A Comprehensive Framework for Visual SLAM Baselines and Datasets
[Alejandro Fontan](https://scholar.google.com/citations?user=SDtnGogAAAAJ&hl=en)
·
[Tobias Fischer](https://scholar.google.com/citations?user=eq46ylAAAAAJ&hl=en)
·
[Nicolas Marticorena](https://nmarticorena.github.io/)
[Somayeh Hussaini](https://www.linkedin.com/in/somayeh-hussaini/?originalSubdomain=au)
·
[Ted Vanderfeen ](https://github.com/TedVanderfeen)
·
[Beverley Gorry ](https://scholar.google.com/citations?hl=es&user=s3eIy0YAAAAJ)
·
[Javier Civera](https://scholar.google.com/citations?user=j_sMzokAAAAJ&hl=en)
·
[Michael Milford](https://scholar.google.com/citations?user=TDSmCKgAAAAJ&hl=en)
Introduction
VSLAM-LAB is designed to simplify the development, evaluation, and application of Visual SLAM (VSLAM) systems. This framework enables users to compile and configure VSLAM systems, download and process datasets, and design, run, and evaluate experiments — all from a single command line!
Why Use VSLAM-LAB?
- Unified Framework: Streamlines the management of VSLAM systems and datasets.
- Ease of Use: Run experiments with minimal configuration and single command executions.
- Broad Compatibility: Supports a wide range of VSLAM systems and datasets.
- Reproducible Results: Standardized methods for evaluating and analyzing results.
Getting Started
To ensure all dependencies are installed in a reproducible manner, we use the package management tool pixi. If you haven't installed pixi yet, please run the following command in your terminal:
curl -fsSL https://pixi.sh/install.sh | bash
After installation, restart your terminal or source your shell for the changes to take effect. For more details, refer to the pixi documentation.
If you already have pixi remember to update: pixi self-update
Clone the repository and navigate to the project directory:
git clone https://github.com/VSLAM-LAB/VSLAM-LAB.git && cd VSLAM-LAB
Quick Demo
You can now execute any baseline on any sequence from any dataset within VSLAM-LAB using the following command:
pixi run demo
For a full list of available systems and datasets, see the VSLAM-LAB Supported Baselines and Datasets. Example commands:
pixi run demo mast3rslam eth table_3 mono
pixi run demo droidslam rgbdtum rgbd_dataset_freiburg1_xyz rgbd
pixi run demo orbslam2 kitti 04 stereo
pixi run demo pycuvslam euroc MH_01_easy stereo-vi
To change the paths where VSLAM-LAB-Benchmark and/or VSLAM-LAB-Evaluation data are stored (for example, to /media/${USER}/data), use the following commands:
pixi run set-benchmark-path /media/${USER}/data
pixi run set-evaluation-path /media/${USER}/data
Configure your own experiments
With VSLAM-LAB, you can easily design and configure experiments using a YAML file and run them with a single command. To run the experiment demo, execute the following command:
pixi run vslamlab configs/exp_vslamlab.yaml # resumes: runs already done are kept
pixi run vslamlab configs/exp_vslamlab.yaml --overwrite # deletes the previous results first
VSLAMLAB_HEADLESS=1 pixi run vslamlab configs/exp_vslamlab.yaml # unattended: figures are saved, no plot windows open
Experiments in VSLAM-LAB are sequences of entries in a YAML file (see example configs/exp_vslamlab.yaml):
exp_demo_droidslam:
Config: config_vslamlab.yaml # YAML file containing the sequences to be run
NumRuns: 1 # Maximum number of executions per sequence
Parameters: {verbose: 1, rgb_idx: [0,250]} # Vector with parameters that will be input to the baseline executable
Module: droidslam # droidslam/monogs/orbslam2/mast3rslam/dpvo/...
exp_demo_orbslam2:
Config: config_vslamlab.yaml
NumRuns: 1
Parameters: {verbose: 1, rgb_idx: [0,250]}
Module: orbslam2
exp_demo_colmap:
Config: config_vslamlab.yaml
NumRuns: 1
Parameters: {verbose: 1, rgb_idx: [0,250], matcher_type: exhaustive, matching_type: aliked_lightglue} # baseline-specific keys: see Baselines/colmap/README.md
Module: colmap
Frame selection: Parameters also accepts four optional flags to control which RGB frames of a sequence are fed to the baseline. They are independent and stack in this order — rgb_idx slices the frame range first, rgb_step then keeps 1 frame every n of what remains, rgb_max truncates that result to at most that many frames, and rgb_vpr finally downsamples to at most that many frames by visual dissimilarity (VPR) rather than a fixed stride, so visually redundant frames are dropped preferentially. If none are set, every frame of the sequence is used.
