🚀 𝗘𝗰𝗵𝗼-𝟮 𝗶𝘀 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲.🚀 🌍 Turn a single prompt or image into fully explorable 3D worlds. ✨ Imagine it. Create it. Share it. 🎮 Try it now and show me what you build. Link to my world: app.spaitial.ai/worlds/ade0e… #Echo2 #SpaitialAI #worldmodels

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

When triangles strike back as splatting primitives, I wondered: how well do they work on meshes, where traditional differentiable rasterizers are designed to excel? There’s still a gap—but Elastic Triangle Splatting is closing it. Interactive results: shenhanqian.github.io/ets

The synced map to world is one of the coolest feature of our viewer. I had fun building this out 😀 You can click anywhere on the map to jump to a point in the world World movement is tracked in real time on map Gives a really nice experience! shoutout to @playcanvas

Take videos of your house with your phone, and let Spaitial reconstruct it in 3D 😀🔥

Large, consistent, and high-quality 3D worlds from simple iPhone recordings. Works for multi-room scenes, fills missing gaps consistently while maintaining high quality, and it’s super easy to use. Now in beta with partners and coming soon to the SpAItial API. Link to the scenes in the comments so you can navigate this world yourself 👇🏽

Real-world capture is almost never complete. A missed corner, object, a room that didn't get enough viewpoints etc. leaving empty holes where the geometry should be. Our SOTA model Echo is built for that reality. It fills unscanned regions from surrounding visual context, so you still get a complete, explorable 3D world instead of broken voids. Incomplete capture shouldn't mean an incomplete experience.

Our SOTA world model, Echo, reconstructs high-quality scenes from sparse inputs and fills missing areas using its world knowledge. That means far less capture, data, and prep to produce geometrically consistent, multi-room reconstructions. We can’t wait to share it. Public release coming soon

Announcing the SpAItial Startup and Creative Partners Program for teams and creators building with world models. Accepted applicants get free credits, priority API access, early Echo model access, integration support, a direct feedback loop with the lab. We want real builders using Echo in real workflows so your feedback shapes what comes next. Application links in the comment 👇

Sparse captures in, complete worlds out. Echo reconstructs scenes from a small set of views, using world modeling priors to fill what sparse 3DGS leaves behind. Coming soon to the SpAItial API.

📣New Paper: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation. 🌐 flat-splat.github.io/ 🤗: huggingface.co/papers/2606.2… A feedforward latent scene decoder for generating explicit triangle-based 3D scenes from video diffusion latents.

Create 3D worlds easier than ever with our SpAItial plugin for your AI agent. Build 3D environments without ever leaving your chat🤖🔥

Photoreal walls. Real geometry. Bots. WebRTC and all open source. Here's how built a fully multiplayer, browser-playable Quake III arena where every level is a 3D world created from a single Image using Echo-2 🧵👇

Having a few hours this afternoon after @CVPR? Consider visiting Red Rocks 20 minutes outside of Denver! For some inspiration, here's a world processed by @SpAItial_AI Echo-2 HQ model from a single phone image! Link to the world in🧵

One step further towards the objective of murdering splats 🩸

Fun weekend project: using @AIatMeta Sam3 to segment objects inside a @SpAItial_AI scene. Pipeline: -> Generate a world on @SpAItial_AI app and export as .ply -> @playcanvas viewer to render splat + a uniform spatial grid over splat centers -> Capture frames + camera pose, POST to a local SAM3 server -> Lift each 2D mask → 3D: frustum-cull splats via the grid, reproject with the pose -> Recolor / isolate the segmented Gaussians This is all running locally on my Mac. Static scene, segment once, reuse persisted mask. All open source (link in comment), you can clone and build on top of this 👇🏽

Thanks Andrea 😁🔥

At #CVPR2026 this afternoon? Come find us at Poster 598! TrackMAE brings explicit motion supervision to masked video modeling through trajectory prediction and motion-aware masking. 📄 📷arxiv.org/abs/2603.27268 💻 github.com/rvandeghen/TrackM… 🤗 📷huggingface.co/rvandeghen/Tr…

Don't forget to stop by my oral presentation today during the session from 1:00 PM to 2:00 PM in Mile High Ballroom 1A-2A. Or come by later for the poster session and visit poster #14🚀

Third workshop for learning 3D with multi-view happening today at room 703 in the morning @CVPR #CVPR2026

The future of 3D is triangles!