Software
MASt3R-SLAM
From github.com/rmurai0610/MASt3R-SLAM (opens in a new tab)
- Navigation and mapping
- Library
- CC-BY-NC-SA-4.0
A real-time dense SLAM system that builds 3D reconstructions of a scene from RGB video, using MASt3R 3D reconstruction priors. It runs on live camera feeds, MP4 videos, or image folders.
- Non-commercial. The code license (CC-BY-NC-SA-4.0) does not allow commercial use.
- Stale. No commit in 12 months: the newest is from 9 Nov 2025.
Facts
- GitHub stars
- 3,236read on 6 Nov 2026
- Last update
- 9 Nov 2025Newest commit on main
- Maintenance
- Staleno commit in 12 months
- Difficulty
- Advanced
- Hardware it needs, as the project states it
- An NVIDIA GPU with CUDA (11.8, 12.1 or 12.4) matching the installed PyTorch build; the authors report running on an RTX 4090, and performance may differ on other GPUs. Ubuntu is the primarily tested OS; WSL is supported via a separate branch. A RealSense camera is needed only for the live demo.
Checked on GitHub on 6 Nov 2026.
Licenses
- Code
- CC-BY-NC-SA-4.0 (opens in a new tab)
Read by Robotheca from LICENSE.md (opens in a new tab) at commit e6f4e3d (opens in a new tab), on 16 Oct 2026. A license text Robotheca's reader does not know: a person at Robotheca set it on 9 Nov 2026.
- Commercial use
- No
The code license does not allow commercial use.
Overview
What it does: Robotheca's summary
- Performs dense simultaneous localization and mapping from monocular RGB input, including live RealSense cameras, MP4 videos, and image folders.
- Uses pretrained MASt3R checkpoints, which must be downloaded separately into a checkpoints folder.
- Includes scripts to download and evaluate on TUM-RGBD, 7-Scenes, EuRoC and ETH3D SLAM datasets.
- Accepts known camera calibration through an intrinsics file, or runs without calibration.
- Has a WSL variant on a separate windows branch that disables multiprocessing.
Written by Robotheca from the project's README (opens in a new tab) at commit e6f4e3d, not by its creator.
The README
Files and versions
- Repository on GitHubgithub.com/rmurai0610/MASt3R-SLAM (opens in a new tab)
- The version Robotheca reade6f4e3d (opens in a new tab)
- Latest releaseNone published on GitHub
Robotheca never hosts the code: each link goes to the creator's own page.
Use it
How to install it, in the creator's words: The project's website (opens in a new tab)
Robotheca doesn't review code. Read it before running it.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.