Another SLAM live demo session from our lab in #CVPR2025! Dense SLAM is not just by 3D Gaussians, but also by 2D segments!

COMO will be presented as an 𝐨𝐫𝐚𝐥 at #ECCV2024! Also come see the 𝐥𝐢𝐯𝐞 𝐝𝐞𝐦𝐨 of our compact 3D representation for real-time monocular SLAM Oral: Session 2C at 1:40 PM on Tue 1 Oct Poster: #181 at 4:30-6:30 PM on Tue 1 Oct Demo: Thurs 3 Oct AM edexheim.github.io/como/

Come and see COMO at #ECCV2024 in Eric's oral presentation and poster on Tuesday, and *live demo* on Thursday morning. State of the art real-time monocular dense SLAM via depth covariance network and a compact 3D point set.

One of the most impressive demos I have seen in recent years presented at #ECCV2024. Monocular (RGB only!) dense SLAM running on a consumer laptop at 30FPS. COMO by Eric Dexheimer Andrew Davison, also open source edexheim.github.io/como/

We are presenting Hyperion at #ECCV2024 TODAY! Come by the poster 199. Continuous-time SLAM + Guassian Belief Propagation, with applications to multi-agents. A collaboration with David Hug and Margarita Chli. High performance code open sourced github.com/VIS4ROB-lab/hy…

Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation. Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map. With Eric Dexheimer*, Andrew Davison (*Equal Contribution)

For robustness, MASt3R-SLAM performs relocalisation allowing it to handle the kidnapped robot problem. As a purely monocular SLAM, it loses track when the camera’s view is obstructed, but as soon as the view is unblocked, it immediately relocalises and resumes mapping.

For more please visit: Website: edexheim.github.io/mast3r-slam/ Video: youtu.be/wozt71NBFTQ

Vslam from a single uncalibrated rgb camera. With stuff like this and depth-anything, I think the days of overpriced, unreliable structured light RGBD sensors are numbered

MASt3R-SLAM: it's easily the most robust dense monocular SLAM system I've ever seen, and also very accurate. Real-time, RGB only (no IMU), handles unknown focal length and zoom. More new videos coming soon Eric Dexheimer Riku Murai. Paper and full info: edexheim.github.io/mast3r-slam

Google Internship call: we are looking for a PhD student in the area of object/scene understanding and VLMs to join our Google team in Zurich next summer. If you have applied for the 2025 Google Internship Call already and are interested to know more, ping me!

Full draft of the SLAM Handbook now released --- available as a free PDF, with a printed version coming soon. Now including Part 3, "From SLAM to Spatial AI" (I knew it would catch on eventually), with contributions from Hide and me. #SpatialAI github.com/SLAM-Handbook-…

📢📢📢 Neural Inverse Rendering from Propagating Light 💡 Our CVPR Oral introduces the first method for multiview neural inverse rendering from videos of propagating light, unlocking applications such as relighting light propagation videos, geometry estimation, or light

Our Android XR team at Google is hosting a tutorial session at #CVPR2025 this week, on June 12! Join us to explore the latest computer vision tech stack for immersive user experiences. augmentedperception.github.io/cvpr2025/

✨I will be in Nashville for #CVPR2025 🎤 Catch me at the poster session or just come say hi. 🗓️ Sunday 15 June 10:30 a.m. - 12:30 p.m. CDT 📍Poster Session #5 — Exhibit Hall D Poster #62 (highlighted as an Outstanding Reviewer poster) (1/2)

Will present Today 4-6pm, ExHall D Poster#74 See you there!