正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

🌍 Introducing Echo-3, a new world model enabling the most accurate reconstructions of real spaces to date! From a quick phone video of my daughter’s room, Echo-3 built a 3DGS model and restyled the whole house with her favorite fairy tales 🚀✨. Get the app and try it out!

David Novotny

1,554 subscribers

162,137 次观看 • 7 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

39 条评论

Bilawal Sidhu 的头像

Bilawal Sidhu7 天前

reskinning room results look great!

xiaopengyou 的头像

xiaopengyou7 天前

only apple? how to use it by api or web for production?

David Novotny 的头像

David Novotny7 天前

Yes Android is coming soon. So does the api

Matthias Niessner 的头像

Matthias Niessner7 天前

Restyling is pretty cool - can finally live in my dream world :)

Costa Creates 的头像

Costa Creates7 天前

This is the coolest shit I’ve seen

Brock Robinson 🇺🇸 的头像

Brock Robinson 🇺🇸7 天前

This is a preview of how people in the future will change their own realities. They will get to live in worlds of their own choosing.

Stateofnoise 的头像

Stateofnoise7 天前

This in realtime on a Vision Pro 😍

Rex 🐾🦴 🔜 MFF 的头像

Rex 🐾🦴 🔜 MFF7 天前

open-source?

Tone Elt 的头像

Tone Elt7 天前

Is this a Gaussian mesh hybrid approach?

Boe 的头像

Boe7 天前

A lot of people would love something like this in VR as an upgrade/alternative to Hyperscape. Would you consider optimizing and syncing the splat outputs to a Quest app? If the results are as impressive as in the video, this would be big. DM to talk more.

Art Manbaby 的头像

Art Manbaby7 天前

Add VR and I'm living in a Monet

Pamir 的头像

Pamir6 天前

I imagine this can work in real-time with an AR headset, let's say when a prospective buyer is touring an apartment?

lmnek 的头像

lmnek7 天前

wow, super cool! Will it be possible to also regenerate shapes of the splats? (e.g. adding in a piece of furniture)

Joel 的头像

Joel7 天前

@angelaqdai Would love to try, just not willing to pay a high fee to see if the results match the hype

Biff Buster 的头像

Biff Buster7 天前

Insane

AM 🫗🫘 的头像

AM 🫗🫘7 天前

@SadlyItsBradley

josh 的头像

josh7 天前

Link ?

David Novotny 的头像

David Novotny7 天前

Sure, you can get the app here:

ustare 的头像

ustare6 天前

love it ...could you make it mcp or api for indoor? i badly need it in my production...

David Novotny 的头像

David Novotny6 天前

Yes! Api coming soon!

Wayne Schillo 的头像

Wayne Schillo7 天前

First one free, without having to do the trial would be nice, to try it out.

𝛼 的头像

𝛼7 天前

damn

PapaJoe 的头像

PapaJoe6 天前

🤯

David 的头像

David6 天前

Man, I’m digging that restyle! I’ve gotta try this 🎨

光速的头像

光速6 天前

如果移动端设备（平板、手机）算力性能可以支持的话，那玩法就更多了

Kent 的头像

Kent7 天前

#chefcheck is this safe

splatsandworlds 的头像

splatsandworlds6 天前

Very cool! Is the restyling happening directly on the 3D splat, or are you generating new views and reconstructing it again?

Vic Voice 的头像

Vic Voice7 天前

Wow! Looks incredible! Does it only work with phone captures or can it create 3D worlds from any reference images?

David Novotny 的头像

David Novotny7 天前

The api is coming soon, contact [email protected] for more info

MetaDJ 的头像

MetaDJ6 天前

Awesome ✨

Sherman Li 的头像

Sherman Li7 天前

Wow cool! What 3DGS tools do you use?

AI 百球哥的头像

AI 百球哥7 天前

Looks really cool, but can this world model with its structure move around? And how about its physics properties?

Ishika ✧ 的头像

Ishika ✧6 天前

now this is what we call a banger🔥

Boardy 的头像

Boardy7 天前

know someone who runs dev strategy for a 3D geospatial platform and has been building toward phone-to-3D capture. couldn't get a DM through so say the word here and i'll make the intro.

Rami 的头像

Rami7 天前

The camera angle looks like my pixel 10 pro on .5 zoom

ArcyDev 的头像

ArcyDev6 天前

5 years ago, I would've been impressed. Today, I still am. 5 years from now, I won't be.

Gautam 的头像

Gautam7 天前

when it would be available via api?

David Novotny 的头像

David Novotny7 天前

Its on the way, will be released soon

Deb 的头像

Deb7 天前

How are you downloading the ply? The app doesn’t let me.

相关视频

Introducing Echo-3. A state-of-the-art world model. Echo-3 turns phone captures into photorealistic, metric-scale 3D worlds. From a single room to multi-floor buildings, outdoor and public spaces. Available today.

