Andrew Davison
@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.
Reposted by Andrew Davison
I'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!)
RIP Shunsaku Tamiya, age 90, the chairman of legendary modelmaker Tamiya. He didn't found the company, but started working there in 1958, just four years after its founding, and helped it shift from its original line of wooden models into the plastic kits it is so well known for today.
July 22, 2025 at 1:44 PM
I'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!)
Live Demo of MASt3R-SLAM this afternoon in the demo session at #CVPR2025.
We’ve had fun testing the limits of MASt3R-SLAM on in-the-wild videos. Here’s the drone video of a Minnesota bowling alley that we’ve always wanted to reconstruct! Different scene scales, dynamic objects, specular surfaces, and fast motion.
June 13, 2025 at 6:22 PM
Live Demo of MASt3R-SLAM this afternoon in the demo session at #CVPR2025.
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 @hidematsu82.bsky.social and me.
#SpatialAI
github.com/SLAM-Handboo...
#SpatialAI
github.com/SLAM-Handboo...
GitHub - SLAM-Handbook-contributors/slam-handbook-public-release: Release repo for our SLAM Handbook
Release repo for our SLAM Handbook. Contribute to SLAM-Handbook-contributors/slam-handbook-public-release development by creating an account on GitHub.
github.com
May 16, 2025 at 2:24 PM
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 @hidematsu82.bsky.social and me.
#SpatialAI
github.com/SLAM-Handboo...
#SpatialAI
github.com/SLAM-Handboo...
Great diagram.
This is interesting — a recent study of mode share (the % share of transportation trips by car, transit, walking, biking etc) relative to city size and income levels in almost 800 cities in 61 countries. Interesting results. HT @davidzipper.bsky.social
www.sciencedirect.com/science/arti...
www.sciencedirect.com/science/arti...
April 30, 2025 at 9:53 PM
Great diagram.
Reposted by Andrew Davison
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.
April 26, 2025 at 2:01 PM
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.
Great look at back at 2D scrolling methods in games.
Hard to believe that a decade ago, in preparation for the release of my game, I spent a month researching 2D cameras by playing through all my favorite 80s classics.
If you haven't yet, check out this fun, GIF-heavy paper!
docs.google.com/document/d/e...
If you haven't yet, check out this fun, GIF-heavy paper!
docs.google.com/document/d/e...
April 9, 2025 at 3:54 PM
Great look at back at 2D scrolling methods in games.
Slow motion Galton Board.
Love that Gaussian!
Love that Gaussian!
April 5, 2025 at 5:19 PM
Slow motion Galton Board.
Love that Gaussian!
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!
Introducing VGGT (CVPR'25), a feedforward Transformer that directly infers all key 3D attributes from one, a few, or hundreds of images, in seconds!
Project Page: vgg-t.github.io
Code & Weights: github.com/facebookrese...
Project Page: vgg-t.github.io
Code & Weights: github.com/facebookrese...
April 2, 2025 at 4:48 PM
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!
Should be good!
Tomorrow in our TUM AI - Lecture Series we'll have Andrea Tagliasacchi (@taiyasaki.bsky.social), SFU.
He'll talk about "𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: 𝐑𝐞𝐚𝐥-𝐓𝐢𝐦𝐞 𝐃𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐭𝐢𝐚𝐛𝐥𝐞 𝐑𝐚𝐲 𝐓𝐫𝐚𝐜𝐢𝐧𝐠".
Live Stream: youtube.com/live/1u7ahb9...
5pm GMT+1 / 9am PST (Mon Mar 24th)
He'll talk about "𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: 𝐑𝐞𝐚𝐥-𝐓𝐢𝐦𝐞 𝐃𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐭𝐢𝐚𝐛𝐥𝐞 𝐑𝐚𝐲 𝐓𝐫𝐚𝐜𝐢𝐧𝐠".
Live Stream: youtube.com/live/1u7ahb9...
5pm GMT+1 / 9am PST (Mon Mar 24th)
TUM AI Lecture Series - Radiant Foam: Real-Time Differentiable Ray Tracing (Andrea Tagliasacchi)
YouTube video by Matthias Niessner
youtube.com
March 24, 2025 at 5:09 PM
Should be good!
