# Stereo Visual Odometry with Deep Learning-Based Point and Line Feature Matching using an Attention Graph Neural Network

arXiv: https://arxiv.org/abs/2308.01125 · HTML: https://mlsanity.com/paper/2308.01125/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 2 Aug 2023.

## Builds on (most cited first, 17 of 17)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [LF-Net: Learning Local Features from Images](https://mlsanity.com/paper/1805.09662/) (2018)
- [SOLD2: Self-supervised Occlusion-aware Line Description and Detection](https://mlsanity.com/paper/2104.03362/) (2021)
- [Ford Multi-AV Seasonal Dataset](https://mlsanity.com/paper/2003.07969/) (2020)
- [Robust Visual SLAM with Point and Line Features](https://mlsanity.com/paper/1711.08654/) (2017)
- [Robust Line Segments Matching via Graph Convolution Networks](https://mlsanity.com/paper/2004.04993/) (2020)
- [On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods](https://mlsanity.com/paper/2007.10000/) (2020)
- [Improving Worst Case Visual Localization Coverage via Place-specific Sub-selection in Multi-camera Systems](https://mlsanity.com/paper/2206.13883/) (2022)
- [Leveraging Structural Information to Improve Point Line Visual-Inertial Odometry](https://mlsanity.com/paper/2105.04064/) (2021)
- [S-BEV: Semantic Birds-Eye View Representation for Weather and Lighting Invariant 3-DoF Localization](https://mlsanity.com/paper/2101.09569/) (2021)
- [A Review of Visual Odometry Methods and Its Applications for Autonomous Driving](https://mlsanity.com/paper/2009.09193/) (2020)

## Built on by (most cited first, 3 of 3)

- [Reconstructing 4D Spatial Intelligence: A Survey](https://mlsanity.com/paper/2507.21045/) (2025)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [OTPL-VIO: Robust Visual-Inertial Odometry with Optimal Transport Line Association and Adaptive Uncertainty](https://mlsanity.com/paper/2603.09653/) (2026)

## Abstract (arXiv)

Robust feature matching forms the backbone for most Visual Simultaneous Localization and Mapping (vSLAM), visual odometry, 3D reconstruction, and Structure from Motion (SfM) algorithms. However, recovering feature matches from texture-poor scenes is a major challenge and still remains an open area of research. In this paper, we present a Stereo Visual Odometry (StereoVO) technique based on point and line features which uses a novel feature-matching mechanism based on an Attention Graph Neural Network that is designed to perform well even under adverse weather conditions such as fog, haze, rain, and snow, and dynamic lighting conditions such as nighttime illumination and glare scenarios. We perform experiments on multiple real and synthetic datasets to validate the ability of our method to perform StereoVO under low visibility weather and lighting conditions through robust point and line matches. The results demonstrate that our method achieves more line feature matches than state-of-the-art line matching algorithms, which when complemented with point feature matches perform consistently well in adverse weather and dynamic lighting conditions.