# laurentkneip/opengv

OpenGV is a collection of computer vision methods for solving geometric vision problems. It is hosted and maintained by the Mobile Perception Lab of ShanghaiTech.

Repository: https://github.com/laurentkneip/opengv
Canonical: https://ross.abutalabs.com/products/opengv
Language: C++
License: NOASSERTION
License Family: other
Last push: 2023-06-07T18:14:14+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4771, "days_push": 1183, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1126, forks 363 (observed 2026-08-28T04:03:41.236024+00:00)

## What it is
OpenGV is a C++ library of computer vision methods for solving geometric vision problems such as absolute-pose, relative-pose, triangulation, and point-cloud alignment for calibrated central and non-central cameras. It supports RANSAC and nonlinear optimization contexts, with Matlab and Python interfaces.

## Use cases
- estimate camera pose from 2D-3D correspondences
- compute relative pose between two calibrated camera views
- triangulate 3D points from multiple views
- align point clouds from calibrated cameras
- solve geometric vision problems with non-central camera rigs
- robustly estimate geometry using RANSAC

## When to choose
- you need calibrated geometric vision algorithms in C++
- you work with central or non-central multi-camera systems
- you need Matlab or Python bindings for geometric vision
- you are doing visual SLAM or structure-from-motion research

## When to avoid
- you need uncalibrated vision or feature detection/tracking
- you want a high-level computer vision toolkit like OpenCV
- you need GPU-accelerated vision pipelines
- you require an actively developed project with frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, math, simulation
- domain: computer-vision, robotics
- platform: cpp, python, windows
- tags: geometric-vision, pose-estimation, ransac, calibrated-cameras, matlab-interface, algorithms, linux, macos

## Member repositories
- laurentkneip/opengv (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:41.236024+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:39:12.348186+00:00, confidence not recorded.
  - readme: https://github.com/laurentkneip/opengv (fetched 2026-08-28T04:03:41.236024+00:00, sha 4c751b578457)
- Data as of 2026-08-30T08:39:29.467469+00:00.