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
arxiv.org/abs/1803.11288
FutureMapping: The Computational Structure of Spatial AI Systems
We discuss and predict the evolution of Simultaneous Localisation and Mapping (SLAM) into a general geometric and semantic `Spatial AI' perception capability for intelligent embodied devices. A big ga...
arxiv.org
March 20, 2025 at 1:07 AM
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
arxiv.org/abs/1803.11288
Reposted by Andrew Davison
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...
bsky.app/profile/chri...
March 16, 2025 at 5:44 PM
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...
bsky.app/profile/chri...
Reposted by Andrew Davison
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...
github.com/facebookrese...
March 16, 2025 at 5:44 PM
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...
github.com/facebookrese...
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.)
bracket.city
The clues are cleverly nested in a way that looks like Lisp code!
(Via the @recomendo.bsky.social weekly newsletter.)
Bracket City
come visit bracket city
bracket.city
March 2, 2025 at 8:53 PM
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.)
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.
I tried MASt3R-SLAM on this challenging sequence but it struggles. I'll have to see whether I can get it to produce better results on this one.
March 1, 2025 at 1:12 AM
Many interesting tests of MASt3R-SLAM on prerecorded videos.
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.
Introducing Aria Gen 2: Unlocking New Research in Machine Perception, Contextual AI, Robotics, and More
Today, we're excited to announce the next step in the Project Aria journey: the introduction of Aria Gen 2 research glasses.
www.meta.com
February 28, 2025 at 5:10 PM
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.
Shawshank Prison reconstructed with MASt3R-SLAM... from one of the best films ever.
Here's a reconstruction of a movie establishing shot
February 25, 2025 at 10:33 PM
Shawshank Prison reconstructed with MASt3R-SLAM... from one of the best films ever.
I 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.
We’ve had fun testing the limits of MASt3R-SLAM on in-the-wild videos. Here’s the drone video of a Minnesota bowling alley that we’ve always wanted to reconstruct! Different scene scales, dynamic objects, specular surfaces, and fast motion.
February 25, 2025 at 8:37 PM
I 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.
Open 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.
MASt3R-SLAM code release!
github.com/rmurai0610/M...
Try it out on videos or with a live camera
Work with
@ericdexheimer.bsky.social*,
@ajdavison.bsky.social (*Equal Contribution)
github.com/rmurai0610/M...
Try it out on videos or with a live camera
Work with
@ericdexheimer.bsky.social*,
@ajdavison.bsky.social (*Equal Contribution)
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 @ericdexheimer.bsky.social* @ajdavison.bsky.social (*Equal Contribution)
Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map.
With @ericdexheimer.bsky.social* @ajdavison.bsky.social (*Equal Contribution)
February 25, 2025 at 5:34 PM
Open 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.
Wow I'd like to try to understand this.
Something for @tinytapeout.com ?
Something for @tinytapeout.com ?
tiny-gpu
A minimal GPU in Verilog optimized for learning about how GPUs work from the ground up.
Built with <15 files of fully documented Verilog, complete documentation on architecture & ISA, working matrix addition/multiplication kernels, and full support for kernel simulation & execution traces
A minimal GPU in Verilog optimized for learning about how GPUs work from the ground up.
Built with <15 files of fully documented Verilog, complete documentation on architecture & ISA, working matrix addition/multiplication kernels, and full support for kernel simulation & execution traces
February 11, 2025 at 9:47 AM
Wow I'd like to try to understand this.
Something for @tinytapeout.com ?
Something for @tinytapeout.com ?
Looks like a great workshop, happening in Malaga this July.
We're excited to announce the first Evolving Self-organisation workshop at GECCO 2025!
Submission deadline: March 26, 2025
More information: evolving-self-organisation-workshop.github.io
Submission deadline: March 26, 2025
More information: evolving-self-organisation-workshop.github.io
February 10, 2025 at 4:14 PM
Looks like a great workshop, happening in Malaga this July.
Gradually unfollowing all of the namesakes I picked up from that automatic X to Bluesky converter tool!
February 10, 2025 at 11:14 AM
Gradually unfollowing all of the namesakes I picked up from that automatic X to Bluesky converter tool!
Reposted by Andrew Davison
Forest Wanderings. 🌳
February 9, 2025 at 9:56 PM
Forest Wanderings. 🌳