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.

Atlas beta access is rolling out to users, some ideas for API developers - give Astra "eyes" in Blender, let it place and render new camera views with Atlas - 3D reconstruction (this video uses 9 image inputs of my studio to make a scene, any Zillow apartment works)... show more

neilson

4,962 subscribers

47,285 views • 1 month ago •via X (Twitter)

Gaming Science & Technology

Anya Rossi• Live Now

Private livecam show

14 Comments

neilson1 month ago

inspo from one of our internal tools on how to render point clouds, display images, and create camera paths

Kevin Lin1 month ago

da journaling den

MidnightSun1 month ago

@drfeifei Nice, ImageNet taught machines to see pictures. Atlas is teaching them to live in rooms.

Ian Curtis1 month ago

watched for a couple mins before i noticed it looped 😅

clankr1 month ago

It is a truly great idea to combine Atlas and Astra to boost real2sim topic. If you also add a zero-shot transformer 3D asset generator like SAM3D to this pipeline 🤌

Dave Matthews1 month ago

@BenMildenhall Any tips to getting an earlier invite? :) I have a big set of videos of messy/clean kitchens and this looks like the most promising approach I’ve seen for modeling those details.

Ryan McAdams1 month ago

@drfeifei Let’s goooooo!

John Amadeo1 month ago

@BenMildenhall When do you think everyone who signed up for the waitlist will get access 🙂

ethereagle · building1 month ago

9 stills of a studio. when you orbit behind the desk, does Atlas invent the occluded side or leave a hole? that's what decides if a Zillow listing is actually usable.

AI Mastery Guide1 month ago

9 images to rebuild a room, cool

ButtMatrix1 month ago

what's the cook time for a splat / scene like this one?

RAZA | AI EXPLORER1 month ago

So many exciting possibilities for 3D workflows and API developers.

Ben Barrey1 month ago

👀

Delayed Gratification 🛑🔨🕒1 month ago

I applied to try it out, have some ideas I would like to use it on.

Related Videos

We’re opening up access to Atlas to everyone today. We’ve built apps and API endpoints to help you use Atlas any way you can imagine: bring your ideas for building a 3D world and come away with keyframes, video clips, or 3D Gaussian splats.

We’re opening up access to Atlas to everyone today. We’ve built apps and API endpoints to help you use Atlas any way you can imagine: bring your ideas for building a 3D world and come away with keyframes, video clips, or 3D Gaussian splats.

World Labs

306,082 views • 17 hours ago

Experimenting with Chisel in Atlas beta. We’ve been rolling out beta access to a bunch of users and it’s been really cool seeing what people are building.

Experimenting with Chisel in Atlas beta. We’ve been rolling out beta access to a bunch of users and it’s been really cool seeing what people are building.

Brittani Natali

17,993 views • 1 month ago

Check out CAT3D! Image(s)-to-3D in 1 minute! Given any number of real or generated images, CAT3D uses a multi-view diffusion prior to create consistent novel views. These views are used to reconstruct a 3D scene using NeRF/3DGS.

Check out CAT3D! Image(s)-to-3D in 1 minute! Given any number of real or generated images, CAT3D uses a multi-view diffusion prior to create consistent novel views. These views are used to reconstruct a 3D scene using NeRF/3DGS.

Philipp Henzler

12,752 views • 2 years ago

With Atlas, you can literally make films. And it also basically solves first-frame-last-frame transitions. Reconstruct a 3D scene from images, then position the camera exactly where you want it, and let Atlas fill in what the camera would see along that path. You’re in the director's chair, staging the scene. Here we made a 1 min video with a couple images of totally different scenes, and we set where the camera keyframes should move through each part of the scene. The scene-to-scene transitions are great. Atlas makes it feel like a smooth shot with no cuts.

With Atlas, you can literally make films. And it also basically solves first-frame-last-frame transitions. Reconstruct a 3D scene from images, then position the camera exactly where you want it, and let Atlas fill in what the camera would see along that path. You’re in the director's chair, staging the scene. Here we made a 1 min video with a couple images of totally different scenes, and we set where the camera keyframes should move through each part of the scene. The scene-to-scene transitions are great. Atlas makes it feel like a smooth shot with no cuts.

David Pantera

27,621 views • 2 months ago

a few space scenes made with atlas. each one started from a single image. atlas generates the video as the camera moves, including the parts of the scene that weren’t in the original image. orange = input image in 3D space blue = camera moving through the scene

a few space scenes made with atlas. each one started from a single image. atlas generates the video as the camera moves, including the parts of the scene that weren’t in the original image. orange = input image in 3D space blue = camera moving through the scene

Ian Curtis

10,626 views • 28 days ago

our new model Atlas also happens to be a capable text-to-image generator, providing it with a strong foundation of “world knowledge”... this generalizes across both single and multi view domains, meaning you can step into even highly stylized scenes with precise 3D control

our new model Atlas also happens to be a capable text-to-image generator, providing it with a strong foundation of “world knowledge”... this generalizes across both single and multi view domains, meaning you can step into even highly stylized scenes with precise 3D control

Ben Mildenhall

105,150 views • 2 months ago

Block out a world. Let Atlas bring it to life. A sneak peek at Chisel, now in Atlas beta.

Block out a world. Let Atlas bring it to life. A sneak peek at Chisel, now in Atlas beta.

World Labs

50,543 views • 1 month ago

Two of us filmed this on a couple phones, and we used Atlas to turn it into a short film. This is just a clip from the World Labs tech blog Atlas is able to generate the parts of the scene that none of the cameras actually filmed. It can freeze time, allowing you to reframe shots to positions never filmed, then resume. View events from impossible angles because Atlas knows what was there.

