Visual localization made easy with hloc

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

🤗 image matching webui

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

A clean and concise Python implementation of SIFT (Scale-Invariant Feature Transform)

Wrapper of 50+ image matching models with a unified interface

KISS-Matcher: Fast, Robust, and Scalable Registration + ROS2 SLAM examples

ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO

[CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation

slamplay is a collection of powerful tools to start playing and experimenting with SLAM in C++

[CVPR 2020, Oral] MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask

SuperPoint and SuperGlue with TensorRT. Deploy with C++.

UFM: A Unified Dense Image Correspondence Estimator for both Optical Flow & Wide Baseline Matching Tasks. Matches any pair of images. (NeurIPS 2025)

Patch2Pix: Epipolar-Guided Pixel-Level Correspondences [CVPR2021]

MambaGlue: Fast and Robust Local Feature Matching With Mamba @ ICRA'25

A framework for building high-performance real-time multiple object trackers

[ICCV 2025, Highlight] BUFFER-X: Zero-Shot Point Cloud Registration