| Parameter | Effect |
|---|---|
rgb_idx: [start, end] |
Keep only frames start..end (inclusive) |
rgb_step: n |
Keep 1 frame every n frames of what remains |
rgb_max: n |
Truncate the result to at most n frames |
rgb_vpr: n |
Downsample the result to at most n frames, chosen by VPR dissimilarity - computes the sequence's VPR distance matrix via pixi run vpr first if it isn't already cached |
exp_vslamlab:
Config: config_vslamlab.yaml
NumRuns: 1
Parameters: {verbose: 1, rgb_idx: [0, 250], rgb_step: 3, rgb_max: 50, rgb_vpr: 30}
Module: droidslam
Config files are YAML files containing the list of sequences to be executed in the experiment (see example configs/config_vslamlab.yaml):
eth:
- table_3
rgbdtum:
- 'rgbd_dataset_freiburg1_xyz'
For a full list of available VSLAM systems and datasets, refer to the section VSLAM-LAB Supported Baselines and Datasets.
VSLAM-LAB Pipeline Commands
In addition to running the full automated pipeline, VSLAM-LAB provides modular commands to interact directly with datasets and baselines. For a comprehensive list of all available commands consult Wiki: Command-line Interface
pixi run install-baseline # Example: pixi run install-baseline droidslam
pixi run download-sequence # Example: pixi run download-sequence eth table_3
pixi run run-exp # Example: pixi run run-exp configs/exp_vslamlab.yaml
pixi run evaluate # Example: pixi run evaluate configs/exp_vslamlab.yaml
pixi run compare # Example: pixi run compare configs/exp_vslamlab.yaml
pixi run rerun-vis # Example: pixi run rerun-vis eth table_3 (Rerun viewer of a sequence)
Run a VSLAM system online from an iPhone
The ARStream app streams RGB, intrinsics and ARKit's pose from an iPhone over USB or Wi-Fi. record-iphone turns a recording into a sequence of the iphone dataset (see the Tools table); stream-iphone relays the live stream over ZeroMQ so any number of subscribers (a baseline's execute-mono-stream, the viewer, your own Python/C++ code) consume it at once:
pixi run stream-iphone --run orbslam3-dev # relay + ORB-SLAM3-DEV (or orbslam2-dev) online in one go: Ctrl-C stops the stream, the baseline saves ../VSLAM-LAB-Evaluation/stream_orbslam3-dev/00000_KeyFrameTrajectory.csv
pixi run stream-iphone --run orbslam3-dev --view # ... plus the Rerun viewer as another subscriber (--duration 30, --verbose 0, --exp-folder are also available)
pixi run stream-iphone --run orbslam2 --mode rgbd # LiDAR phone: RGB-D online with ARKit's depth (orbslam2/orbslam3 and their -dev variants), results in ../VSLAM-LAB-Evaluation/stream_orbslam2_rgbd
pixi run stream-iphone # relay only: phone over USB (or --wifi / --host ) -> tcp://*:5556, writes ../VSLAM-LAB-Benchmark/IPHONE/stream/calibration.yaml from the first frame
pixi run view-iphone --sub # the Rerun viewer as a subscriber
pixi run execute-mono-stream stream_url:tcp://localhost:5556 calibration_yaml: exp_folder: settings_yaml:vslamlab_orbslam3-dev_settings.yaml # a baseline's stream entry point by hand (runs inside Baselines/ORB-SLAM3-DEV)
Subscribers keep only the newest frame by default, so a system slower than the stream skips frames instead of lagging; the relay sends an end-of-stream message when it stops and the baseline then saves its KeyFrameTrajectory.csv as usual. A baseline joins --run by providing an execute--stream entry point taking stream_url: instead of sequence_path:/rgb_csv: (see BaselineVSLAMLAB.build_stream_command). Writing a subscriber: arstream.Subscriber (Python) or arstream/arstream.hpp (C++, conda package libarstream), see the ARStream README.
Add a new VSLAM Dataset
Expand the evaluation suite by integrating custom datasets. If you're using Claude Code, run the add-dataset skill (/add-dataset ) to walk through the full workflow end to end. Otherwise, follow the instructions in Wiki: Integrate a new VSLAM Dataset.
Add a new VSLAM Baseline
Incorporate new algorithms into the framework. Follow the guide in Wiki: Integrate a new VSLAM Baseline. Benchmark your method against state-of-the-art baselines across all supported datasets.
For a reference implementation, see the VGGT-SLAM integration in commit 259f7ae.
