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。

Reconstructing the world in 3D from random internet photos is a deep rabbit hole. In 2008, Photosynth proved that 3D reconstruction of smaller monuments was possible. The next year, "Building Rome in a Day" proved it could be done for entire cities. Since then, there’s been a wild lineage... of research from early point clouds to modern NeRFs and 3DGS --with a similar cast of characters appearing along the way. In this deep dive, we'll break it all down, and explore why IARPA is funding what comes next. 0:00 The Internet's 3D Model of the World 0:40 Building Rome in a Day (2009) 2:09 The Long Tail Problem 3:18 MegaDepth and the Mannequin Challenge 4:44 NeRFs and 3D Gaussian Splatting 7:19 MegaScenes, Doppelgangers, and Foundation Models 10:00 MegaDepth-X Punches Through the Wall 11:26 Why IARPA Is Funding What's Next 13:51 The 4D Frontier and the Sensoriumshow more

Bilawal Sidhu

119,058 subscribers

52,684 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

27 条评论

Bilawal Sidhu 的头像

Bilawal Sidhu3 个月前

Watch it on YouTube if you prefer - with chapters and sources in description:

Robert Scoble 的头像

Robert Scoble3 个月前

You teach the future of computing better than anyone

Bilawal Sidhu 的头像

Bilawal Sidhu3 个月前

Thank you Robert that is very kind :)

db 的头像

db3 个月前

Amazing! Learning a lot from you 🙏

Bilawal Sidhu 的头像

Bilawal Sidhu3 个月前

Thanks! Glad you’re enjoying the frontier maps :)

db 的头像

db3 个月前

Fits very well with XR and real time sensors data. Appreciate your work!

Justin Ryan 的头像

Justin Ryan3 个月前

Another banger.

Bilawal Sidhu 的头像

Bilawal Sidhu3 个月前

Thank you brother!

Greg Cook 的头像

Greg Cook3 个月前

The photos are here, they’re just not evenly distributed.

AI Mastery Guide 的头像

AI Mastery Guide3 个月前

Building Rome in a day, wild

Bilawal Sidhu 的头像

Bilawal Sidhu3 个月前

One helluva name for a paper eh?

AI Mastery Guide 的头像

AI Mastery Guide3 个月前

Bold claim for a title, but they actually delivered

Bilawal Sidhu 的头像

Bilawal Sidhu3 个月前

@sandwichmaker rare case in tech history

AI Mastery Guide 的头像

AI Mastery Guide3 个月前

@sandwichmaker Rare, but that's exactly why it's still talked about today

ANNnonymous 的头像

ANNnonymous3 个月前

PS shoutout to Mark Davis

Bilawal Sidhu 的头像

Bilawal Sidhu3 个月前

Shoutout!

ThiirdEyeTribe 的头像

ThiirdEyeTribe3 个月前

Incredible deep dives. Thank you for sharing

Bilawal Sidhu 的头像

Bilawal Sidhu3 个月前

You’re most welcome 🙏

Hey, it's me. 的头像

Hey, it's me.3 个月前

Fantastic presentation and explanation as usual; awesome stuff.

Bilawal Sidhu 的头像

Bilawal Sidhu3 个月前

Glad you enjoyed mate!

Jay Kapoor 的头像

Jay Kapoor3 个月前

Bro, this is so fire! Really fantastic stuff.

Oleg Kostour 🇺🇦 的头像

Oleg Kostour 🇺🇦3 个月前

Really cool stuff

Captain HaHaa 的头像

Captain HaHaa3 个月前

Great work mate, this was an interesting watch.

Bilawal Sidhu 的头像

Bilawal Sidhu3 个月前

Thanks Cap’n!

asldkasldkl 的头像

asldkasldkl3 个月前

AI to do better not less. nice

Adam J. Gramling 的头像

Adam J. Gramling2 个月前

My favorite is still SMERFs. I don’t see many players commercializing this tech, outside of Google Maps for interior restaurant views. Polycam isn’t great for scanning IMO

ANNnonymous 的头像

ANNnonymous3 个月前

We really do need to catch up!

