#vSLAM
VSLAM-LAB: A Comprehensive Framework for Visual SLAM Methods and Datasets

Alejandro Fontan, Tobias Fischer, Javier Civera, Michael Milford

tl;dr:
arxiv.org/abs/2504.04457
April 11, 2025 at 11:49 AM
I caught my dog giving his reflection dirty looks in the mirror 💀 (🎥: ViralHog)
YouTube video by LADbible Shorts
youtube.com
September 2, 2025 at 6:14 PM
Andrew Bernas' autonomous drone uses real-time VSLAM on an NVIDIA Jetson Orin Nano to navigate GPS-denied areas via visual-inertial sensing and onboard mapping.
GPS-Denied Drone With NVIDIA Jetson Orin Nano
Autonomous drone using real-time VSLAM on Jetson Orin Nano to navigate GPS-denied areas via visual-inertial sensing and onboard mapping. By Andrew Bernas.
www.hackster.io
June 23, 2025 at 1:29 PM
Drift-free Visual SLAM using Digital Twins

Roxane Merat, Giovanni Cioffi, Leonard Bauersfeld, Davide Scaramuzza

tl;dr: VIO/VSLAM->local sparse 3D point cloud->point-to-plane ICP->digital twin point cloud->global measurement->VIO/VSLAM->globally consistent pose estimates

arxiv.org/abs/2412.08496
December 12, 2024 at 4:24 AM
3D Densification for Multi-Map Monocular VSLAM in Endoscopy

X. Anadón, Javier Rodríguez-Puigvert, J.M.M. Montiel

tl;dr: sparse maps from CudaSIFT-SLAM+dense depth from LightDepth, aligning them using Least Median Squares for scale corrections and outlier filtering

arxiv.org/abs/2503.14346
March 20, 2025 at 9:31 AM
VSLAM-LAB: A Comprehensive Framework for Visual SLAM Methods and Datasets

Alejandro Fontan, Tobias Fischer, @jcivera.bsky.social, Michael Milford

tl;dr: in title

arxiv.org/abs/2504.04457
April 8, 2025 at 5:25 AM
Worx Landroid Vision Cloud WR306E 2WD Robot Cortacésped, Sin Cable Perimetral, hasta 500 m², Evitación de Obstáculos con IA, Navegación VSLAM + RTK Cloud, Mapeo Automático, Control por App
💥 644,58€ (-29%)
👉 https://go.descontospt.pt/r/CUN7NAM
#chollos #poupar #promocoes
September 21, 2026 at 11:10 AM
Dynamic semantic VSLAM with known and unknown objects

Sanghyoup Gu, Ratnesh Kumar

tl;dr: ORB-SLAM2+Fast-SAM+PWC-Net

arxiv.org/abs/2412.14359
December 20, 2024 at 5:56 AM
My paper “3D Gaussian Splatting as Test Video Generators for Loop Closure in Underwater vSLAM” got accepted at AUV2026 🥳

www.auv2026-southampton.com

See you in September 👋🏻🤖🌊
AUV2026, Southampton
auv2026-southampton
www.auv2026-southampton.com
March 2, 2026 at 11:30 AM
How Robotic Lawn Mowers Navigate Your Yard Using vSLAM and LiDAR

Check out our blog for more insights and learn how these technologies work, along with high-quality lawn mower parts for your needs: www.wholetoolbox.com/blog/post/ho...

#roboticlawnmower #smartrobots #vSLAM #LiDAR #homeautomation
April 3, 2026 at 11:43 AM
I like it! The app is really cool. Being able to paint an area to clean etc. Impressed with the vslam and ability to understand the house + floor types. Vacuum itself is really quiet and nice
March 25, 2025 at 12:07 AM
Interest In A SouthEast Florida ROS Users Group?

I'm in Palm Beach County FL, and tired of doing ROS alone. Let's make our ROS robots smart, safe, and reliable.

#ROS2 #Robots #Navigation #Mapping #vSLAM #RTAB_Map #ORB_SLAM #MobileRobots #AutonomousVehicles #Florida
#PBSC #FAU #SouthTechAcademy
December 7, 2024 at 8:14 PM
Yep, it's also possible to integrate ArduPilot with ROS and take advantage of various vSLAM packages.

I think Ukraine just went with basic GPS waypoints, though.
June 4, 2025 at 5:52 PM
> IMU and wheel encoders
I found that IMU and wheel encoders alone were insufficient to maintain heading accuracy, and vSLAM too difficult for my robot resources.

Added LIDAR to next re-incarnation - easy, accurate mapping, but poor obstacle detection made navigation brittle.
January 1, 2026 at 5:06 PM
Review of deep learning-enhanced visual SLAM

🤖 Learning boosts VSLAM robustness.
⚠️ Classical geometry fails in harsh scenes.
🔗 Five fusion interfaces categorized.
🧭 Future: foundation models, real-time deployment.
DOI: https://doi.org/10.32604/cmc.2026.086341 #VSLAM #DeepLearning
September 9, 2026 at 2:26 AM
Review of deep learning-enhanced visual SLAM

🤖 Learning boosts VSLAM robustness.
⚠️ Classical geometry fails in harsh scenes.
🔗 Five fusion interfaces categorized.
🧭 Future: foundation models, real-time deployment.
DOI: https://doi.org/10.32604/cmc.2026.086341 #VSLAM #DeepLearning
September 9, 2026 at 2:26 AM
>stereo pair for SLAM
Will be interesting to hear performance for non-fiduciary visual SLAM when you get fully up an running. Having non-fixed camera mount may be a problem - I don't know enough to judge.

The other vSLAM issue is repeatable lighting, so works best with cameras with illuminators.
January 1, 2026 at 4:59 PM
2 yr ago I built a non-LIDAR RaspberryPi5 w/Oak-D-Lite stereo depth cam on a Create3. Planned to use RTABmap visual SLAM - almost got it working but Pi5 and Create3 were both at 125% (out of resources).

Your Orin powered bot, might be able to do vSLAM. (LIDAR is planar + can't see black objs.)
January 1, 2026 at 4:51 PM
> one student is doing API Python

Shortly before iRobot fired the Education folk, I suggested to them to use the API Python, moving all ROS 2 to an external SBC/RaspberryPi. The Create3 internal processors hit a brick wall trying to keep up with ROS 2 message traffic (RMW) with vSLAM for me.
April 14, 2025 at 11:52 AM