Pith. sign in

REVIEW 5 cited by

SuperGlue: Learning Feature Matching with Graph Neural Networks

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 1911.11763 v2 pith:IF4OBXMS submitted 2019-11-26 cs.CV

Paul-Edouard Sarlin , Daniel DeTone , Tomasz Malisiewicz , Andrew Rabinovich This is my paper
classification cs.CV
keywords superglueneuralassignmentsfeaturegraphjointlymatchingmodern
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. Assignments are estimated by solving a differentiable optimal transport problem, whose costs are predicted by a graph neural network. We introduce a flexible context aggregation mechanism based on attention, enabling SuperGlue to reason about the underlying 3D scene and feature assignments jointly. Compared to traditional, hand-designed heuristics, our technique learns priors over geometric transformations and regularities of the 3D world through end-to-end training from image pairs. SuperGlue outperforms other learned approaches and achieves state-of-the-art results on the task of pose estimation in challenging real-world indoor and outdoor environments. The proposed method performs matching in real-time on a modern GPU and can be readily integrated into modern SfM or SLAM systems. The code and trained weights are publicly available at https://github.com/magicleap/SuperGluePretrainedNetwork.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Rig3R: Rig-Aware Conditioning for Learned 3D Reconstruction

    cs.CV 2025-06 conditional novelty 7.0 of 10

    Rig3R conditions learned 3D reconstruction on optional rig metadata and predicts rig-relative raymaps, enabling state-of-the-art pose estimation and rig calibration discovery from images.

  2. KAMERA: Enhancing Aerial Surveys of Ice-associated Seals in Arctic Environments

    cs.CV 2025-09 conditional novelty 6.0 of 10

    KAMERA, an open-source multi-spectral aerial imaging system, synchronizes nine cameras and runs real-time detection, cutting survey processing time by up to 80%.

  3. Accelerating SfM-based Pose Estimation with Dominating Set

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Using a greedy dominating set on a graph of reference images speeds up SfM-based 6-DoF pose estimation by 1.5-14.5x with moderate accuracy loss.

  4. DreamSat-Pose: Spacecraft Pose Estimation from Single-View 3D Reconstructions and Learned 2D-3D Feature Matching

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A single RGB image of an unknown spacecraft, combined with a generated 3D proxy and learned 2D-3D matching, gives line-of-sight pointing accurate to ~0.16° but leaves rotation error around 59°.

  5. ZeroReg3D: A Zero-shot Registration Pipeline for 3D Consecutive Histopathology Image Reconstruction

    cs.CV 2025-06 conditional novelty 5.0 of 10

    ZeroReg3D is a zero-shot pipeline that pairs XFeat keypoint matching with affine and B-spline registration to align serial histology slices, outperforming tested baselines on kidney datasets.

Pith tools