相关视频

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 • 7 个月前

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,960 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

178,050 次观看 • 11 个月前

See the world through the eyes of a brave mouse in Hela, a 3D adventure game with Scandinavian-inspired landscapes launching this year. #IGNFanFest Get a deep dive into the world and gameplay:

See the world through the eyes of a brave mouse in Hela, a 3D adventure game with Scandinavian-inspired landscapes launching this year. #IGNFanFest Get a deep dive into the world and gameplay:

IGN

25,807 次观看 • 8 个月前

📁 Fei-Fei Li founder of World Labs, says the next leap in AI is not language. Human intelligence does not just speak, it moves, perceives, and acts in the physical world. Spatial intelligence is the real core of intelligence. From text to space, from models to 3D and 4D worlds, from understanding words to interacting with reality. The next chapter is not read, it is inhabited.

📁 Fei-Fei Li founder of World Labs, says the next leap in AI is not language. Human intelligence does not just speak, it moves, perceives, and acts in the physical world. Spatial intelligence is the real core of intelligence. From text to space, from models to 3D and 4D worlds, from understanding words to interacting with reality. The next chapter is not read, it is inhabited.

Jon Hernandez

20,660 次观看 • 9 个月前

A museum in France. Accessible from anywhere in the world. One of our mappers captured the Musée Archéologique du Val-d'Oise, home to more than 35,000 archaeological artifacts and over 3,000 objects on display. Using an Insta360 X5 and Over the Reality's reconstruction technology, the entire museum, including its multiple floors, has been transformed into a high-fidelity 3D Gaussian Splat and digital twin. This means anyone can now explore the museum remotely, walk through its galleries, move across different floors, and experience the space as if they were there in person. What was once a physical location is now a machine-readable 3D environment, preserved digitally and accessible through a browser, smartphone, or XR headset. From museums and cultural landmarks to entire cities, Over the Reality has built the largest 3D map of the world. The link to explore the experience remotely is available in the first comment.

A museum in France. Accessible from anywhere in the world. One of our mappers captured the Musée Archéologique du Val-d'Oise, home to more than 35,000 archaeological artifacts and over 3,000 objects on display. Using an Insta360 X5 and Over the Reality's reconstruction technology, the entire museum, including its multiple floors, has been transformed into a high-fidelity 3D Gaussian Splat and digital twin. This means anyone can now explore the museum remotely, walk through its galleries, move across different floors, and experience the space as if they were there in person. What was once a physical location is now a machine-readable 3D environment, preserved digitally and accessible through a browser, smartphone, or XR headset. From museums and cultural landmarks to entire cities, Over the Reality has built the largest 3D map of the world. The link to explore the experience remotely is available in the first comment.

