@ajdavison.bsky.social
From SLAM to Spatial AI; Professor of Robot Vision, Imperial College London; Director of the Dyson Robotics Lab; Co-Founder of Slamcore. FREng, FRS.
good morning
30.07.2025 13:16 β π 1379 π 371 π¬ 23 π 89For those watching in black and white, the blue is behind the brown...
23.07.2025 08:43 β π 7 π 0 π¬ 1 π 0I've been a Tamiya RC fan since owning and loving a Grasshopper in the 80s, and more recently built one or their RC kits with each of my kids (Hornet, LunchBox and Midnight Pumpkin!)
22.07.2025 13:44 β π 4 π 0 π¬ 0 π 0Live Demo of MASt3R-SLAM this afternoon in the demo session at #CVPR2025.
13.06.2025 18:22 β π 11 π 1 π¬ 0 π 0Full 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 @hidematsu82.bsky.social and me.
#SpatialAI
github.com/SLAM-Handboo...
Great diagram.
30.04.2025 21:53 β π 117 π 19 π¬ 4 π 1
It's 3PM. Exactly 40 years ago the first ARM processor was powered up. It worked. To mark the occasion, a bottle of champagne was opened and the time and date was written on the bottle - by Sophie Wilson IIRC. I hope today another bottle is opened to celebrate the anniversary.
26.04.2025 14:01 β π 105 π 26 π¬ 5 π 0Great look at back at 2D scrolling methods in games.
09.04.2025 15:54 β π 1 π 0 π¬ 0 π 0Slow motion Galton Board.
Love that Gaussian!
We were fortunate to have Jianyuan visit us at Imperial yesterday, and he gave a brilliant and thoughtful talk about 3D geometry and learning. Maybe every 6--12 months or so there is a paper in my area which really seems like something new and important, and VGGT is one of those!
02.04.2025 16:48 β π 17 π 1 π¬ 0 π 0Should be good!
24.03.2025 17:09 β π 5 π 0 π¬ 0 π 0
Remember: the route to Spatial AI is through SLAM. Key research topics are representations for real-time fusion of measurements and priors into persistent semantic/metric scene models; and algorithm/hardware co-design for 1000X efficiency. #SpatialAI
arxiv.org/abs/1803.11288
On the tram station video, VGGT fails entirely, whereas MASt3R-SLAM had done a more reasonable (albeit also not stellar) job.
bsky.app/profile/chri...
Visual Geometry Grounded Transformer (VGGT) predicts cameras, point maps, depth maps, and point tracks for up to hundreds of images in less than a second on a H100 GPU.
github.com/facebookrese...
200 hours of play in I am still addicted to Balatro!
11.03.2025 12:13 β π 1 π 0 π¬ 0 π 0Cool to see this.
05.03.2025 18:42 β π 6 π 0 π¬ 0 π 0
If you like word puzzles, Bracket City is really cool:
bracket.city
The clues are cleverly nested in a way that looks like Lisp code!
(Via the @recomendo.bsky.social weekly newsletter.)
Many interesting tests of MASt3R-SLAM on prerecorded videos.
01.03.2025 01:12 β π 6 π 0 π¬ 0 π 0
Aria Gen 2 is very impressive, with fully onboard SLAM and various other perception all within a 75g device with an hours-long battery life. Processing on custom silicon. Congrats to the Reality Labs team.
28.02.2025 17:10 β π 23 π 3 π¬ 0 π 1!
27.02.2025 15:40 β π 0 π 0 π¬ 0 π 0Shawshank Prison reconstructed with MASt3R-SLAM... from one of the best films ever.
25.02.2025 22:33 β π 24 π 0 π¬ 2 π 1I remember seeing this drone video a few years ago and thinking "we'll never run SLAM on that".... but here it is, complete with dense reconstruction (single camera, unknown calibration, no IMU). MASt3R-SLAM is absurdly robust.
25.02.2025 20:37 β π 34 π 6 π¬ 2 π 0Open source code now available MASt3R-SLAM: the best dense visual SLAM system I've ever seen. Real-time and monocular, and easy to run with a live camera or on videos without needing to know the camera calibration. Brilliant work from Eric and Riku.
25.02.2025 17:34 β π 31 π 6 π¬ 0 π 0Wow I'd like to try to understand this.
Something for @tinytapeout.com ?
Looks like a great workshop, happening in Malaga this July.
10.02.2025 16:14 β π 6 π 0 π¬ 0 π 0Gradually unfollowing all of the namesakes I picked up from that automatic X to Bluesky converter tool!
10.02.2025 11:14 β π 5 π 0 π¬ 1 π 0
Forest Wanderings. π³
09.02.2025 21:56 β π 70 π 9 π¬ 0 π 0Not one VC would ever fund a startup to do the kind of hardcore optimization work that DeepSeek did.
Every VC firm should be asking themselves why.
