SpAItial is pioneering physically-grounded world models, a groundbreaking AI paradigm that simulates virtual environments like the real world.
Joined April 2025
- Tweets173
- Following6
- Followers6.7K
- Likes319
Pinned Tweet
Introducing Echo-3. A state-of-the-art world model.
Echo-3 turns phone captures into photorealistic, metric-scale 3D worlds. From a single room to multi-floor buildings, outdoor and public spaces.
Available today.
Echo-3 actually works. Try it out today spaitial.ai/echo-3
After testing the new Echo-3 from @SpAItial_AI I am convinced Gaussian Splatting is a solved problem. So what's next?
Well, maybe not exactly solved yet for all use cases, but I think it will be in a matter of months.
Generating Gaussian Splats has become easier than ever. You can now do it with a consumer grade 360 camera, a phone, or with an AI world model that can generate high-quality environments that are also measurable and accurate in the real world, particularly for robotic simulation.
Of course, there are still applications where you need higher fidelity or better quality around specific objects. But those problems will probably be solved too.
The bigger problem now is the application.
The technology is moving much faster than companies are adopting it.
Now we need to figure out what comes next.
How do we turn these environments into meaningful, valuable experiences that people and companies can actually use?
That, to me, is where the interesting part of Gaussian Splatting starts and where not so many have an answer for.
RT @risingodegua: Answering some FAQ:
Can I try it without buying credits?
Yes! we give you a free months when you subscribe. Use it for…
This quoted post is unavailable.
SpAItial AI retweeted
The barrier to entry for 3D keeps plummeting. I’ve seen a lot of people pairing Astra with Blender for scans, but I think this will be stronger and much more photoreal.
Not to mention all the applications this opens up for Physical AI.
SpAItial AI retweeted
Today, we're launching Echo-3, our world model for reconstructing real spaces.
Key idea: treat reconstruction as conditional generation. The outputs are photorealistic 3DGS, point clouds, and meshes at metric scale -- only from a short iPhone video.
We believe this is an important step for physical AI, which is bottlenecked by real-world 3D data. When any phone can produce a metric digital twin, capture scales with phones rather than expensive scanning rigs, for robotics as much as for construction and real estate.
Echo-3 is also available via API: photos or video in, 3D worlds out. Check it out!
SpAItial AI retweeted
10 minutes with an iPhone, and this gorgeous craftsman house is now a 3D world you can walk through! It still blows my mind how easy Echo-3 makes this.
Go capture your favorite space 🙂 spaitial.ai/echo-3
SpAItial AI retweeted
With 𝐄𝐜𝐡𝐨-𝟑, you can turn the world around you into a 3D space 🌎
I scanned my apartment in less than 5 minutes, and the level of detail in the reconstruction is amazing! 😀
You can explore your space, ask questions about it, redesign it, and much more. Check below! 🤓👇
SpAItial AI retweeted
🌍 Introducing Echo-3, a new world model enabling the most accurate reconstructions of real spaces to date!
From a quick phone video of my daughter’s room, Echo-3 built a 3DGS model and restyled the whole house with her favorite fairy tales 🚀✨.
Get the app and try it out!
We’re also releasing a new capture app for Echo-3.
Capture a space with your phone, upload it, and get a 3D world.
Available now on the App Store spaitial.ai/echo-3
Enterprise customers can also access Echo-3 via our API. Reach out to [email protected]
Explore worlds captured on phones and reconstructed with Echo-3. From houses, cafes and museums to laboratories and industrial sites:
spaitial.ai/gallery
We're hiring PhD Research Interns at SpAItial♥️
Work with us on cutting-edge generative AI, including image & video diffusion, VLAs/WAMs, world models, and 3D scene generators.
Publish a paper at a top-tier conference for your PhD.
Interested? Apply here👇
We're looking for 3rd-year+ PhD students who have already published their first paper(s). Projects can be used for your PhD, potentially in collaboration with your advisor.
Duration: 5–7 months
Location: Munich or London (in person)
Application here: spaitial.ai/careers
We're hiring at SpAItial 🚀🚀🚀
Want to build AI that generates 3D worlds and understands their physics? 15 roles in London & Munich:
🧠 RS: World Models · 3D Diffusion · 3D Recon · Robot Learning
🛠️ RE: World Models · 3D Recon · Graphics
⚡ ML Infra · Inference
Join us 👇
Apply here: spaitial.ai/careers
Lots of exciting things happening now - stay tuned :)
SpAItial AI retweeted
SpAItial trains world models on Crusoe, over 97% scaling efficiency in benchmarks, with the control plane and NVIDIA Quantum InfiniBand networking managed for them. ⚡️
"We didn't have to do any performance optimizations." - @davnov134, Co-founder and CTO, @SpAItial_AI
↪ crusoe.ai/resources/customer…
SpAItial AI retweeted
I finally got my hands on @SpAItial_AI’s Echo. Here are my first 3 tests with just a single reference image. An outside urban area, a hotel room, and an expansive lake. I also toggled on the point view. None of these use Echo 2 high quality. What do you think?
#worldmodel #3dgs