Loading video...

Video Failed to Load

Go Home

Experimenting with image-to-world: creating consistent 3D environments from a single photo. As someone who studied architecture, this feels like a glimpse into the future of spatial creation and I’m excited to see where World Labs takes it.

XRarchitect's profile picture

Ian Curtis

26,049 subscribers

61,754 views • 1 year ago •via X (Twitter)

Science & TechnologyEducationArts
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

A short glimpse into the world of TORNBLADE. A few moments from the game as it takes shape. #indiedev #indiegame
0:14

A short glimpse into the world of TORNBLADE. A few moments from the game as it takes shape. #indiedev #indiegame

TORNBLADE game

66,719 views • 7 months ago

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”
0:18

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Bilawal Sidhu

92,886 views • 2 years ago

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.
0:12

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,849 views • 1 year ago

World Models are heating up as Prof. Fei-fei Li Fei-Fei Li's World Labs World Labs ignites the space with their first product Marble 🔥🌍 Riding that momentum, we’re launching a World Model demo on Theta Network EdgeCloud, powered by Tencent Tencent 腾讯's open-source Hunyuan 3D World Model, and packaged as a standard model template for creators, devs, and AI worldbuilders. Text/Image → explorable 3D worlds. Single image → full geometry. Exportable, editable, fast! Try it now:
0:11

World Models are heating up as Prof. Fei-fei Li Fei-Fei Li's World Labs World Labs ignites the space with their first product Marble 🔥🌍 Riding that momentum, we’re launching a World Model demo on Theta Network EdgeCloud, powered by Tencent Tencent 腾讯's open-source Hunyuan 3D World Model, and packaged as a standard model template for creators, devs, and AI worldbuilders. Text/Image → explorable 3D worlds. Single image → full geometry. Exportable, editable, fast! Try it now:

Jieyi Long | Theta Network

25,507 views • 9 months ago

Bring new robot testing environments to life with World Labs and Isaac Sim. 🤖 If you can describe a world 🌎, you can start testing in it the same day. Learn how to: 1. Export scenes from World Labs' Marble as Gaussian splats 2. Convert to USD using NVIDIA Omniverse NuRec 3. Import into NVIDIA Isaac Sim 4. Add a robot and run the simulation Read the guide ➡️ #SIGGRAPHAsia2025
0:12

Bring new robot testing environments to life with World Labs and Isaac Sim. 🤖 If you can describe a world 🌎, you can start testing in it the same day. Learn how to: 1. Export scenes from World Labs' Marble as Gaussian splats 2. Convert to USD using NVIDIA Omniverse NuRec 3. Import into NVIDIA Isaac Sim 4. Add a robot and run the simulation Read the guide ➡️ #SIGGRAPHAsia2025

NVIDIA Robotics

158,102 views • 8 months ago

Been experimenting with a similar technique lately Midjourney —&gt; Gaussian Splat So cool to see this generative AI video to 3D workflow. Excited to see where it’s headed
0:14

Been experimenting with a similar technique lately Midjourney —&gt; Gaussian Splat So cool to see this generative AI video to 3D workflow. Excited to see where it’s headed

Ian Curtis

127,552 views • 1 year ago

The new Victoria VR website is live. We continue to evolve our journey with AI. Victoria VR is more than a virtual world, it’s an AI-driven platform where creation is powered by intelligence itself. Imagine writing a single sentence and watching it become a living world. AI generates the architecture. AI populates it with avatars. AI gives them memory, logic, and awareness. This is creation redefined, where generative AI meets virtual reality, and imagination meets execution. Welcome to the foundation layer of the immersive internet. Discover the new Victoria VR: Victoria VR, a world where anything is possible.
0:12

The new Victoria VR website is live. We continue to evolve our journey with AI. Victoria VR is more than a virtual world, it’s an AI-driven platform where creation is powered by intelligence itself. Imagine writing a single sentence and watching it become a living world. AI generates the architecture. AI populates it with avatars. AI gives them memory, logic, and awareness. This is creation redefined, where generative AI meets virtual reality, and imagination meets execution. Welcome to the foundation layer of the immersive internet. Discover the new Victoria VR: Victoria VR, a world where anything is possible.