Over the Reality 🌐

27,828 次观看 • 5 个月前

New greenpill.network pod today with @thedevanshmehta about Deep Funding, a new AI-powered funding mechanism that combines human evaluation and prediction markets to allocate resources for open-source projects. Topics: 1. how Deep Funding scales human judgment, 2. prevents Sybil attacks, 3. and creates a fair, dynamic “price feed” for public goods. 4. Devansh shares insights from the pilot run, the results of the data-science competition, and how the model will power Gitcoin Grants 24 #GG24 Timestamps: 00:00 – Intro: Welcome to the Greenpill Podcast – exploring tech, coordination & Protopia 00:45 – Introducing guest Devansh Mehta, AI & Public Goods Lead at the Ethereum Foundation 01:20 – What is Deep Funding and why it matters 02:00 – How Deep Funding scales human evaluations with AI models 02:45 – Overview of the pilot run and what was tested 03:20 – How the mechanism works: human jurors + model builders 04:30 – The White Hat Sybil attack and what it revealed 05:40 – How Deep Funding integrates data science competitions and prediction markets 06:50 – Results of the pilot: weighted funding for 45 open-source repos 07:30 – Creating a credibly neutral funding system with unequal weights 08:40 – Comparing Deep Funding with Protocol Guild and other mechanisms 09:20 – Building a strong community of AI developers and human jurors 10:30 – The role of jurors and models in fair evaluation 11:10 – What’s next: expanding to 90 repos in Gitcoin Grants 24 (GG24) 11:50 – Funding pool: $350K from Ethereum Foundation & Gitcoin 12:30 – Challenges of distributing capital efficiently and fairly 13:20 – Moving to GitHub repo-level governance: who controls the funds? 14:40 – Two models of spending: splits contracts vs counterfactual wallets 15:40 – Lessons from past Gitcoin funding rounds 16:20 – Why Deep Funding focuses on units of work, not organizations 17:20 – Avoiding distortions and improving fairness in funding 18:10 – The vision: creating a live price feed for public goods 19:10 – How prediction markets price open-source value 20:30 – Self-correcting market behavior and real-time adjustments 21:20 – Subsidies and liquidity: bootstrapping active participation 22:10 – Balancing liquidity levels to prevent manipulation 23:00 – What’s next for Deep Funding: refining future iterations 23:40 – Shoutout to the model builders and competition winners 24:20 – Where to learn more: & 25:00 – Closing: the future of AI, governance, and funding what matters If you’re curious about the intersection of AI, governance, and funding public goods, this conversation is for you. And participate in GG24 at

New greenpill.network pod today with @thedevanshmehta about Deep Funding, a new AI-powered funding mechanism that combines human evaluation and prediction markets to allocate resources for open-source projects. Topics: 1. how Deep Funding scales human judgment, 2. prevents Sybil attacks, 3. and creates a fair, dynamic “price feed” for public goods. 4. Devansh shares insights from the pilot run, the results of the data-science competition, and how the model will power Gitcoin Grants 24 #GG24 Timestamps: 00:00 – Intro: Welcome to the Greenpill Podcast – exploring tech, coordination & Protopia 00:45 – Introducing guest Devansh Mehta, AI & Public Goods Lead at the Ethereum Foundation 01:20 – What is Deep Funding and why it matters 02:00 – How Deep Funding scales human evaluations with AI models 02:45 – Overview of the pilot run and what was tested 03:20 – How the mechanism works: human jurors + model builders 04:30 – The White Hat Sybil attack and what it revealed 05:40 – How Deep Funding integrates data science competitions and prediction markets 06:50 – Results of the pilot: weighted funding for 45 open-source repos 07:30 – Creating a credibly neutral funding system with unequal weights 08:40 – Comparing Deep Funding with Protocol Guild and other mechanisms 09:20 – Building a strong community of AI developers and human jurors 10:30 – The role of jurors and models in fair evaluation 11:10 – What’s next: expanding to 90 repos in Gitcoin Grants 24 (GG24) 11:50 – Funding pool: $350K from Ethereum Foundation & Gitcoin 12:30 – Challenges of distributing capital efficiently and fairly 13:20 – Moving to GitHub repo-level governance: who controls the funds? 14:40 – Two models of spending: splits contracts vs counterfactual wallets 15:40 – Lessons from past Gitcoin funding rounds 16:20 – Why Deep Funding focuses on units of work, not organizations 17:20 – Avoiding distortions and improving fairness in funding 18:10 – The vision: creating a live price feed for public goods 19:10 – How prediction markets price open-source value 20:30 – Self-correcting market behavior and real-time adjustments 21:20 – Subsidies and liquidity: bootstrapping active participation 22:10 – Balancing liquidity levels to prevent manipulation 23:00 – What’s next for Deep Funding: refining future iterations 23:40 – Shoutout to the model builders and competition winners 24:20 – Where to learn more: & 25:00 – Closing: the future of AI, governance, and funding what matters If you’re curious about the intersection of AI, governance, and funding public goods, this conversation is for you. And participate in GG24 at

owocki’s gitcoin 3.0 arc

12,981 次观看 • 1 年前

This is NOT a mesh, NOT a NeRF, NOT video footage. This is 3D Gaussian Splatting which produces a similar output to NeRFs. Check out those reflections in the water! The fine structure detail 🤩 #3D #AI #Computervision #VFX