Two of us filmed this on a couple phones, and we used Atlas to turn it into a short film. This is just a clip from the World Labs tech blog Atlas is able to generate the parts of the scene that none of the cameras actually filmed. It can freeze time, allowing you to reframe shots to positions never filmed, then resume. View events from impossible angles because Atlas knows what was there.

David Pantera

956,435 views • 2 months ago

📢Introducing 360Anything, our method for lifting any perspective image or video to gravity-aligned 360° panoramas without using any camera or 3D information. This enables consistent novel view synthesis and 3D scene reconstruction. Project page: 🧵

📢Introducing 360Anything, our method for lifting any perspective image or video to gravity-aligned 360° panoramas without using any camera or 3D information. This enables consistent novel view synthesis and 3D scene reconstruction. Project page: 🧵

Ziyi Wu

64,124 views • 9 months ago

There’s been massive progress in agentic 3D world creation in the past year, but producing polished, high fidelity pixels purely procedurally via code is still orders of magnitude more expensive than generating them directly. I view these strategies as complementary – in our Atlas release today, both the Chisel web app and Codex/Claude Code integrations are designed for using an agent to build out coarse geometry in 3D and control precise final pixel generation through Atlas model endpoints. This demo showcases the Chisel variant of Atlas we finetuned for flexible control, capable of taking in any combination of partial RGB and partial depth frames. We can take masked depth renders of the car model and use text prompting to control both stylistic appearance and what fills in the rest of the scene.

There’s been massive progress in agentic 3D world creation in the past year, but producing polished, high fidelity pixels purely procedurally via code is still orders of magnitude more expensive than generating them directly. I view these strategies as complementary – in our Atlas release today, both the Chisel web app and Codex/Claude Code integrations are designed for using an agent to build out coarse geometry in 3D and control precise final pixel generation through Atlas model endpoints. This demo showcases the Chisel variant of Atlas we finetuned for flexible control, capable of taking in any combination of partial RGB and partial depth frames. We can take masked depth renders of the car model and use text prompting to control both stylistic appearance and what fills in the rest of the scene.

Ben Mildenhall

15,846 views • 15 hours ago

Omar Alama عمر الأعمى tried GPT 6 Astra Xhigh to recreate this from World Labs's Atlas - and 👀 🤯 Video shows the blender reconstruction and fun fact ... Astra used COLMAP! 😳 and pulled the floor plan via search! 🧵👇 They really did train with tons of 3D tool data!!

Omar Alama عمر الأعمى tried GPT 6 Astra Xhigh to recreate this from World Labs's Atlas - and 👀 🤯 Video shows the blender reconstruction and fun fact ... Astra used COLMAP! 😳 and pulled the floor plan via search! 🧵👇 They really did train with tons of 3D tool data!!

Nikhil Keetha

10,643 views • 2 months ago

i made AnyScene to build any scene in an hour. i built AnyShot to render those scenes in a few minutes. on my RTX 5070 Ti, a single walkthrough like this takes 6 hours to render. AnyShot fans it out across up to 100 RTX 5090s on fal and renders it in 3 minutes. but it’s not just a render farm. point it at any Blender scene, give it a brief, and an AI cinematographer plans every camera move, checks it never clips through the set, pulls focus, and shoots it. like AnyScene, AnyShot is open source

i made AnyScene to build any scene in an hour. i built AnyShot to render those scenes in a few minutes. on my RTX 5070 Ti, a single walkthrough like this takes 6 hours to render. AnyShot fans it out across up to 100 RTX 5090s on fal and renders it in 3 minutes. but it’s not just a render farm. point it at any Blender scene, give it a brief, and an AI cinematographer plans every camera move, checks it never clips through the set, pulls focus, and shoots it. like AnyScene, AnyShot is open source

apek

16,246 views • 11 days ago

Lyria 3, our music model is here! 🎶 Generate music from text, image, or even a video. Rolling out to users globally in the Gemini app today, and coming to our API and AI Studio very soon :)

Lyria 3, our music model is here! 🎶 Generate music from text, image, or even a video. Rolling out to users globally in the Gemini app today, and coming to our API and AI Studio very soon :)

Ammaar Reshi

29,074 views • 8 months ago

Atlas lets you build out large 3D environments starting from a single input image. You can then define a camera path through the world and generate a video along it. Here’s how the 3D structure, camera path and final flythrough connect.

Atlas lets you build out large 3D environments starting from a single input image. You can then define a camera path through the world and generate a video along it. Here’s how the 3D structure, camera path and final flythrough connect.

World Labs

22,174 views • 21 days ago

Midjourney-to-3D is now available! (Indeed, you can convert any 2D image to 3D) Please note that, for now, you'll need to manually set a depth map for your image in order to view its correct 3D version. (You can use to generate the depth map) But... stay tuned! We'll soon be offering instant 3D conversion for any image. *This is just an experimental version, and any feedback or videos of your results would be really interesting to see!

Midjourney-to-3D is now available! (Indeed, you can convert any 2D image to 3D) Please note that, for now, you'll need to manually set a depth map for your image in order to view its correct 3D version. (You can use to generate the depth map) But... stay tuned! We'll soon be offering instant 3D conversion for any image. *This is just an experimental version, and any feedback or videos of your results would be really interesting to see!

Cristian Peñas ░░░░░░░░

445,506 views • 3 years ago

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization.

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization.

Stability AI

197,625 views • 1 year ago