small_gicp
- Software
- Navigation and mapping
- Library
A header-only C++ library, with Python bindings, for fast and parallelized point cloud registration such as ICP, Point-to-Plane ICP, GICP and VGICP.
Source on GitHub: github.com/koide3/small_gicp (opens in a new tab). Facts read at commit fa0cfc9 (opens in a new tab).
Licenses
- Code
- MIT (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit fa0cfc9 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Refined rewrite of fast_gicp, with the core registration algorithm optimized for up to 2x speed gain.
- Parallel preprocessing (downsampling, KdTree construction, normal and covariance estimation) with OpenMP or Intel TBB backends.
- Requires only Eigen; nanoflann and Sophus are bundled.
- Optional PCL interface that can serve as a drop-in replacement for pcl::Registration.
- Template-based design allows custom point cloud types, correspondence estimators and registration factors.
- Python bindings are isolated from PCL and can be used with libraries such as Open3D.
Written by Robotheca from the project's README (opens in a new tab) at commit fa0cfc9.
Getting started
- Difficulty
- Intermediate
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 30 Sept 2026 on master
- Latest release
- v1.0.0 (JOSS publication) (9 Aug 2024)
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.