Skip to content

kornia-slam

  • Software
  • Navigation and mapping
  • Library

A Rust library and app for real-time visual-inertial SLAM, built on kornia-rs, covering monocular, stereo and inertial setups with loop closing.

Made by kornia.

Source on GitHub: github.com/kornia/kornia-slam (opens in a new tab). Facts read at commit 05ea01c (opens in a new tab).

Licenses

Code
Apache-2.0 (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit 05ea01c (opens in a new tab), on 22 Oct 2026.

Commercial use
Yes

What it does

  • Runs monocular, stereo and visual-inertial ORB SLAM, with local bundle adjustment including visual-inertial BA.
  • Detects place recognition with DBoW2 and closes loops with pose-graph optimization, using an ORB-SLAM3 vocabulary file.
  • Reads EuRoC, Hilti, MCAP, OAK-D and UVC webcam sources; live OAK-D and UVC support needs a build with extra features.
  • Offers a terminal UI, Rerun streaming and ATE/RPE evaluation against ground truth.
  • Exposes a Rust library where a system configuration and sensor rig build a SlamSystem that processes frames and returns poses.
  • Can be driven from RON run files, and integrates with Copper as stereo visual-inertial odometry tasks.

Written by Robotheca from the project's README (opens in a new tab) at commit 05ea01c.

Getting started

Difficulty
Advanced

Maintenance

Status
Active: a commit in the last 90 days
Newest commit
17 Oct 2026 on main
Latest release
v0.1.0 (27 Sept 2026)

Checked on GitHub on 22 Oct 2026.

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.