# Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization

arXiv: https://arxiv.org/abs/2109.04753 · HTML: https://mlsanity.com/paper/2109.04753/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 10 Sep 2021.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [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)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Visual Transformers: Token-based Image Representation and Processing for Computer Vision](https://mlsanity.com/paper/2006.03677/) (2020)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [R2D2: Repeatable and Reliable Detector and Descriptor](https://mlsanity.com/paper/1906.06195/) (2019)
- [Non-Local Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2007.10042/) (2020)
- [Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking](https://mlsanity.com/paper/1803.11285/) (2018)
- [Learning with Average Precision: Training Image Retrieval with a Listwise Loss](https://mlsanity.com/paper/1906.07589/) (2019)
- [The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset](https://mlsanity.com/paper/1909.01300/) (2019)
- [PL-SLAM: a Stereo SLAM System through the Combination of Points and Line Segments](https://mlsanity.com/paper/1705.09479/) (2017)
- [SOLD2: Self-supervised Occlusion-aware Line Description and Detection](https://mlsanity.com/paper/2104.03362/) (2021)
- [CvxPnPL: A Unified Convex Solution to the Absolute Pose Estimation Problem from Point and Line Correspondences](https://mlsanity.com/paper/1907.10545/) (2019)

## Built on by (most cited first, 14 of 14)

- [MatchFormer: Interleaving Attention in Transformers for Feature Matching](https://mlsanity.com/paper/2203.09645/) (2022)
- [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023)
- [3D Line Mapping Revisited](https://mlsanity.com/paper/2303.17504/) (2023)
- [Fully Geometric Panoramic Localization](https://mlsanity.com/paper/2403.19904/) (2024)
- [A Comprehensive Review of Image Line Segment Detection and Description: Taxonomies, Comparisons, and Challenges](https://mlsanity.com/paper/2305.00264/) (2023)
- [Handbook on Leveraging Lines for Two-View Relative Pose Estimation](https://mlsanity.com/paper/2309.16040/) (2023)
- [LDL: Line Distance Functions for Panoramic Localization](https://mlsanity.com/paper/2308.13989/) (2023)
- [Representing 3D sparse map points and lines for camera relocalization](https://mlsanity.com/paper/2402.18011/) (2024)
- [LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching](https://mlsanity.com/paper/2510.16438/) (2025)
- [EVOLIN Benchmark: Evaluation of Line Detection and Association](https://mlsanity.com/paper/2303.05162/) (2023)
- [Camera Agnostic Two-Head Network for Ego-Lane Inference](https://mlsanity.com/paper/2404.12770/) (2024)
- [TP3M: Transformer-based Pseudo 3D Image Matching with Reference Image](https://mlsanity.com/paper/2405.08434/) (2024)
- [Improved 3D Point-Line Mapping Regression for Camera Relocalization](https://mlsanity.com/paper/2502.20814/) (2025)
- [Unified and Efficient Point-Line Local Features](https://mlsanity.com/paper/2608.19894/) (2026)

## Abstract (arXiv)

Along with feature points for image matching, line features provide additional constraints to solve visual geometric problems in robotics and computer vision (CV). Although recent convolutional neural network (CNN)-based line descriptors are promising for viewpoint changes or dynamic environments, we claim that the CNN architecture has innate disadvantages to abstract variable line length into the fixed-dimensional descriptor. In this paper, we effectively introduce Line-Transformers dealing with variable lines. Inspired by natural language processing (NLP) tasks where sentences can be understood and abstracted well in neural nets, we view a line segment as a sentence that contains points (words). By attending to well-describable points on aline dynamically, our descriptor performs excellently on variable line length. We also propose line signature networks sharing the line's geometric attributes to neighborhoods. Performing as group descriptors, the networks enhance line descriptors by understanding lines' relative geometries. Finally, we present the proposed line descriptor and matching in a Point and Line Localization (PL-Loc). We show that the visual localization with feature points can be improved using our line features. We validate the proposed method for homography estimation and visual localization.