# MIT-SPARK/TEASER-plusplus

A fast and robust point cloud registration library

Repository: https://github.com/MIT-SPARK/TEASER-plusplus
Canonical: https://ross.abutalabs.com/products/teaser-plusplus
Language: C++
License: MIT
License Family: permissive
Topics: point-clouds, robotics, optimization, 3d-registration, 3d-reconstruction, slam
Last push: 2025-12-09T15:55:47+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 56, release rhythm 8, longevity 100
- inputs: {"age_days": 2416, "days_push": 267, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2337, forks 414 (observed 2026-08-28T04:06:38.062481+00:00)

## What it is
TEASER++ is a fast and certifiably-robust C++ library for rigid body point cloud registration in 3D, with Python and MATLAB bindings. It estimates transformations between point clouds even when input correspondences contain an extremely large number of outliers.

## Use cases
- register two 3D point clouds robustly
- align point clouds with many outlier correspondences
- estimate rigid body transformation between 3D scans
- build SLAM or 3D reconstruction pipelines
- find inlier correspondences between 3D feature matches
- use certifiably optimal registration from Python or MATLAB

## When to choose
- you need robust 3D registration under extreme outlier rates
- you want a fast, certifiably-optimal registration algorithm with C++/Python/MATLAB APIs
- you are building SLAM, mapping, or 3D reconstruction systems

## When to avoid
- you need 2D image registration rather than 3D point clouds
- you need a full SLAM system rather than a registration component
- you cannot build C++ dependencies or use Eigen/Boost

## Facets
- artifact type: library
- maturity: stable
- function: computer-vision, math
- domain: robotics, computer-vision
- platform: cpp, python, windows, cross-platform
- tags: point-cloud-registration, 3d-registration, slam, robust-estimation, matlab-bindings, certifiable-algorithms, optimization, algorithms, linux, macos

## Member repositories
- MIT-SPARK/TEASER-plusplus (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:38.062481+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 2026-08-30T02:37:34.592845+00:00, confidence not recorded.
  - readme: https://github.com/MIT-SPARK/TEASER-plusplus (fetched 2026-08-28T04:06:38.062481+00:00, sha 5e9fde388465)
- Data as of 2026-08-30T08:39:29.467469+00:00.