Victoria VR

176,796 views • 10 months ago

It is now possible to create 360 equirectangular VR 8K seamless videos from a single image! 😃 Theoretically Media World Labs #aivideo #VR
0:10

It is now possible to create 360 equirectangular VR 8K seamless videos from a single image! 😃 Theoretically Media World Labs #aivideo #VR

Daniel Skaale

52,025 views • 11 months ago

I think I just saw a glimpse of where ecommerce marketing is headed. I uploaded a photo of a pair of brown Martin boots into Pollo AI Marketing Studio, selected a UGC template, and within minutes got a video that looked like it came from a real creator partnership. No casting. No outreach. No back-and-forth revisions. No waiting days for content. As someone who's talked to ecommerce founders, I keep hearing the same problem: every new product needs new content, and scaling creator production is expensive and time-consuming. This feels like one of those AI use cases that's immediately practical. Not perfect. But good enough that it makes you rethink the entire content creation workflow. Turn a single product image into ready-to-publish marketing content with Pollo AI's Marketing Studio.
0:15

I think I just saw a glimpse of where ecommerce marketing is headed. I uploaded a photo of a pair of brown Martin boots into Pollo AI Marketing Studio, selected a UGC template, and within minutes got a video that looked like it came from a real creator partnership. No casting. No outreach. No back-and-forth revisions. No waiting days for content. As someone who's talked to ecommerce founders, I keep hearing the same problem: every new product needs new content, and scaling creator production is expensive and time-consuming. This feels like one of those AI use cases that's immediately practical. Not perfect. But good enough that it makes you rethink the entire content creation workflow. Turn a single product image into ready-to-publish marketing content with Pollo AI's Marketing Studio.

Oliver

39,654 views • 2 months ago

EVANIE congrats on your solo debut. it feels like just yesterday we were talking about this day and now it’s here 🤍 thank you for sharing a piece of yourself through your music and for creating something so genuine and meaningful. i’m proud of you and excited to see where this new chapter takes you 🫳🏻
0:13

EVANIE congrats on your solo debut. it feels like just yesterday we were talking about this day and now it’s here 🤍 thank you for sharing a piece of yourself through your music and for creating something so genuine and meaningful. i’m proud of you and excited to see where this new chapter takes you 🫳🏻

샐마•𝗘𝗡╸(rest)

18,476 views • 2 months ago

Today, we released Lyra 2.0, a framework for generating persistent, explorable 3D worlds at scale, from NVIDIA Research. Generating large-scale, complex environments is difficult for AI models. Current models often “forget” what spaces look like and lose track of movement over time, causing objects to shift, blur, or appear inconsistent. This prevents them from creating the reliable 3D environments required for downstream simulations. Lyra 2.0 solves these issues by: ✅ Maintaining per-frame 3D geometry to retrieve past frames and establish spatial correspondences ✅ Using self-augmented training to correct its own temporal drifting. Lyra 2.0 turns an image into a 3D world you can walk through, look back, and drop a robot into for real-time rendering, simulation, and immersive applications. ➡️ Learn more: 📄 Read the paper:
0:15

Today, we released Lyra 2.0, a framework for generating persistent, explorable 3D worlds at scale, from NVIDIA Research. Generating large-scale, complex environments is difficult for AI models. Current models often “forget” what spaces look like and lose track of movement over time, causing objects to shift, blur, or appear inconsistent. This prevents them from creating the reliable 3D environments required for downstream simulations. Lyra 2.0 solves these issues by: ✅ Maintaining per-frame 3D geometry to retrieve past frames and establish spatial correspondences ✅ Using self-augmented training to correct its own temporal drifting. Lyra 2.0 turns an image into a 3D world you can walk through, look back, and drop a robot into for real-time rendering, simulation, and immersive applications. ➡️ Learn more: 📄 Read the paper:

NVIDIA AI Developer

437,944 views • 4 months ago

.@spicyflowerhands This main challenge used only a promotional photo to model this virtual sculpture from a future world!! It showcases the design of an entire space for DEADLINE and LISA.
0:15

.@spicyflowerhands This main challenge used only a promotional photo to model this virtual sculpture from a future world!! It showcases the design of an entire space for DEADLINE and LISA.

LDN327

24,791 views • 6 months ago

What if you could turn a single 360° photo into a production-ready Isaac Sim environment in minutes? That's exactly what we did here. Using World Labs' Marble and an Insta360 X5 capture (rotating on top), we generated a complete navigable 3D environment and populated it with Lightwheel Sim Ready assets (bottom view). The result? A fully interactive scene in Isaac Sim, ready for sim2real testing,. Navigation, manipulation, or any robotics task you need to validate. What used to take weeks of manual 3D modeling and asset placement now takes minutes. Capture once in the real world, simulate everywhere in your training pipeline. This is the future of robotics development with world models. NVIDIA Robotics NVIDIA Omniverse #Sim2Real #Robotics #Simulation
0:15

What if you could turn a single 360° photo into a production-ready Isaac Sim environment in minutes? That's exactly what we did here. Using World Labs' Marble and an Insta360 X5 capture (rotating on top), we generated a complete navigable 3D environment and populated it with Lightwheel Sim Ready assets (bottom view). The result? A fully interactive scene in Isaac Sim, ready for sim2real testing,. Navigation, manipulation, or any robotics task you need to validate. What used to take weeks of manual 3D modeling and asset placement now takes minutes. Capture once in the real world, simulate everywhere in your training pipeline. This is the future of robotics development with world models. NVIDIA Robotics NVIDIA Omniverse #Sim2Real #Robotics #Simulation

