正在加载视频...

视频加载失败

返回首页

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...

bilawalsidhu's profile picture

Bilawal Sidhu

109,010 subscribers

50,671 次观看 • 7 天前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

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!
2:41

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 • 4 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:
0:50

📢 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

66,702 次观看 • 10 个月前

🚀 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:
1:07

🚀 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

176,105 次观看 • 8 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.
1:36

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 🌐

27,503 次观看 • 2 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
25:41

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 • 10 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?
0:38

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

23,271 次观看 • 1 年前

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.
2:42

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 🌐

400,097 次观看 • 3 个月前

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.
1:52

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

12,736,650 次观看 • 2 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.
0:24

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 • 2 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
44:21

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

194,705 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.
0:56

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

61,942 次观看 • 6 个月前

Quantum computing is no longer a science experiment. The machines being built could one day break the encryption protecting your bank account, your data, and systems that run entire countries. We spoke with IonQ COO & CFO Inder Singh about the technology and how the industry is preparing the road ahead. 0:00 Machines that could break the internet 0:44 The next leap 3:17 What it could do for you 4:47 The company at the front 6:55 The power & risk 10:33 Where the money moves 13:51 Next steps
16:36

Quantum computing is no longer a science experiment. The machines being built could one day break the encryption protecting your bank account, your data, and systems that run entire countries. We spoke with IonQ COO & CFO Inder Singh about the technology and how the industry is preparing the road ahead. 0:00 Machines that could break the internet 0:44 The next leap 3:17 What it could do for you 4:47 The company at the front 6:55 The power & risk 10:33 Where the money moves 13:51 Next steps

Jon Erlichman

15,552 次观看 • 17 天前

This will change the way we experience sports forever -- watching the game from a gods eye view. Arcturus is building 4D gaussian splatting tech that can capture every angle of a sporting event and pushes the bar for volumetric video. I tested this in a headset and it makes 360 and 3D 180 video look ancient. This puts you closer to the action than any stadium seat, and it’s genuinely mind blowing.
0:23

This will change the way we experience sports forever -- watching the game from a gods eye view. Arcturus is building 4D gaussian splatting tech that can capture every angle of a sporting event and pushes the bar for volumetric video. I tested this in a headset and it makes 360 and 3D 180 video look ancient. This puts you closer to the action than any stadium seat, and it’s genuinely mind blowing.

Bilawal Sidhu

501,894 次观看 • 6 个月前

A Walk In The Park (part II) feat Alberto 🌎 (00:00) 👋 (01:10) What world models are (03:42) Origin story from text-to-3D to reactor (09:22) Deciding to start the company (11:22) GTA, games, and the path into programming (15:09) Building in stealth and keeping secrets (18:32) Picking investors with independent conviction (21:43) Where world models will grow first (26:08) Why low latency matters (29:34) Becoming CEO and scaling the team (32:23) Final advice
32:50

A Walk In The Park (part II) feat Alberto 🌎 (00:00) 👋 (01:10) What world models are (03:42) Origin story from text-to-3D to reactor (09:22) Deciding to start the company (11:22) GTA, games, and the path into programming (15:09) Building in stealth and keeping secrets (18:32) Picking investors with independent conviction (21:43) Where world models will grow first (26:08) Why low latency matters (29:34) Becoming CEO and scaling the team (32:23) Final advice

Nikunj Kothari

24,897 次观看 • 2 个月前

Meta released SAM3 a model to reconstruct objects from segmented images. I tried it and here are 4 things I found out - The generation is incredibly fast when compared with other 3D GenAI models - The models generated are not meshes but Gaussian Splatting. I was surprised that in the paper it was not mentioned anywhere - When generating multiple objects the arrangement is a bit messed up. - Unfortunately, it is impossible to download any of the .ply generated 😔 I cannot stop thinking about the implications of this in XR. Objects in the real world could be almost instantly turned into photorealistic copies and even rearranged to the user's wish.
0:43

Meta released SAM3 a model to reconstruct objects from segmented images. I tried it and here are 4 things I found out - The generation is incredibly fast when compared with other 3D GenAI models - The models generated are not meshes but Gaussian Splatting. I was surprised that in the paper it was not mentioned anywhere - When generating multiple objects the arrangement is a bit messed up. - Unfortunately, it is impossible to download any of the .ply generated 😔 I cannot stop thinking about the implications of this in XR. Objects in the real world could be almost instantly turned into photorealistic copies and even rearranged to the user's wish.

