Pith. sign in

REVIEW 5 cited by

LightGlue: Local Feature Matching at Light Speed

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.13643 v1 pith:AY7GH6MX submitted 2023-06-23 cs.CV

Philipp Lindenberger , Paul-Edouard Sarlin , Marc Pollefeys This is my paper · ORCID
classification cs.CV
keywords lightgluedeeplocalmatchmatchingmuchaccurateacross
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 https://github.com/cvg/LightGlue.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 12 citations worldwide. Full citation record

  1. SkyEV: RGB-Event UAV detection and tracking dataset and baseline

    cs.CV 2026-07 conditional novelty 6.0 of 10

    The paper introduces SkyEV, a 2.17-hour RGB-event drone detection dataset with ego-motion and varied optics, plus a SAST+YOLOX fusion baseline.

  2. Glob3R: Global Structure-from-Motion with 3D Foundation Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A frozen Pi3X backbone plus dense warping tracks and keyframe sliding-window global optimization yields more accurate, scalable SfM than feed-forward or classical baselines alone.

  3. MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MUVOD provides multi-view video panoptic masks for 17 dynamic scenes (459 instances, 73 categories) and benchmarks for multi-view video and 3D object segmentation.

  4. Black-box Adversarial Attacks on CNN-based SLAM Algorithms

    cs.RO 2025-05 conditional novelty 6.0 of 10

    Black-box FGSM/PGD perturbations transferred from ImageNet classifiers disrupt GCN-SLAM tracking, causing up to 76% untracked frames on TUM.

  5. Hybrid Deep Learning for Traceability and Classification of Industrial Slate Tiles

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Hybrid XFeat+LightGlue matching and MobileNetV3 fusion improves slate-tile instance re-identification by +15.4% AUC and quarry classification by +10.9% accuracy on a new 2610-image industrial dataset.

Pith tools