LightGlue: Local Feature Matching at Light Speed
By Philipp Lindenberger, Paul-Edouard Sarlin, Marc Pollefeys. IEEE International Conference on Computer Vision, 2023
1,084 citations recorded by the source corpus.
We introduce LightGlue, a deep neural network that learns to match local features across images. We revisit multiple design decisions of SuperGlue, the state of the art in sparse matching, and derive simple but effective improvements. Cumulatively, they make LightGlue more efficient – in terms of both memory and computation, more accurate, and much easier to train. One key property is that LightGlue is adaptive to the difficulty of the problem: the inference is much faster on image pairs that are intuitively easy to match, for example because of a larger visual overlap or limited appearance change. This opens up exciting prospects for deploying deep matchers in latency-sensitive applications like 3D reconstruction. The code and trained models are publicly available at github.com/cvg/LightGlue.
Subfields: Computational Mechanics, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/a6159daf277e73ca511da98a0d05432f6bab0de7
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mechanics
In Computer Vision and Pattern Recognition
- Yohann Cabon
- Vincent Leroy
- Jérôme Revaud
- Luc Van Gool
- Cordelia Schmid
- Andrea Vedaldi
- Ming-Hsuan Yang
- Andreas Geiger
Citations in the corpus
- CoTracker3: Simpler and Better Point Tracking by Pseudo-Labeling Real Videos (2025, neutral): “5, we have explored alternative point sampling methods, including LightGlue [20], Super-Point [5], and DISK [36].”
- VGGT: Visual Geometry Grounded Transformer (2025, neutral): “In recent years, deep learning has improved many components of the SfM pipeline, with keypoint detection [12, 19, 76, 102] and image matching [7, 46, 60, 66] being two primary areas of focus.”
- Grounding Image Matching in 3D with MASt3R (2024, methodology): “SuperGlue and similar approaches [51, 72] thus propose to perform global reasoning in the last pairing step leveraging stronger priors to guide matching, yet leaving the detection and description local.”
- RoMa: Robust Dense Feature Matching (2023, neutral): “Regression by Classification: Regression by classification [48, 57, 58] involves casting regression problems as classification by, e.g ., binning.”