mlsanityData to 14 Oct 2026

LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching

arXiv 2510.16438 ↗First posted 18 Oct 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Lines and points are complementary local features, whose combination has proven effective for applications such as SLAM and Structure-from-Motion. The backbone of these pipelines are the local feature matchers, establishing correspondences across images. Traditionally, point and line matching have been treated as independent tasks. Recently, GlueStick proposed a GNN-based network that simultaneously operates on points and lines to establish matches. While running a single joint matching reduced the overall computational complexity, the heavy architecture prevented real-time applications or deployment to edge devices. Inspired by recent progress in point matching, we propose LightGlueStick, a lightweight matcher for points and line segments. The key novel component in our architecture is the Attentional Line Message Passing (ALMP), which explicitly exposes the connectivity of the lines to the network, allowing for efficient communication between nodes. In thorough experiments we show that LightGlueStick establishes a new state-of-the-art across different benchmarks. The code is available at https://github.com/aubingazhib/LightGlueStick.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 51 of its 90 references that are in the map. First posted on arXiv 18 Oct 2025.

Builds on

51 of 90 references.

References · 51

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  5. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  6. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  7. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  8. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  9. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  10. 2016Training Deep Nets with Sublinear Memory Costcited by 848
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  12. 2023LightGlue: Local Feature Matching at Light Speedcited by 590
38 more
  1. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  2. 2020DISK: Learning local features with policy gradientcited by 312
  3. 2016LIFT: Learned Invariant Feature Transformcited by 306
  4. 2023RoMa: Robust Dense Feature Matchingcited by 302
  5. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 264
  6. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  7. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 207
  8. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 191
  9. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
  10. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 177
  11. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 171
  12. 2018LF-Net: Learning Local Features from Imagescited by 151
  13. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  14. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  15. 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 121
  16. 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
  17. 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
  18. 2021Learnable Fourier Features for Multi-Dimensional Spatial Positional Encodingcited by 93
  19. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  20. 2019ContextDesc: Local Descriptor Augmentation with Cross-Modality Contextcited by 79
  21. 2021ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extractioncited by 77
  22. 2023GlueStick: Robust Image Matching by Sticking Points and Lines Togethercited by 66
  23. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 63
  24. 2022ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matchingcited by 62
  25. 2017PL-SLAM: a Stereo SLAM System through the Combination of Points and Line Segmentscited by 59
  26. 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidancecited by 56
  27. 2023SiLK -- Simple Learned Keypointscited by 54
  28. 2021SOLD2: Self-supervised Occlusion-aware Line Description and Detectioncited by 47
  29. 2025MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Trainingcited by 41
  30. 20233D Line Mapping Revisitedcited by 39
  31. 2024Robust Incremental Structure-from-Motion with Hybrid Featurescited by 31
  32. 2017Robust Visual SLAM with Point and Line Featurescited by 23
  33. 2021UV-SLAM: Unconstrained Line-based SLAM Using Vanishing Points for Structural Mappingcited by 23
  34. 2020PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Featurescited by 15
  35. 2023A Large Scale Homography Benchmarkcited by 15
  36. 2021Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localizationcited by 14
  37. 2019CvxPnPL: A Unified Convex Solution to the Absolute Pose Estimation Problem from Point and Line Correspondencescited by 12
  38. 2023Handbook on Leveraging Lines for Two-View Relative Pose Estimationcited by 6

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Unified and Efficient Point-Line Local Featurescited by 0
  2. 2026Stable and Scalable Bundle Adjustment of Holistic 3D Structurescited by 0