Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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... show more

SpAItial AI

4,736 subscribers

78,785 views • 1 month ago •via X (Twitter)

Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

26 Comments

SpAItial AI1 month ago

Explore these worlds reconstructed from iPhone capture

Bilawal Sidhu1 month ago

promising results! excited to try this. do y'all support 360 as an input as well?

SpAItial AI1 month ago

Yup!

A.W.E.S.O.M.-O 40001 month ago

This is seriously pushing single-phone 3D reconstruction into production-grade territory

Vincent Woo1 month ago

Hi can I be in the beta I made the grace cathedral splat

SpAItial AI1 month ago

yes, sign up as a creative partner here and we will reach out

Vincent Woo1 month ago

done!

Shreyash T1 month ago

Would be nice to see the original source footage used here so we can compare vs normal photogrammetry/splatting

Zan Gojcic1 month ago

Great results!

CAPT. Marcus Flemming1 month ago

I made this!! Can I get access?

SpAItial AI1 month ago

Please sign up for our creative partner program here and we will reach out

shreyans bhansali1 month ago

this is very cool, the highest quality scans of spaces I've seen. I would love to try this API! I have a specific app idea.

SpAItial AI1 month ago

Thanks! you can sign up for our creative partner programs here and we will reach out

shreyans bhansali1 month ago

great, done!

AI Mastery Guide1 month ago

iPhone to full 3D scans, that's impressive

SplatPaint1 month ago

Amazing - looks very promising 🤘

Kiru1 month ago

cc: @0xchromuh

Tariki1 month ago

#virtualrooms

Yannoid1 month ago

The lack of parallax on the windows, and no reflections on the shiny surfaces (baked POV) is pretty unusual for 3DGS. Is there a custom pipeline you guys got, or is this dataset preprocessed and could differ from what users can get on their sides with just an iPhone ? 🧐

TC1 month ago

Amazing for real estate! Any plans for further improvements to window views and reflections? They look a bit fake in these!

SpAItial AI1 month ago

Yes!

TC1 month ago

How do I try it?

Arnav Bhatia1 month ago

Can I use 360 video too ?

Brad Milne1 month ago

I’ve been using @Polycam3D for a while

Adam Hicks1 month ago

lets chat. this looks like a great fit for

Spenser Dickerson1 month ago

👀👀 💪💪

Related Videos

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

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

SpAItial AI

10,999 views • 2 months ago

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.

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.

SpAItial AI

29,124 views • 3 months ago

Introducing the SpAItial API to help you build immersive 3D worlds programmatically. You can now create world from text, image url, uploaded image, and 360 panorama with code. Track generation status, download results, export meshes and more. ⬇️

Introducing the SpAItial API to help you build immersive 3D worlds programmatically. You can now create world from text, image url, uploaded image, and 360 panorama with code. Track generation status, download results, export meshes and more. ⬇️

SpAItial AI

43,627 views • 4 months ago

3D AI is leveling up! Rodin 3D AI can create stunning, high-quality 3D models from just text or image inputs. And with its latest update, it can even generate 8K HDRI textures to bring your models to life. Check out the link in the comments!

3D AI is leveling up! Rodin 3D AI can create stunning, high-quality 3D models from just text or image inputs. And with its latest update, it can even generate 8K HDRI textures to bring your models to life. Check out the link in the comments!

el.cine

46,061 views • 1 year ago

oh my.. hows this even possible Meta just dropped SAM 3D, you can auto select any object in still image and.. turn them into high quality 3D model the model is free to download and test in playground link in comments

oh my.. hows this even possible Meta just dropped SAM 3D, you can auto select any object in still image and.. turn them into high quality 3D model the model is free to download and test in playground link in comments

el.cine

795,982 views • 10 months ago

Removing stickers from large windows is surprisingly easy and satisfying. However, this seems to be due to the high-quality material of the stickers, making them easy to remove

Removing stickers from large windows is surprisingly easy and satisfying. However, this seems to be due to the high-quality material of the stickers, making them easy to remove

icel 🥟

67,224 views • 5 months ago

Turned my real world 360 images into 3d scenes with World Labs. You can use the built-in editing tools to stitch them together into large-scale 3d worlds - then use them as virtual set for your AI videos, games and VR experiences. The holodeck is much closer than you think.

Turned my real world 360 images into 3d scenes with World Labs. You can use the built-in editing tools to stitch them together into large-scale 3d worlds - then use them as virtual set for your AI videos, games and VR experiences. The holodeck is much closer than you think.

Bilawal Sidhu

27,928 views • 10 months ago

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 in minutes, then drop it into a world it has never seen and it keeps navigating obstacles. -> The worlds are real scenes generated from a text prompt or a photo via the SpAItial AI API (you get a splat + a collision mesh). -> Mesh is made into a 2D walkability + height grid that the RL environment runs on. -> The trick to generalization: the policy only ever sees egocentric inputs. A 16-ray lidar, the goal's body frame, and its speed. No global coordinates, no map. So it learns navigation, not a memorized world.

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 in minutes, then drop it into a world it has never seen and it keeps navigating obstacles. -> The worlds are real scenes generated from a text prompt or a photo via the SpAItial AI API (you get a splat + a collision mesh). -> Mesh is made into a 2D walkability + height grid that the RL environment runs on. -> The trick to generalization: the policy only ever sees egocentric inputs. A 16-ray lidar, the goal's body frame, and its speed. No global coordinates, no map. So it learns navigation, not a memorized world.

