# ethan-li-coding/SemiGlobalMatching

SGM，立体匹配StereoMatching最经典应用最广泛算法，4000+引用，兼顾效率和效果。完整实现，代码规范，注释清晰，博客教学！

Repository: https://github.com/ethan-li-coding/SemiGlobalMatching
Canonical: https://ross.abutalabs.com/products/semiglobalmatching
Homepage: https://github.com/ethan-li-coding/SemiGlobalMatching
Language: C++
License: MIT
License Family: permissive
Topics: sgm, semiglobalmatching, census, stereo, semi-global-matching, stereo-matching, depth-estimation, 3d-reconstruction, semi-global
Last push: 2021-04-20T06:28:06+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2352, "days_push": 1961, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1197, forks 229 (observed 2026-08-28T04:03:57.404386+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning
- domain: computer-vision, image-processing, robotics
- platform: windows, cpp, cross-platform
- tags: stereo-matching, sgm, depth-estimation, disparity-map, 3d-reconstruction, census-transform, opencv, educational, algorithms

## Member repositories
- ethan-li-coding/SemiGlobalMatching (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:57.404386+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 2026-08-30T06:21:26.852105+00:00, confidence not recorded.
  - readme: https://github.com/ethan-li-coding/SemiGlobalMatching (fetched 2026-08-28T04:03:57.404386+00:00, sha bd6e3cd2fac6)
  - homepage: https://github.com/ethan-li-coding/SemiGlobalMatching (fetched 2026-08-29T12:28:38.614318+00:00, sha c371aa42979c)
- Data as of 2026-08-30T08:39:29.467469+00:00.