License
VSLAM-LAB is released under a LICENSE.txt. For a list of code dependencies which are not property of the authors of VSLAM-LAB, please check docs/Dependencies.md.
Citation
If you're using VSLAM-LAB in your research, please cite:
@INPROCEEDINGS{fontan2025vslam,
author={Fontan, Alejandro and Fischer, Tobias and Civera, Javier and Milford, Michael},
booktitle={2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
title={VSLAM-LAB: A Comprehensive Framework for Visual SLAM Methods and Datasets},
year={2025},
volume={},
number={},
pages={9013-9020},
keywords={Visualization;Simultaneous localization and mapping;Robot vision systems;Standardization;Benchmark testing;Programming;Reproducibility of results;Intelligent robots;Faces;Software development management},
doi={10.1109/IROS60139.2025.11247218}
}
VSLAM-LAB Supported Baselines and Datasets
For full per-dataset details — license, access requirements, and publication/BibTeX citation — see Datasets/extra-files/dataset_table.xlsx.
| Baselines | System | Modes | License | Label | Conda Pkg | Camera Models |
|---|---|---|---|---|---|---|
| AllFeature-VSLAM | VSLAM | mono rgbd |
GPLv3 | allfeature |
✅ | pinhole radtan4 radtan5 |
| VGGT-SLAM 2.0 | VSLAM | mono |
BSD-2 | vggtslam |
✅ | pinhole |
| MASt3R-SLAM | VSLAM | mono |
CC BY-NC-SA 4.0 | mast3rslam |
✅ | pinhole radtan4 radtan5 |
| DPVO | VSLAM | mono |
License | dpvo |
✅ | pinhole radtan4 radtan5 |
| DROID-SLAM | VSLAM | mono rgbd stereo |
BSD-3 | droidslam |
✅ | pinhole radtan4 radtan5 |
| ORB-SLAM2 | VSLAM | mono rgbd stereo |
GPLv3 | orbslam2 |
✅ | pinhole radtan4 radtan5 |
| MonoGS | VSLAM | mono rgbd |
License | monogs-dev |
➖ | pinhole radtan4 radtan5 |
| ---------- | ------- | ------- | ---------- | -------- | --- | ---------- |
| PyCuVSLAM | VSLAM | rgbd stereo(-vi) |
NVIDIA | pycuvslam |
➖ | pinhole radtan4 radtan5 equid4 |
| ORB-SLAM3 | VSLAM | mono(-vi) rgbd(-vi) stereo(-vi) |
GPLv3 | orbslam3 |
✅ | pinhole radtan4 radtan5 equid4 |
| OKVIS2 | VSLAM | mono-vi |
BSD-3 | okvis2 |
✅ | pinhole radtan4 radtan5 radtan8 equid4 |
| ---------- | ------- | ------- | ---------- | -------- | --- | ---------- |
| COLMAP | ||||||
matching_type: SIFT · ALIKED · LoMa features with brute-force or learned matchers · mapper_type: colmap · glomap · dense: 1 with mesher: delaunay · poisson · advancing_front — reference |
SfM | mono |
BSD | colmap |
✅ | pinhole radtan4 radtan5 radtan8 equid4 unknown |
| Depth Anything 3 | Feed-forward | mono |
Apache-2.0 (giant/nested weights CC BY-NC 4.0) | da3 |
➖ | pinhole |
| DA3-Streaming | VSLAM | mono |
Apache-2.0 | da3-streaming |
➖ | pinhole |
| MapAnything | ||||||
module: VGGT · VGGT-Ω · π³ · DUSt3R · MASt3R · MUSt3R · Pow3R (mono, each under its own license) |
Feed-forward | mono rgbd |
Apache-2.0 (default weights CC BY-NC 4.0) | mapanything |
➖ | pinhole |
[!NOTE]
-devvariants:orbslam2-dev,orbslam3-dev,droidslam-dev,dpvo-dev,mast3rslam-dev,vggtslam-dev,allfeature-dev,okvis2-devandmonogs-devclone the baseline's source intoBaselines/-DEV/and build it locally instead of installing the conda package, with the same modes and camera models - use them to modify a baseline.monogs-devexists only in this form.