Introducing Echo-3. A state-of-the-art world model. Echo-3 turns phone captures into photorealistic, metric-scale 3D worlds. From a single room to multi-floor buildings, outdoor and public spaces. Available today.

SpAItial AI

317,446 次观看 • 7 天前

I like to do a quick scan when i go anywhere, because why not 😁. This hotel room took me around 4minutes to scan and Echo-3 reconstructed it perfectly. View the world here Try Echo-3

I like to do a quick scan when i go anywhere, because why not 😁. This hotel room took me around 4minutes to scan and Echo-3 reconstructed it perfectly. View the world here Try Echo-3

RO2⚡️

17,543 次观看 • 3 天前

We are releasing Echo-3 today. Its the best model in the world at 3D world reconstruction. Believe it or not, this world below was generated from just an iPhone capture, no specialize capture hardware needed. You scan a space with an iPhone and Echo-3 reconstructs it in super high quality while keeping metric consistent. Think of the possibilities. Try it today at with our app SpAItial AI

We are releasing Echo-3 today. Its the best model in the world at 3D world reconstruction. Believe it or not, this world below was generated from just an iPhone capture, no specialize capture hardware needed. You scan a space with an iPhone and Echo-3 reconstructs it in super high quality while keeping metric consistent. Think of the possibilities. Try it today at with our app SpAItial AI

RO2⚡️

27,556 次观看 • 7 天前

Introducing the new SpAItial app to help you create with Echo-2, our newest frontier world model. 🖼️ Upload an image. 🖊️ Describe a scene. 🌐 Get a navigable 3D world. Edit and refine until it's just right. Export and use in your 3D pipeline. Try it today → Share what you build! we'll be featuring the best ones.

Introducing the new SpAItial app to help you create with Echo-2, our newest frontier world model. 🖼️ Upload an image. 🖊️ Describe a scene. 🌐 Get a navigable 3D world. Edit and refine until it's just right. Export and use in your 3D pipeline. Try it today → Share what you build! we'll be featuring the best ones.

SpAItial AI

10,765 次观看 • 6 个月前

A new chapter of creativity begins. Introducing GEN-3 Alpha - The first of a series of new models built by creatives for creatives. Video generated with Runway's new Text-2-Video model. Coming soon.

A new chapter of creativity begins. Introducing GEN-3 Alpha - The first of a series of new models built by creatives for creatives. Video generated with Runway's new Text-2-Video model. Coming soon.

Nicolas Neubert

112,271 次观看 • 2 年前

🔊 Introducing the next generation of AI-powered Echo devices, purpose-built for Alexa+. With custom AZ silicon and our Omnisense sensor fusion platform, these are the most advanced Echo devices ever. And, they come with Alexa+ right out of the box.

🔊 Introducing the next generation of AI-powered Echo devices, purpose-built for Alexa+. With custom AZ silicon and our Omnisense sensor fusion platform, these are the most advanced Echo devices ever. And, they come with Alexa+ right out of the box.

Amazon

70,733 次观看 • 1 年前

🚀 Announcing Echo — our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world — not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly — even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering — but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows — digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations — all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction — environments that don’t just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. 🌍 #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out:

🚀 Announcing Echo — our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world — not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly — even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering — but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows — digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations — all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction — environments that don’t just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. 🌍 #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out:

SpAItial AI

177,689 次观看 • 10 个月前

Introducing Character World Model-1 the most controllable interactive avatar model in the world Features and how we built it 👇️

LemonSlice

89,873 次观看 • 1 个月前

We’re introducing major updates to Gemini in @GoogleChrome for MacOS, Windows and Chromebook Plus. Built on Gemini 3, our most intelligent model, these powerful new AI features can help you multitask more easily and get the most out of the web 🧵

We’re introducing major updates to Gemini in @GoogleChrome for MacOS, Windows and Chromebook Plus. Built on Gemini 3, our most intelligent model, these powerful new AI features can help you multitask more easily and get the most out of the web 🧵

Google

2,160,324 次观看 • 9 个月前

What a time to be alive. Pulled the map of my house from the vaccum, built a 3D model with all the devices in my house and now I can literally play with my lights like I’m in Official Lagos Life App Need to find a way to get in here

What a time to be alive. Pulled the map of my house from the vaccum, built a 3D model with all the devices in my house and now I can literally play with my lights like I’m in Official Lagos Life App Need to find a way to get in here

JO⚡️🇬🇭

141,354 次观看 • 17 天前

Odyssey launches Odyssey-3, a foundation world model that sets a new state of the art on Physics-IQ Verified (66.1) for video-to-video physical simulation. The same pretrained model generates real-time interactive environments from prompts and adapts to control robots, humanoids, cars, and drones with limited task-specific data.

Odyssey launches Odyssey-3, a foundation world model that sets a new state of the art on Physics-IQ Verified (66.1) for video-to-video physical simulation. The same pretrained model generates real-time interactive environments from prompts and adapts to control robots, humanoids, cars, and drones with limited task-specific data.

