cvg/Hierarchical-Localization
Visual localization made easy with hloc
Implements a two-stage hierarchical pipeline combining image retrieval for coarse candidate selection with learned feature matching (SuperPoint, DISK, D2-Net) and geometric verification for precise 6-DoF localization. Integrates pluggable matchers including SuperGlue, LightGlue, and LoFTR, plus retrieval methods like NetVLAD and AP-GeM, enabling modular experimentation and SfM reconstruction with COLMAP for building 3D reference models from unordered image collections.
3,989 stars.
Stars
3,989
Forks
732
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/cvg/Hierarchical-Localization"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
isl-org/Open3D
Open3D: A Modern Library for 3D Data Processing
andyzeng/3dmatch-toolbox
3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.
Vincentqyw/image-matching-webui
🤗 image matching webui
gmberton/CosPlace
Official code for CVPR 2022 paper "Rethinking Visual Geo-localization for Large-Scale Applications"
cvg/glue-factory
Training library for local feature detection and matching