Label
Features
Summary
Modes
Camera Models
🏠 Indoor datasets
7scenes
📸🏠🤳
Tracked RGB-D Kinect frames from seven indoor scenes, for camera...
mono rgbd
pinhole
aria-digital-twin
📸🏠🥽
Aria Digital Twin (ADT) - egocentric dataset captured with Meta's Project Aria...
mono(-vi) stereo(-vi) rgbd(-vi)
pinhole
bonn-rgbd
📸🏠🤳
Bonn RGB-D Dynamic Dataset - 24 highly dynamic indoor RGB-D sequences (people...
mono rgbd
radtan5
eth
📸🏠🤳
ETH3D SLAM & Stereo Benchmarks
mono rgbd
pinhole
minimal
📸🏠🤳
Minimal Texture Dataset for RGB-D SLAM - RealSense D435i RGB-D sequences over...
mono rgbd
pinhole
monotum
📸🏠🏞️🤳
Photometrically calibrated monocular visual odometry benchmark with 50...
mono
pinhole
msd
📸🏠🥽
Monado SLAM Dataset - Valve Index
mono(-vi) stereo(-vi)
equid4
newer-college-stereo-vi
📸🏞️🤳
The Newer College Dataset (stereo-inertial collection) - handheld RealSense...
mono(-vi) stereo(-vi)
radtan4
openloris-d400
📸🏠🤳
OpenLORIS-Scene - real-world lifelong SLAM dataset from real robots in real...
mono(-vi) rgbd(-vi)
pinhole
openloris-t265
📸🏠🤳
OpenLORIS-Scene - real-world lifelong SLAM dataset from real robots in real...
mono(-vi) stereo(-vi)
equid4
rgbdtum
📸🏠🤳
RGB-D SLAM benchmark with motion-capture ground-truth trajectories
mono rgbd
radtan5
rvp-handheld
📸🏞️🤳
VBR - A Vision Benchmark in Rome (hand-held sequences) - hardware-synced stereo...
mono(-vi) stereo(-vi)
radtan4
vitum
📸🏠🏞️🤳
TUM Visual-Inertial Dataset - stereo fisheye and IMU sequences from a handheld...
mono(-vi) stereo(-vi)
equid4
💻 Synthetic datasets
drunkards
💻🏠🤳
The Drunkard's Dataset - synthetic RGB-D exploratory camera trajectories with...
mono rgbd
pinhole
endomapper-sim
💻🫀🤳
EndoMapper simulated colon - photorealistic VR-Caps renders of a CT-derived...
mono rgbd
pinhole
nuim
💻🏠🤳
ICL-NUIM RGB-D benchmark with ground-truth trajectories and 3D models for...
mono rgbd
pinhole
replica
💻🏠🤳
Photorealistic 3D indoor scene reconstructions (Replica), with RGB-D SLAM...
mono rgbd
pinhole
tartanair
💻🏞️🤳
Large-scale photorealistic simulation dataset with multimodal ground truth for...
mono
pinhole
tartanair-train
💻🏠🏞️🤳
TartanAir training split - photorealistic simulated stereo+depth sequences over...
mono stereo rgbd
pinhole
🚗 Vehicle datasets
kitti
📸🏞️🚗
KITTI Odometry Benchmark with stereo image sequences and ground-truth poses for...
mono stereo
pinhole
malaga
📸🏞️🚗
The Malaga Urban Dataset - high-rate rectified stereo images from a car driven...
mono stereo
pinhole
nsavp
📸🏞️🚗
Novel Sensors for Autonomous Vehicle Perception - stereo thermal, event,...
mono stereo
radtan4
rvp-car
📸🏞️🚗
VBR - A Vision Benchmark in Rome (car sequences) - hardware-synced stereo...
mono(-vi) stereo(-vi)
radtan4
🚁 UAV datasets
euroc
📸🏞️🚁
EuRoC MAV visual-inertial dataset with stereo images, IMU, and ground-truth...
mono(-vi) stereo(-vi)
radtan4
uzh-fpv
📸🏠🏞️🚁
UZH-FPV Drone Racing Dataset - aggressive quadrotor flight sequences from an...
mono(-vi) stereo(-vi)
equid4
🤖 Robot datasets
blt
📸🏞️🤖
BACCHUS Long-Term (BLT) dataset - a Thorvald II robot driving the same 500 m...
mono rgbd
pinhole
fomo
📸🏞️🤖
FoMo (Forêt Montmorency) - a Clearpath Warthog UGV repeating six on-road,...
mono(-vi) stereo(-vi)
pinhole
grandtour-alphasense
📸🏠🏞️🤖
GrandTour (Alphasense rig) - 48 ANYmal-D quadruped missions across alpine,...
mono(-vi) stereo(-vi)
equid4
grandtour-zed2i
📸🏠🏞️🤖
GrandTour (ZED2i rig) - 47 ANYmal-D quadruped missions across alpine, forest,...