RO2⚡️

12,797 views • 3 months ago

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

Santiago

65,446 views • 5 months ago

Gemini Omni is coming to Zeely 👀 Soon, you'll create AI ads in gamified worlds, from Minecraft-inspired scenes to fantasy adventures. Better yet, you can turn yourself into the hero of the story. Comment "GAME" to grab 500 free credits and try it for yourself.

Gemini Omni is coming to Zeely 👀 Soon, you'll create AI ads in gamified worlds, from Minecraft-inspired scenes to fantasy adventures. Better yet, you can turn yourself into the hero of the story. Comment "GAME" to grab 500 free credits and try it for yourself.

Zeely AI

134,054 views • 3 months ago

We want Unreal Engine 5.6 to scale to large and rich worlds while preserving graphic quality and delivering 60 FPS. What better world to do this in than that of The Witcher? Tap in:

We want Unreal Engine 5.6 to scale to large and rich worlds while preserving graphic quality and delivering 60 FPS. What better world to do this in than that of The Witcher? Tap in:

Unreal Engine

134,849 views • 1 year ago

Speech-02 from MiniMax Design (H3) is now live—and it’s a great tool to use alongside Hedra for high-quality voice-driven content. Create voiceovers in 30+ languages with natural tone and expressive delivery, then upload them into Hedra to turn your audio into rich, visual content for characters, scenes, and stories. Try it out and see what you can create.

Speech-02 from MiniMax Design (H3) is now live—and it’s a great tool to use alongside Hedra for high-quality voice-driven content. Create voiceovers in 30+ languages with natural tone and expressive delivery, then upload them into Hedra to turn your audio into rich, visual content for characters, scenes, and stories. Try it out and see what you can create.

Hedra

399,697 views • 1 year ago

Thanks to Sean Riddle’s high-quality scan and trace of the Super Mario Nelsonic watch display, the complete emulation is now ready. You can play it at the link

Thanks to Sean Riddle’s high-quality scan and trace of the Super Mario Nelsonic watch display, the complete emulation is now ready. You can play it at the link

azya

12,906 views • 1 year ago

📸 A few photos. ⚡ A few seconds. A high-quality 3D scene！🎬 Meet Topos-Lite, our new 3D Gaussian Splatting model. With just a few sparse multi-view images, it can generate a high-quality, renderable 3D scene in few seconds We’re excited to share more soon. The technical report is coming shortly — stay tuned and stay in touch. 👀 #ToposLite #3DGS #3DGeneration #SpatialAI #AIGC #photograph #3DArtwork

📸 A few photos. ⚡ A few seconds. A high-quality 3D scene！🎬 Meet Topos-Lite, our new 3D Gaussian Splatting model. With just a few sparse multi-view images, it can generate a high-quality, renderable 3D scene in few seconds We’re excited to share more soon. The technical report is coming shortly — stay tuned and stay in touch. 👀 #ToposLite #3DGS #3DGeneration #SpatialAI #AIGC #photograph #3DArtwork

InSpatio｜影溯

23,176 views • 2 months ago

Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.

Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, metric 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.

Linyi Jin

94,683 views • 1 year ago

Nvidia presents Edify 3D! The method can generate high-quality 3D assets from text descriptions. It uses a diffusion model to create detailed quad-mesh topologies and high-resolution textures in under 2 minutes.

Nvidia presents Edify 3D! The method can generate high-quality 3D assets from text descriptions. It uses a diffusion model to create detailed quad-mesh topologies and high-resolution textures in under 2 minutes.

Dreaming Tulpa 🥓👑

39,523 views • 1 year ago

I just added 3D low-poly model generation to Retro Diffusion! Create super high quality low poly models with pixel art textures in minutes. Then animate them however you want with just a prompt! Check it out on the site and the API/MCP!

I just added 3D low-poly model generation to Retro Diffusion! Create super high quality low poly models with pixel art textures in minutes. Then animate them however you want with just a prompt! Check it out on the site and the API/MCP!

Astropulse

28,901 views • 11 days ago

I did an experiment to get an improvement to sprite rotation quality while maintaining the retro vibe, in #UnrealEngine. I works with any type of 3D transformed object too. And it still respects the scanlines, so it will fit in correctly with CRT filters. #gamedev #pixelart

I did an experiment to get an improvement to sprite rotation quality while maintaining the retro vibe, in #UnrealEngine. I works with any type of 3D transformed object too. And it still respects the scanlines, so it will fit in correctly with CRT filters. #gamedev #pixelart

MarcDWyz🕹️ #GameDev

14,756 views • 9 months ago

🚨 If you were Shocked and Horrified by the recently released Epstein Files, sorry to break it to you but.. The High Quality image is in the comments.

🚨 If you were Shocked and Horrified by the recently released Epstein Files, sorry to break it to you but.. The High Quality image is in the comments.

T R U T H P O L E

4,978,813 views • 7 months ago

"We need to get the next million developers into the blockchain industry to build the way they are used to in Web2—quickly, at a very high quality, and with easy-to-use applications."—Sergey Nazarov #CCIP

"We need to get the next million developers into the blockchain industry to build the way they are used to in Web2—quickly, at a very high quality, and with easy-to-use applications."—Sergey Nazarov #CCIP

Chainlink

49,818 views • 3 years ago