This is NOT a mesh, NOT a NeRF, NOT video footage. This is 3D Gaussian Splatting which produces a similar output to NeRFs. Check out those reflections in the water! The fine structure detail 🤩 #3D #AI #Computervision #VFX

Jonathan Stephens

171,286 次观看 • 3 年前

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

AI at Meta

18,031 次观看 • 11 个月前

Fly through the world in 3D 🌎 Captured by iROBOTICS, Inc. with a DJI Osmo 360 and reconstructed in Scaniverse, this Gaussian splat of Kutani Dam shows the potential of large-scale 3D reconstruction for infrastructure planning and assessment. Start today with Scaniverse. #WorldModels #RealWorldModels #SpatialAI #PhysicalAI #AI #GaussianSplat #RealityCapture #3DGS #3DReconstruction

Fly through the world in 3D 🌎 Captured by iROBOTICS, Inc. with a DJI Osmo 360 and reconstructed in Scaniverse, this Gaussian splat of Kutani Dam shows the potential of large-scale 3D reconstruction for infrastructure planning and assessment. Start today with Scaniverse. #WorldModels #RealWorldModels #SpatialAI #PhysicalAI #AI #GaussianSplat #RealityCapture #3DGS #3DReconstruction

Niantic Spatial 🌎

96,069 次观看 • 1 个月前

Wild Rift vs LoLM: 3D replay viewing function. 😅 - I thought everyone knew that in the Chinese version (not only in PBE) there is a 3D replay viewing function of 240 degrees and 15% zoom to the hero. - In China the game is called "Leagues of Legends Mobile" and in ours "lol Wild Rift". They are different, although the same game. - I don’t know why 3D viewing is not added to the global version, since it has been in the Chinese version for a long time. #lolm #wildrift #viewing #why?

Wild Rift vs LoLM: 3D replay viewing function. 😅 - I thought everyone knew that in the Chinese version (not only in PBE) there is a 3D replay viewing function of 240 degrees and 15% zoom to the hero. - In China the game is called "Leagues of Legends Mobile" and in ours "lol Wild Rift". They are different, although the same game. - I don’t know why 3D viewing is not added to the global version, since it has been in the Chinese version for a long time. #lolm #wildrift #viewing #why?

WR Uzbeks

23,361 次观看 • 2 年前

Today we are releasing JST-2, the world's first full-stack physics-native world foundation model. Many world models learn in pixel/video space. We went back to first principles and built the entire model stack in 3D. Generate a 3D scene in seconds and expand it in real time. Create characters with motion built in, all through one general architecture.

Today we are releasing JST-2, the world's first full-stack physics-native world foundation model. Many world models learn in pixel/video space. We went back to first principles and built the entire model stack in 3D. Generate a 3D scene in seconds and expand it in real time. Create characters with motion built in, all through one general architecture.

ViggleAI

1,743,564 次观看 • 25 天前

Another city. Another full 3D Gaussian Splat reconstruction. This entire neighborhood was captured while walking with an Insta360 X5, then processed with our GPU pipeline and transformed into a high-fidelity, machine-readable 3D environment with Over the Reality. What you’re seeing is not an isolated virtual world. It’s a 3D digital twin of a real-world location, built from structured spatial data where every building, street, and detail can become usable by AI, robotics, and XR. And it’s happening at scale, across cities in more than 180 countries every day. Have an Insta360 X5 and want to become a mapper? Apply here: Want to build a 3D Gaussian Splat from a video you already recorded? Do it for free at powered by Over the Reality.

Another city. Another full 3D Gaussian Splat reconstruction. This entire neighborhood was captured while walking with an Insta360 X5, then processed with our GPU pipeline and transformed into a high-fidelity, machine-readable 3D environment with Over the Reality. What you’re seeing is not an isolated virtual world. It’s a 3D digital twin of a real-world location, built from structured spatial data where every building, street, and detail can become usable by AI, robotics, and XR. And it’s happening at scale, across cities in more than 180 countries every day. Have an Insta360 X5 and want to become a mapper? Apply here: Want to build a 3D Gaussian Splat from a video you already recorded? Do it for free at powered by Over the Reality.

