Pith. sign in

REVIEW 5 cited by

LightGlue: Local Feature Matching at Light Speed

Not yet reviewed by Pith; the record is open.

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

LightGlue: Local Feature Matching at Light Speed

classification cs.CV
keywords lightgluedeeplocalmatchmatchingmuchaccurateacross
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
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)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features

    cs.CV 2025-10 unverdicted novelty 7.0

    FastForward represents scenes as collections of 3D-anchored image features and performs camera pose estimation via feed-forward correspondence prediction, achieving competitive accuracy with minimal mapping time.

  2. Zero-Parameter Geometric Gating for Temporally Stable Low-Altitude UAV Video Semantic Segmentation

    cs.CV 2026-06 unverdicted novelty 6.0

    A RANSAC-based geometric gate routes regions to homography or optical flow warping before SSP fusion, improving mIoU by 4.24-4.91% on synthetic UAVid with only 211K added parameters to frozen backbones.

  3. Long-tail Internet photo reconstruction

    cs.CV 2026-04 unverdicted novelty 6.0

    Finetuning 3D foundation models on simulated sparse subsets from MegaDepth-X produces robust reconstructions from extremely sparse, noisy internet photos while preserving performance on dense benchmarks.

  4. Leveraging AV1 motion vectors for Fast and Dense Feature Matching

    cs.CV 2025-10 unverdicted novelty 6.0

    AV1 motion vectors filtered by cosine consistency yield dense sub-pixel correspondences that support structure-from-motion on short video clips with lower CPU cost and higher match density than sequential SIFT.

  5. PairWise Image Finder: An Open-source Tool for Finding Visually Aligned Street-Level Image Pairs for Urban Perception Studies

    cs.CV 2026-06 unverdicted novelty 4.0

    PairWise is an open-source tool that finds visually aligned street-level image pairs by integrating feature matching with semantic segmentation mask alignment and outputs quantitative alignment metrics for filtering.