cvg/Hierarchical-Localization

Visual localization made easy with hloc

56
/ 100
Established

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.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

3,989

Forks

732

Language

Python

License

Apache-2.0

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.