Alternatives and similar repositories for LightGlue

Users that are interested in LightGlue are comparing it to the libraries listed below

• verlab / accelerated_features
  Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!
  ☆1,518Updated last year
• zju3dv / LoFTR
  Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022
  ☆2,781Updated last year
• Vincentqyw / image-matching-webui
  🤗 image matching webui
  ☆1,195Updated last week
• cvg / glue-factory
  Training library for local feature detection and matching
  ☆1,034Updated 2 months ago
• magicleap / SuperGluePretrainedNetwork
  SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
  ☆3,925Updated last year
• rpautrat / SuperPoint
  Efficient neural feature detector and descriptor
  ☆2,347Updated 8 months ago
• YvanYin / Metric3D
  The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foun…
  ☆2,078Updated 10 months ago
• zju3dv / EfficientLoFTR
  Code for "Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed", CVPR 2024
  ☆943Updated 5 months ago
• Parskatt / RoMa
  [CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and rel…
  ☆1,123Updated this week
• google-research / omniglue
  Code release for CVPR'24 submission 'OmniGlue'
  ☆694Updated last year
• qianqianwang68 / omnimotion
  ☆2,260Updated last year
• naver / mast3r
  Grounding Image Matching in 3D with MASt3R
  ☆2,698Updated 6 months ago
• prs-eth / Marigold
  [CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
  ☆3,061Updated last month
• siyuanliii / masa
  Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything
  ☆1,361Updated 8 months ago
• hkchengrex / Tracking-Anything-with-DEVA
  [ICCV 2023] Tracking Anything with Decoupled Video Segmentation
  ☆1,477Updated 8 months ago
• zju3dv / MatchAnything
  Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.
  ☆1,201Updated 3 weeks ago
• autonomousvision / unimatch
  [TPAMI'23] Unifying Flow, Stereo and Depth Estimation
  ☆1,338Updated last year
• cvg / Hierarchical-Localization
  Visual localization made easy with hloc
  ☆3,907Updated last month
• facebookresearch / silk
  SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.
  ☆676Updated last week
• NVlabs / FoundationStereo
  [CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching
  ☆2,463Updated last month
• google-deepmind / tapnet
  Tracking Any Point (TAP)
  ☆1,778Updated 3 months ago
• isl-org / ZoeDepth
  Metric depth estimation from a single image
  ☆2,774Updated 8 months ago
• cvg / GlueStick
  Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)
  ☆644Updated 9 months ago
• magicleap / SuperPointPretrainedNetwork
  PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)
  ☆2,135Updated 3 years ago
• facebookresearch / co-tracker
  CoTracker is a model for tracking any point (pixel) on a video.
  ☆4,783Updated last year
• cvg / DeepLSD
  Implementation of the paper "DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients"
  ☆602Updated last year
• fabio-sim / LightGlue-ONNX
  ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO
  ☆565Updated this week
• UX-Decoder / Semantic-SAM
  [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"
  ☆2,803Updated 6 months ago
• princeton-vl / DROID-SLAM
  ☆2,402Updated 8 months ago
• princeton-vl / RAFT
  ☆3,918Updated 5 months ago