@digitalurban
Account based inUnited Kingdom
About this account
- Account based in
- United Kingdom
- Connected via
- United Kingdom App Store
Account-level information from X, not a live location or the device used for a specific post.
Professor of Digital Urban Systems, UCL. FRSA, FRGS, FAcSS https://nitter.cf/t.co/mOmCPcufFA IoT, AR, VR, The Metaverse, Making T. @digitalurban.bsky.social
WC1E 7HB
Joined March 2007
- Tweets9.6K
- Following753
- Followers6.1K
- Likes2.4K
An aquarium where the fish tell the time
Live: digitalurban.org/Aqua_Clock_…
Code (MIT): github.com/digitalurban/Aqua…
New post - Color Weather, a new data watch face for the @Pebble Time 2 -
digitalurban.org/blog/2026/0…
I just backed Livegrid Aura: A Living Pixel Aquarium for Your Wall on @Kickstarter kickstarter.com/projects/liv…
Digital Urban has migrated from wordpress to GitHub - 1863 posts, 377k words over 21 years all archived with a new look and new system for whatever comes next in all things digital & cities digitalurban.org (with a new book Digital Cities of Tomorrow, incoming)...
The smooth "tween" that Weather Display Live had in the Flash era. Finally got it. These needles are a damped spring — ratio 0.8, deliberately underdamped, so they overshoot ~1.3% and settle like a moving-coil instrument. digitalurban.org/blog/2026/0…
Andrew Hudson-Smith retweeted
Academics can use AI-enabled music platforms to transform complex research into their own singles or albums reaching thousands of listeners. Andrew Hudson-Smith explains how: ow.ly/WWoY50YmRrW @digitalurban
Andrew Hudson-Smith retweeted
3D Gaussian splats deliver more realistic visuals than your average PS5 game! 🤯
Check out this grocery store. You can even read the labels on the products. And this wasn't painstakingly modelled by a 3D artist. It was captured in minutes with an @XGRIDS_OFFICIAL PortalCam.
Rendered in real-time by the @PlayCanvas Engine.
[1 / 2]
Andrew Hudson-Smith retweeted
Genie 3 just generated a playable Subway Surfers world from a SINGLE prompt.
The future of games is going to be ridiculous.
Step inside Project Genie: our experimental research prototype that lets you create, edit, and explore virtual worlds. 🌎
Readers added context they thought people might want to know
This is obviously not ai generated, it’s real game footage
apps.apple.com/fr/app/subway-…
Andrew Hudson-Smith retweeted
Photoreal 3D digital twins of vast natural habitats, this is whats coming!
It's been a fruitful journey so far attempting to bring reefs from the water to tangible digital assets you can interact with. Access the demo here: ben-williams-ai.github.io/
Andrew Hudson-Smith retweeted
A short tutorial on how to train directly on 360 equirectangular images in LichtFeld Studio with 3DGUT @janusch_patas
Conversion scripts for Metashape Standard and Pro versions here: github.com/gradeeterna/metas…
UCL East Professor turns to trance in new album | UCL East - UCL – University College London ucl.ac.uk/ucl-east/news/2025…
Andrew Hudson-Smith retweeted
This seems really cool: yunfan.zone/gswt_webpage/
Using gaussians for seamless tiling of vegetation over wide areas could work out really nice for games.
The New Album Place and Space youtube.com/playlist?list=OL… via @YouTube
Andrew Hudson-Smith retweeted
Today I vibe coded an AR game entirely within my Meta Quest 3, using Gemini 3. The holodeck is real!
Just go to gemini.google.com in the Meta browser, toggle canvas, and ask (via voice) for a WebXR app. Getting scene geometry took a few tries, but it basically just works.
Andrew Hudson-Smith retweeted
🗼 I’m excited to introduce 𝗖𝗶𝘁𝘆 𝗖𝗼𝗿𝗲 - 𝗣𝗮𝗿𝗶𝘀 🥐☕
𝐅𝐀𝐁 𝐋𝐢𝐧𝐤: fab.com/listings/9155a337-2c…
A large, highly detailed Unreal Engine pack I’ve been working on over the past year, inspired by classic Haussmann architecture.
#UnrealEngine #UnrealEngine5 #UE5 @fab
Andrew Hudson-Smith retweeted
Real estate giant @apartmentscom just added gaussian splatting support for exteriors under the name Matterport 3D Exterior
Andrew Hudson-Smith retweeted
After a year of team work, we're thrilled to introduce Depth Anything 3 (DA3)! 🚀
Aiming for human-like spatial perception, DA3 extends monocular depth estimation to any-view scenarios, including single images, multi-view images, and video.
In pursuit of minimal modeling, DA3 reveals two key insights:
💎 A plain transformer (e.g., vanilla DINO) is enough. No specialized architecture.
✨ A single depth-ray representation is enough. No complex 3D tasks.
Three series of models have been released: the main DA3 series, a monocular metric estimation series, and a monocular depth estimation series.
The core team members, aside from me: @HaotongLin, Sili Chen, Jun Hao Liew, @donydchen.
👇(1/n)
#DepthAnything3