Jonathan Stephens

46,643 views • 8 months ago

A Gaussian Splat can become a world where Robots and AI agents can act. In our latest OVER Research experiment, we placed a robot inside a real-world 3D capture, with a VLM making decisions based on what it sees. At every step, the robot holds a pose in the reconstruction, gets a newly rendered view of the environment, takes an action, moves, and sees the world again from its new position. Why does this matter? Because 3D captures can become more than reconstructions to explore. They can become environments where embodied AI and robots can navigate, act, be evaluated and eventually train across real-world spaces at scale. Capture a place once. Then turn it into a world where AI and Robots can act. The full experiment, including what we discovered once we actually put the loop to the test:
0:14

A Gaussian Splat can become a world where Robots and AI agents can act. In our latest OVER Research experiment, we placed a robot inside a real-world 3D capture, with a VLM making decisions based on what it sees. At every step, the robot holds a pose in the reconstruction, gets a newly rendered view of the environment, takes an action, moves, and sees the world again from its new position. Why does this matter? Because 3D captures can become more than reconstructions to explore. They can become environments where embodied AI and robots can navigate, act, be evaluated and eventually train across real-world spaces at scale. Capture a place once. Then turn it into a world where AI and Robots can act. The full experiment, including what we discovered once we actually put the loop to the test:

Over the Reality 🌐

14,841 views • 8 days ago

I think people are still underestimating how important the 3D layer could become in AI video. The problem with complex AI shots has never just been image quality. It’s spatial consistency, camera direction and knowing where everything is supposed to be. GPT-6 Astra can map the scene and keep camera + character paths within the Viewport, giving the shot a spatial structure before generation. I then manually move that scene into CapCut PC and use Seedance 2.5 to render it. From there, CapCut PC becomes the actual editing environment. That feels less like “AI generated a video” and more like a production pipeline worth experimenting with. #CapCutPC #GPT6Astra #AIVideo #Seedance25
0:12

I think people are still underestimating how important the 3D layer could become in AI video. The problem with complex AI shots has never just been image quality. It’s spatial consistency, camera direction and knowing where everything is supposed to be. GPT-6 Astra can map the scene and keep camera + character paths within the Viewport, giving the shot a spatial structure before generation. I then manually move that scene into CapCut PC and use Seedance 2.5 to render it. From there, CapCut PC becomes the actual editing environment. That feels less like “AI generated a video” and more like a production pipeline worth experimenting with. #CapCutPC #GPT6Astra #AIVideo #Seedance25

Manish Kumar Shah

30,785 views • 2 days ago

Huawei's new 3D lock screen wallpaper is actually pretty interesting. Unlike iPhone's Spatial Photo, which creates a fixed stereoscopic depth effect from a photo, this lets you scan an object 360°, generate a full 3D Gaussian Splatting asset, and use that as your lock screen. Tilt the phone and you're moving through a reconstructed 3D scene, not a fixed stereo image. The part worth paying attention to: 3D capture moving out of creative pipelines and into everyday phone personalization. That's a different kind of adoption curve.
0:16

Huawei's new 3D lock screen wallpaper is actually pretty interesting. Unlike iPhone's Spatial Photo, which creates a fixed stereoscopic depth effect from a photo, this lets you scan an object 360°, generate a full 3D Gaussian Splatting asset, and use that as your lock screen. Tilt the phone and you're moving through a reconstructed 3D scene, not a fixed stereo image. The part worth paying attention to: 3D capture moving out of creative pipelines and into everyday phone personalization. That's a different kind of adoption curve.

KIRI Engine - 3D Scanner App

186,235 views • 2 months ago

Experimenting with claymation today Kling AI 2.1 handing it like a champ. No prompt for this one I just put in the image to see where kling it would take it. More to come 😎👍
0:10

Experimenting with claymation today Kling AI 2.1 handing it like a champ. No prompt for this one I just put in the image to see where kling it would take it. More to come 😎👍

Captain HaHaa

42,576 views • 1 year ago

New vibecode project: 3D world generation on your phone ✨ Take a photo of a room or space, and transform it into a new style. Then generate a world you can explore. Made in Cursor using two new APIs - Flux.2 Klein (BlackForestLabsAI - Unofficial) and Marble (World Labs). How it works 👇
0:15

New vibecode project: 3D world generation on your phone ✨ Take a photo of a room or space, and transform it into a new style. Then generate a world you can explore. Made in Cursor using two new APIs - Flux.2 Klein (BlackForestLabsAI - Unofficial) and Marble (World Labs). How it works 👇

Justine Moore

42,665 views • 7 months ago