Skip to content
RobothecaBeta
Log in

pySLAM

  • Software
  • Navigation and mapping
  • Framework

A Python/C++ visual SLAM framework for monocular, stereo and RGBD cameras, built as a modular research baseline for experimenting with VO/SLAM components.

Source on GitHub: github.com/luigifreda/pyslam (opens in a new tab). Facts read at commit 96019cf (opens in a new tab).

Licenses

Code
GPL-3.0-only (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (GPL-3.0-only) at commit 96019cf (opens in a new tab), on 22 Oct 2026.

Commercial use
Yes

Copyleft: Modified source must be published.

What it does

  • Runs visual odometry and full SLAM pipelines with keyframe management, bundle adjustment and loop closing.
  • Offers many local features, matchers and global descriptors for feature tracking and place recognition.
  • Includes volumetric reconstruction (voxel grids, TSDF, Gaussian splatting) to build dense maps from posed frames.
  • Integrates depth prediction and semantic segmentation models into the SLAM pipeline.
  • Provides a sparse-SLAM core in both Python and C++ with interoperable saved maps.
  • Supports feed-forward multi-view 3D scene inference and built-in readers for more than ten dataset types.

Written by Robotheca from the project's README (opens in a new tab) at commit 96019cf.

Getting started

Difficulty
Advanced

Maintenance

Status
Active: a commit in the last 90 days
Newest commit
3 Oct 2026 on master
Latest release
None published on GitHub

Checked on GitHub on 22 Oct 2026.

Links

Robots that can run 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.