) (2025)

## Abstract (arXiv)

The ability for an agent to localize itself within an environment is crucial for many real-world applications. For unknown environments, Simultaneous Localization and Mapping (SLAM) enables incremental and concurrent building of and localizing within a map. We present a new, differentiable architecture, Neural Graph Optimizer, progressing towards a complete neural network solution for SLAM by designing a system composed of a local pose estimation model, a novel pose selection module, and a novel graph optimization process. The entire architecture is trained in an end-to-end fashion, enabling the network to automatically learn domain-specific features relevant to the visual odometry and avoid the involved process of feature engineering. We demonstrate the effectiveness of our system on a simulated 2D maze and the 3D ViZ-Doom environment.