LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching
Ubingazhibov, Aidyn ; Pautrat, Rémi ; Suárez, Iago ; Liu, Shaohui ; Pollefeys, Marc and Larsson, Viktor LU
(2025)
- Abstract
- 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 simultane-ously 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... (More)
- 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 simultane-ously 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. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/ab8b5a7e-b958-4936-a914-9d6fa90f028c
- author
- Ubingazhibov, Aidyn
; Pautrat, Rémi
; Suárez, Iago
; Liu, Shaohui
; Pollefeys, Marc
and Larsson, Viktor
LU
- organization
- publishing date
- 2025
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
- publisher
- IEEE
- external identifiers
-
- scopus:105035155435
- ISBN
- 979-8-3315-8988-2
- DOI
- 10.1109/ICCVW69036.2025.00752
- language
- English
- LU publication?
- yes
- id
- ab8b5a7e-b958-4936-a914-9d6fa90f028c
- date added to LUP
- 2026-04-02 13:57:18
- date last changed
- 2026-05-21 14:13:49
@inproceedings{ab8b5a7e-b958-4936-a914-9d6fa90f028c,
abstract = {{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 simultane-ously 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.}},
author = {{Ubingazhibov, Aidyn and Pautrat, Rémi and Suárez, Iago and Liu, Shaohui and Pollefeys, Marc and Larsson, Viktor}},
booktitle = {{2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)}},
isbn = {{979-8-3315-8988-2}},
language = {{eng}},
publisher = {{IEEE}},
title = {{LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching}},
url = {{http://dx.doi.org/10.1109/ICCVW69036.2025.00752}},
doi = {{10.1109/ICCVW69036.2025.00752}},
year = {{2025}},
}