Log inSign up
SpAItial AI
105 posts
user avatar
SpAItial AI
@SpAItial_AI
SpAItial is pioneering spatial foundation models (SFMs), a groundbreaking AI paradigm that generates virtual environments that behave like the real world.
spaitial.ai
Joined April 2025
4
Following
4,233
Followers

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

TermsยทPrivacyยทCookiesยทAccessibilityยทAds Infoยทยฉ 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    SpAItial AI
    @SpAItial_AI
    Apr 28
    ๐Ÿš€Echo-2 is here - our new world model! These arenโ€™t videos. These are ๐Ÿ‘๐ƒ ๐ฌ๐œ๐ž๐ง๐ž๐ฌ. Generated from a single image. - Stunning visual quality. - Real-time rendering. - Interactive camera control. - Physically grounded. ๐ŸงตMore details๐Ÿ‘‡
    00:00
    99K
  • user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 30
    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
    00:00
    2.7K
    user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 30
    Apply here: Startup Program spaitial.ai/startups Creative Partners spaitial.ai/creative-partnโ€ฆ We are accepting applications on a rolling basis.
    Startup Program โ€” SpAItial
    From spaitial.ai
    269
  • SpAItial AI reposted
    user avatar
    Matthias Niessner
    @MattNiessner
    Jun 25
    High-quality 3D reconstruction is still hard. In particular, with 3DGS, getting full coverage without occlusions is often impractical: training views can look great, but you can barely move around. With Echo-2, we take a different path: reconstruction as conditional generation.
    user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 25
    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.
    00:00
    22K
  • user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 25
    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.
    00:00
    27K
    user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 25
    Sign up for our API here and we will notify you when its available: developers.spaitial.ai/dashboard API docs: docs.spaitial.ai/api/getting-stโ€ฆ
    995
  • user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 22
    New from SpAItial. You can now: - Create 3D world directly from the Claude desktop app using the new SpAItial AI plugin - Create worlds with your agents using the SpAItial MCP. Works for Claude Code, Codex, OpenCode, VS Code, Windsurf etc Create, edit, refine your worlds
    00:00
    5.4K
    user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 22
    Install claude code plugin for desktop: github.com/spaitial-ai/spโ€ฆ Or Add our MCP server to your clients: docs.spaitial.ai/api/mcp-server
    GitHub - spaitial-ai/spaitial-ai-plugin: SpAItial plugins for Claude โ€” generate, manage, and export...
    From github.com
    432
  • SpAItial AI reposted
    user avatar
    RO2โšก๏ธ
    @risingodegua
    Jun 11
    A fun way to try the new Claude Fable. I asked it to train a bot using RL to navigate 3D worlds created with @SpAItial_AI. This is all running in the browser including RL training! Link to demo and code in comments What you can do: -> Train a bot from scratch, watch it learn
    00:00
    12K
  • user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 8
    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 ๐Ÿงต๐Ÿ‘‡
    00:25
    user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 2
    SplatArena: Multiplayer arena is LIVE ๐Ÿš€๐Ÿš€๐Ÿš€ Quake3-style combat. Drop in, frag your friends, and play on a world generated by Echo-2. Play now, directly in your browser: arena.spaitial.io
    4.5K
    user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 8
    The best part: it's all open source (GPLv2). Repo + local setup docs here ๐Ÿ‘‡ github.com/spaitial-ai/spโ€ฆ Build a map from your own .spz and run the whole stack locally. Point Cursor/Claude at the README and it'll walk you through setup.
    GitHub - spaitial-ai/spaitial_arena_community
    From github.com
    511
  • user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 8
    Replying to @SpAItial_AI
    This was made possible by amazing open source projects: -> @playcanvas โ€” splat rendering + splat-transform -> @agonesdev + @kubernetesio โ€” game-server orchestration -> Pion โ€” WebRTC -> ioquake3 + OpenArena โ€” engine + game data -> @NianticSpatial โ€” SPZ -> q3js โ€” the WASM lineage
    315
  • user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 8
    Replying to @SpAItial_AI
    The rendering trick: two stacked canvases. Back canvas = @playcanvas renders the photoreal splats (.sog, GPU sort, LOD). Front canvas is ioquake3 compiled to WASM draws players, weapons, HUD. The BSP is invisible, as it only does collision + depth so you don't shoot through
    187
    user avatar
    SpAItial AI
    @SpAItial_AI
    Jun 8
    Multiplayer is WebRTC. Signaling rides through the edge to an in-cluster proxy. Once ICE settles, media is a direct UDP DataChannel browser to game-server pod. One game = one Agones GameServer pod (q3ded) on Kubernetes, with warm pools per region across EU + US.
    154
  • SpAItial AI reposted
    user avatar
    Ricardo Martin-Brualla
    @rmbrualla
    Jun 7
    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 in๐Ÿงต
    00:00
    11K
  • SpAItial AI reposted
    user avatar
    Martin Valigursky
    @ValigurskyM
    Jun 7
    โ„๏ธ New @playcanvas engine example: real-time Depth of Field on Gaussian Splats, powered by the engine's post-processing stack โ€” with scene depth driven by a proxy mesh. Thanks to @SpAItial_AI for the Gaussian Splat + mesh generation ๐Ÿ™ Live link ๐Ÿ‘‡
    00:00
    6.2K
  • SpAItial AI reposted
    user avatar
    RO2โšก๏ธ
    @risingodegua
    Jun 6
    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,
    00:00
    22K
  • SpAItial AI reposted
    user avatar
    Jan Held
    @janheld14
    May 29
    Excited to share that our paper MeshSplatting received an Oral at CVPR 2026! ๐ŸŽ‰ Iโ€™ll be presenting the CVPR oral: ๐Ÿ—“ Friday, June 5 ๐Ÿ• 13:00 - 14:15 ๐Ÿ“Œ Mile High Ballroom 1A - 2A Have a look at meshsplatting.github.io for more information.
    00:00
    26K