ethan-li-coding/SemiGlobalMatching

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1197 stars · 229 forks observed · 2026-08-28

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

A complete, well-commented C++ implementation of the classic Semi-Global Matching (SGM) stereo matching algorithm for computing disparity and depth maps from stereo image pairs. It is accompanied by a tutorial blog series explaining each algorithm stage, with the core algorithm independent of any image library.

Use cases

• compute depth maps from stereo image pairs
• implement semi-global matching in C++
• learn how SGM stereo matching works step by step
• generate disparity maps for 3D reconstruction
• port a stereo matching algorithm to an embedded or robotics project
• benchmark SGM against other stereo algorithms

When to choose

• you need a readable, educational reference implementation of SGM
• you want a portable C++ stereo matching core with minimal dependencies
• you are learning stereo matching and want code paired with tutorials

When to avoid

• you need state-of-the-art deep-learning stereo matching accuracy
• you need GPU acceleration or a production-ready optimized pipeline out of the box
• you need active maintenance or cross-platform build support beyond Windows/Visual Studio

Facets

library · maturity maintenance

computer-vision image-processing machine-learning computer-vision image-processing robotics windows cpp cross-platform stereo-matching sgm depth-estimation disparity-map 3d-reconstruction census-transform opencv educational algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ethan-li-coding/SemiGlobalMatching")