Over the Reality 🌐

400,303 次观看 • 6 个月前

WOW. 😳 Apple just quietly won the 3D maps war at WWDC. Gaussian Splatting is coming to Apple Maps Flyover this fall. Apple Maps Flyover covers 300+ cities. Until yesterday, every single one was built on standard drone photogrammetry. The technology captures photos from the air and reconstructs 3D geometry from them. Gaussian Splatting does not reconstruct geometry. It represents the scene as millions of tiny 3D ellipsoids, each one carrying its own color and opacity information based on how light actually behaves in that location. The output is not a mesh model. It is a field of light. When you move through it, it does not crumble at the edges. The detail holds because it was never geometry to begin with. Apple has been hiring for this for years. Their SHARP model, published in research last year, generates photorealistic 3D scenes from a single image in under a second. Google has more sensor data than anyone. More Street View cars, more satellites, more capture history. On navigation accuracy and geodata depth, Google Maps is still ahead by most measures. But fidelity in 3D city rendering is a different competition, and Apple just set a bar in that. Most people will experience this in the fall without knowing the name of the technology. They will open Flyover, look at a city they know, and notice it looks different. Real, not rendered. That is the moment Gaussian Splatting stops being a research term and becomes something a billion people use. Bookmark this. It will look prescient by October.

WOW. 😳 Apple just quietly won the 3D maps war at WWDC. Gaussian Splatting is coming to Apple Maps Flyover this fall. Apple Maps Flyover covers 300+ cities. Until yesterday, every single one was built on standard drone photogrammetry. The technology captures photos from the air and reconstructs 3D geometry from them. Gaussian Splatting does not reconstruct geometry. It represents the scene as millions of tiny 3D ellipsoids, each one carrying its own color and opacity information based on how light actually behaves in that location. The output is not a mesh model. It is a field of light. When you move through it, it does not crumble at the edges. The detail holds because it was never geometry to begin with. Apple has been hiring for this for years. Their SHARP model, published in research last year, generates photorealistic 3D scenes from a single image in under a second. Google has more sensor data than anyone. More Street View cars, more satellites, more capture history. On navigation accuracy and geodata depth, Google Maps is still ahead by most measures. But fidelity in 3D city rendering is a different competition, and Apple just set a bar in that. Most people will experience this in the fall without knowing the name of the technology. They will open Flyover, look at a city they know, and notice it looks different. Real, not rendered. That is the moment Gaussian Splatting stops being a research term and becomes something a billion people use. Bookmark this. It will look prescient by October.

Shruti

19,832 次观看 • 5 个月前

I made seven small 3D worlds, each from a single image. One picture per world, one per character. PINOC by ViggleAI, running on their new JST-2 world model, turned them into Gaussian splat worlds and rigged characters that run in the browser. Then Claude Code, connected to the PINOC MCP, walked Fern through every world and directed the camera. All of this is 3D. Imagine it as a landing page, a game or a demo people can explore.

I made seven small 3D worlds, each from a single image. One picture per world, one per character. PINOC by ViggleAI, running on their new JST-2 world model, turned them into Gaussian splat worlds and rigged characters that run in the browser. Then Claude Code, connected to the PINOC MCP, walked Fern through every world and directed the camera. All of this is 3D. Imagine it as a landing page, a game or a demo people can explore.

