laurentkneip/opengv

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1126 stars · 363 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

computer-vision math simulation computer-vision robotics cpp python windows geometric-vision pose-estimation ransac calibrated-cameras matlab-interface algorithms linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="laurentkneip/opengv")