Documenting AGI

38,907 次观看 • 26 天前

Introducing Veo 2, our new, state-of-the-art video model (with better understanding of real-world physics & movement, up to 4K resolution). You can join the waitlist on VideoFX. Our new and improved Imagen 3 model also achieves SOTA results, and is coming today to 100+ countries in ImageFX.

Introducing Veo 2, our new, state-of-the-art video model (with better understanding of real-world physics & movement, up to 4K resolution). You can join the waitlist on VideoFX. Our new and improved Imagen 3 model also achieves SOTA results, and is coming today to 100+ countries in ImageFX.

Sundar Pichai

4,574,637 次观看 • 1 年前

We’re creating a 4D living model of the real world. From indoor spaces to entire cities, Niantic Spatial is turning the physical world into accurate, high-resolution 3D models. Captured by Spexi. Reconstructed by Niantic Spatial. Explore what’s possible: #Scaniverse #3DReconstruction #SpatialAI #GaussianSplat #DigitalTwins #DroneImagery #3DGS #AI

We’re creating a 4D living model of the real world. From indoor spaces to entire cities, Niantic Spatial is turning the physical world into accurate, high-resolution 3D models. Captured by Spexi. Reconstructed by Niantic Spatial. Explore what’s possible: #Scaniverse #3DReconstruction #SpatialAI #GaussianSplat #DigitalTwins #DroneImagery #3DGS #AI

Niantic Spatial 🌎

26,367 次观看 • 7 天前

Odyssey is now previewing Odyssey-3, a world model that it calls a Physics Agent! The model was designed to learn how the world behaves from visual observation and then apply that understanding to control both real and simulated systems. Odyssey-3 can run across different machines and games, with a small amount of task-specific experience teaching it each set of controls. The preview covers humanoids, robot arms, a car and a drone being controlled by an AI model, playable video games, and training runs for other AI agents.

Odyssey is now previewing Odyssey-3, a world model that it calls a Physics Agent! The model was designed to learn how the world behaves from visual observation and then apply that understanding to control both real and simulated systems. Odyssey-3 can run across different machines and games, with a small amount of task-specific experience teaching it each set of controls. The preview covers humanoids, robot arms, a car and a drone being controlled by an AI model, playable video games, and training runs for other AI agents.

🚨 AI News | TestingCatalog

23,779 次观看 • 1 个月前

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks

Yinghao Xu

47,813 次观看 • 9 个月前

1/7: 📢 Big release! Introducing Astra 2 🚀 Our next-gen creative model with a whole new level of controls, including PROMPTS! Try it NOW in Astra app See what it's best for in this short video and 🧵👇

1/7: 📢 Big release! Introducing Astra 2 🚀 Our next-gen creative model with a whole new level of controls, including PROMPTS! Try it NOW in Astra app See what it's best for in this short video and 🧵👇

Topaz Labs

2,626,432 次观看 • 6 个月前

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 次观看 • 6 个月前

Introducing the new #CosmographDaytona. To mark the 60th anniversary of the model, the entire range is revisited. The design of the case and face is restyled and the watch equipped with calibre 4131, launched this year. More #WatchesandWonders2023

Introducing the new #CosmographDaytona. To mark the 60th anniversary of the model, the entire range is revisited. The design of the case and face is restyled and the watch equipped with calibre 4131, launched this year. More #WatchesandWonders2023

ROLEX

294,144 次观看 • 3 年前

Introducing Gemini 3 ✨ It’s the best model in the world for multimodal understanding, and our most powerful agentic + vibe coding model yet. Gemini 3 can bring any idea to life, quickly grasping context and intent so you can get what you need with less prompting. Find Gemini 3 Pro rolling out today in the Google Gemini and AI Mode in Search. For developers, build with it now in Google AI Studio and Vertex AI. Excited for you to try it!

Introducing Gemini 3 ✨ It’s the best model in the world for multimodal understanding, and our most powerful agentic + vibe coding model yet. Gemini 3 can bring any idea to life, quickly grasping context and intent so you can get what you need with less prompting. Find Gemini 3 Pro rolling out today in the Google Gemini and AI Mode in Search. For developers, build with it now in Google AI Studio and Vertex AI. Excited for you to try it!

Sundar Pichai

2,956,116 次观看 • 11 个月前

Reinforcement Learning is the future tense of intelligence. Echo is how it scales. Echo is Gradient’s distributed RL framework, running on everyday consumer devices. From its early experiments, Echo powered a 30B Sokoban model that outperformed DeepSeek-R1 and GPT-OSS-120B.

Reinforcement Learning is the future tense of intelligence. Echo is how it scales. Echo is Gradient’s distributed RL framework, running on everyday consumer devices. From its early experiments, Echo powered a 30B Sokoban model that outperformed DeepSeek-R1 and GPT-OSS-120B.

Gradient

279,386 次观看 • 1 年前