Meng To

10,960 次观看 • 17 天前

Today Reactor is coming out of stealth. We’ve raised $59M in Seed and Series A funding, led by Lightspeed, with participation from Amplify Partners, wndrco, Sky9 Capital, and FPV Ventures. Reactor is the platform for building in the World Model era: the infrastructure that lets developers build with them at global scale for the first time. Stream from a frontier World Model to your app, in real time, all in under 10 lines of code. World Models represent the next major shift in AI: pixels, audio and actions are generated on the fly, in real-time, in response to user inputs, and to the environment. Every time computing has made a shift from passive to interactive, entire industries appeared that didn't exist before. We're standing in front of such moment again. Over the last 6 months, we’ve assembled an all-star team with alumni from Apple, Meta, Google, Luma AI, Netflix, and Replicate. We're already partnering with some of the biggest names and labs in the world, and hundreds of developers are already building on Reactor. The World Model era starts now.

Today Reactor is coming out of stealth. We’ve raised $59M in Seed and Series A funding, led by Lightspeed, with participation from Amplify Partners, wndrco, Sky9 Capital, and FPV Ventures. Reactor is the platform for building in the World Model era: the infrastructure that lets developers build with them at global scale for the first time. Stream from a frontier World Model to your app, in real time, all in under 10 lines of code. World Models represent the next major shift in AI: pixels, audio and actions are generated on the fly, in real-time, in response to user inputs, and to the environment. Every time computing has made a shift from passive to interactive, entire industries appeared that didn't exist before. We're standing in front of such moment again. Over the last 6 months, we’ve assembled an all-star team with alumni from Apple, Meta, Google, Luma AI, Netflix, and Replicate. We're already partnering with some of the biggest names and labs in the world, and hundreds of developers are already building on Reactor. The World Model era starts now.

reactor

12,739,610 次观看 • 5 个月前

Dr. Fei-Fei Li (Fei-Fei Li), the Godmother of AI, on the origin of computer vision and why spatial intelligence is the next frontier. At AI Startup School in San Francisco. 01:00 - Origins of ImageNet 02:15 - The Dream to Make Machines See 03:28 - A paradigm shift in AI 05:50 - AlexNet and Deep Learning 08:00 - Evolving Computer Vision 12:20 - Building World Labs 13:00 - The next frontier in AI 14:20 - Why Spatial Intelligence Is Harder Than Language 18:40 - Technical Barriers for Vision-Based AI 20:00 - AI is more than LLMs 25:50 - Fei Fei’s Journey 29:30 - Mentoring some of the legends of AI 33:00 - Audience Q&A

Dr. Fei-Fei Li (Fei-Fei Li), the Godmother of AI, on the origin of computer vision and why spatial intelligence is the next frontier. At AI Startup School in San Francisco. 01:00 - Origins of ImageNet 02:15 - The Dream to Make Machines See 03:28 - A paradigm shift in AI 05:50 - AlexNet and Deep Learning 08:00 - Evolving Computer Vision 12:20 - Building World Labs 13:00 - The next frontier in AI 14:20 - Why Spatial Intelligence Is Harder Than Language 18:40 - Technical Barriers for Vision-Based AI 20:00 - AI is more than LLMs 25:50 - Fei Fei’s Journey 29:30 - Mentoring some of the legends of AI 33:00 - Audience Q&A

Y Combinator

194,849 次观看 • 1 年前

This is wild. Arcturus Studios is capturing real sports in full volumetric so you can explore the action from any angle. They surround the field with cameras and use Gaussian splatting to turn the game into a 3D experience. This is the future of sports.

This is wild. Arcturus Studios is capturing real sports in full volumetric so you can explore the action from any angle. They surround the field with cameras and use Gaussian splatting to turn the game into a 3D experience. This is the future of sports.

Justin Ryan

61,960 次观看 • 9 个月前

🌍 What if the entire Earth could be streamed as a photorealistic 3D world? This prototype renders billions of 3D Gaussian splats directly in the browser. Powered by PlayCanvas . WebGPU + WebGL. The technology is ready. The remaining challenge is capturing the planet. 👇

🌍 What if the entire Earth could be streamed as a photorealistic 3D world? This prototype renders billions of 3D Gaussian splats directly in the browser. Powered by PlayCanvas . WebGPU + WebGL. The technology is ready. The remaining challenge is capturing the planet. 👇

Martin Valigursky

20,427 次观看 • 5 个月前