mono stereo
radtan4
rover-d435i
📸🏞️🤖
ROVER: A Multiseason Dataset for Visual SLAM
mono rgbd(-vi)
radtan4
rover-picam
📸🏞️🤖
ROVER: A Multiseason Dataset for Visual SLAM
mono
equid4
rover-t265
📸🏞️🤖
ROVER: A Multiseason Dataset for Visual SLAM
mono(-vi) stereo(-vi)
equid4
ut-coda
📸🏞️🤖
The UT Campus Object Dataset (CODa) - egocentric robot perception dataset...
mono stereo
radtan5
vector
📸🏠🤳🤖
VECtor - a versatile event-centric benchmark for multi-sensor SLAM, with a...
mono(-vi) stereo(-vi)
radtan4
🏗️ Construction Site datasets
hilti2022
📸🏠🏞️🏗️🤳
Hilti-Oxford SLAM Challenge 2022 - multi-camera, IMU and lidar dataset for SLAM...
mono(-vi) stereo(-vi)
equid4
hilti2026
📸🏠🏞️🏗️🤳
Hilti x Trimble 360 Visual-Inertial SLAM Challenge 2026 - construction-site...
mono(-vi)
equid4
🪐 Planetary-analog Terrain datasets
madmax
📸🏞️🪐🤳
The MADMAX data set for visual-inertial rover navigation on Mars
mono(-vi) stereo(-vi)
pinhole
s3li-etna
📸🏞️🪐🤳
S3LI Etna - the DLR Planetary Stereo, Solid-State LiDAR, Inertial dataset,...
mono(-vi) stereo(-vi)
pinhole
s3li-vulcano
📸🏞️🪐🤳
S3LI Vulcano - a multi-modal (RGB stereo, solid-state LiDAR, inertial) dataset...
mono(-vi) stereo(-vi)
pinhole
🌊 Underwater datasets
ariel
📸🏠🏞️🌊🤖
Multi-Camera Underwater Visual-Inertial Dataset - a BlueROV2-based platform...
mono(-vi) stereo(-vi)
equid4
caves
📸🏞️🌊
Underwater Caves Sonar and Vision Data Set - a diver-guided AUV exploration of...
mono
pinhole
eiffel-tower
📸🏞️🌊🤖
Deep-sea hydrothermal vent imagery from four ROV Victor6000 survey campaigns...
mono
radtan4
pamir
📸🌊🤳
Multi-session visual-inertial SLAM dataset of the Pamir shipwreck (Barbados),...
mono(-vi)
unknown
pamir-rig
📸🌊🤳
Multi-session visual-inertial SLAM dataset of the Pamir shipwreck (Barbados),...
mono(-vi) stereo(-vi)
unknown
sesoko
📸🏞️🌊
AUV (TUNA-SAND) coral-reef mapping surveys off Sesoko Island, Okinawa, Japan...
mono
unknown
soneva
📸🏞️🌊🤳
Coral reef time-series photogrammetry (Maldives), from Soneva Conservation and...
mono
pinhole
sweetcorals
📸🏞️🌊🤳
Coral reef 3D photogrammetry (Indonesia), from Wildflow
mono
pinhole unknown
🫀 Intracorporeal datasets
endomapper
📸🫀🤳
EndoMapper - 93 complete calibrated colonoscopy and gastroscopy procedures...
mono
equid4 unknown
hamlyn
📸🫀🤳
Hamlyn rectified stereo endoscopy dataset with depth ground truth, from...
mono rgbd stereo
pinhole
| Tools | Features | Label | Modes | Camera Models |
|---|---|---|---|---|
| Stray Scanner App | 📸🤳 | strayscanner |
mono rgbd |
pinhole |
| Pupil Labs Neon | 📸🥽 | pupil-labs |
mono(-vi) |
pinhole |
| Local video files | 📸 | videos |
mono |
pinhole unknown |
| YouTube videos | ||||
add one with the add-youtube-video skill |
📸 | youtube |
mono |
pinhole radtan4 unknown |
| iPhone (ARStream app) | ||||
record one with pixi run record-iphone [] (USB or --wifi); ARKit's VIO pose as groundtruth |
📸🤳 | iphone |
mono |
pinhole |
| iPhone with LiDAR (ARStream app) | ||||
pixi run record-iphone --lidar []; ARKit's sceneDepth (256×192, confidence-masked, upsampled to the RGB size) as depth_0 |
📸🤳 | iphone-lidar |
mono rgbd |
pinhole |
Real / Synthetic : 📸 / 💻
Indoor / Outdoor / Underwater / Intracorporeal : 🏠 / 🏞️ / 🌊 / 🫀
Handheld / Headmounted / Vehicle / UAV / Robot : 🤳 / 🥽 / 🚗 / 🚁 / 🤖
Section dividers only (not per-row features) — Construction Site / Planetary-analog Terrain : 🏗️ / 🪐