#82 · Primary category: Computer Vision
openMVG
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
Project last updated:12/17/25
GitHub Stars
6.5K
Forks
1.7K
Contributors
129
License
MPL-2.0
Why we included this project
openMVG is a C++ library that recovers camera poses and a 3D point cloud from overlapping photos, with no requirement that your images arrive in any particular order. Its pipeline covers feature detection and matching, camera models, robust estimation, and the structure-from-motion stage itself, then exports results to other multi-view stereo tools for dense point clouds or textured meshes. That makes it a practical base for photogrammetry, drone mapping, and any project that needs to turn unordered imagery into geometry. The code is deliberately readable and ships with samples plus a test-driven build, so teams can pull individual modules into their own systems instead of committing to a black box. It builds for Android, iOS, Linux, macOS, and Windows, which matters when the reconstruction has to run on mobile or embedded targets.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)