Gabriele Romagnoli

32,441 次观看 • 9 个月前

This AI paper just solved Google Earth's biggest problem. Satellites look down. Humans look across. That perspective gap is why 3D maps are limited to cities you can blanket with aerial flyovers. Skyfall-GS bridges the gap by synthesizing the views we never captured - rebuilding missing facades and street-level geometry using the world knowledge of diffusion models. And it does so with remarkable consistency. This is a taste of how we go from 3D maps in 3,000 cities to the entire planet. Watch my full video for the rundown:
1:34

This AI paper just solved Google Earth's biggest problem. Satellites look down. Humans look across. That perspective gap is why 3D maps are limited to cities you can blanket with aerial flyovers. Skyfall-GS bridges the gap by synthesizing the views we never captured - rebuilding missing facades and street-level geometry using the world knowledge of diffusion models. And it does so with remarkable consistency. This is a taste of how we go from 3D maps in 3,000 cities to the entire planet. Watch my full video for the rundown:

Bilawal Sidhu

135,003 次观看 • 9 个月前

Real-time world models represent a fundamental shift in AI. reactor is building the platform for real-time generative video infrastructure, supporting developers who need the tech for use across entertainment, physical AI, and robotics. Co-founders Alberto and Bryce Schmidtchen joined us last week on The Investment Memo, hosted by Partners Bucky Moore and Amber Yang, to talk about the era of world models. The conversation centered around the infrastructure Reactor is building, why real-time models are the edge right now, and current use cases for the product. Alberto and Bryce agreed that world models are shaping the way simulations are created, and that developers need a streamlined platform that can support their ideas. We believe Reactor is positioned to be at the frontier of research into real-time generative models. We look forward to seeing how these models apply across industries. Chapters 00:00 Introduction & Overview of Reactor 01:08 Meet the Hosts & Founders 02:18 The Origin Story: From 3D Assets to World Models 05:07 Real-Time Video Applications Across Industries 06:55 The Open Source World Model Explosion 07:23 Why Infrastructure Is the Opportunity 08:42 Parallels to Past Technology Waves 09:51 Bridging the Research-to-Production Gap 13:13 What Developers Are Building with World Models 16:41 Lessons from Luma AI 18:23 What Apple Vision Pro Taught Bryce About Real-Time Systems 20:48 Company Values & Team Culture 22:40 Series A: What the Capital Unlocks 24:13 Reactor's Five-Year Vision 26:09 Closing Remarks
26:35

Real-time world models represent a fundamental shift in AI. reactor is building the platform for real-time generative video infrastructure, supporting developers who need the tech for use across entertainment, physical AI, and robotics. Co-founders Alberto and Bryce Schmidtchen joined us last week on The Investment Memo, hosted by Partners Bucky Moore and Amber Yang, to talk about the era of world models. The conversation centered around the infrastructure Reactor is building, why real-time models are the edge right now, and current use cases for the product. Alberto and Bryce agreed that world models are shaping the way simulations are created, and that developers need a streamlined platform that can support their ideas. We believe Reactor is positioned to be at the frontier of research into real-time generative models. We look forward to seeing how these models apply across industries. Chapters 00:00 Introduction & Overview of Reactor 01:08 Meet the Hosts & Founders 02:18 The Origin Story: From 3D Assets to World Models 05:07 Real-Time Video Applications Across Industries 06:55 The Open Source World Model Explosion 07:23 Why Infrastructure Is the Opportunity 08:42 Parallels to Past Technology Waves 09:51 Bridging the Research-to-Production Gap 13:13 What Developers Are Building with World Models 16:41 Lessons from Luma AI 18:23 What Apple Vision Pro Taught Bryce About Real-Time Systems 20:48 Company Values & Team Culture 22:40 Series A: What the Capital Unlocks 24:13 Reactor's Five-Year Vision 26:09 Closing Remarks

Lightspeed

144,942 次观看 • 2 个月前

3D scanning and rendering is moving so fast - got my splats up and running and I'm mind blown getting ~100fps for this complex 3D scene ⬇️ 🤯 1. WAY faster than NeRF: For comparison, NeRFs would takes around 10 seconds per frame (!) Instead I'm zipping around with FPV controls without breaking a sweat - though I do crash a few times towards the end of the video lol 2. Old Meets New: Gaussian Splatting is cool in that it fuses classical graphics and deep learning techniques. Like NeRFs, this is still a radiance field - just without the slower (ne)ural rendering part. 3. Explicit Representation: Instead you represent a 3D scene as a collection of ellipsoidal "splats" called gaussians. Each gaussian has a position, size, and color. Rendering in real-time is done by projecting into the image plane and alpha blending. 4. Photorealistic Effects: Gaussian splatting use spherical harmonics to represent the view-dependent effects and lighting - allowing surfaces to change color when viewed from different angles, enabling greater photorealism. It doesn't use a neural network, but the training loop is similar to deep learning. 5. Enables Direct Editing: But it's not just speed - with Gaussian Splatting you also get 3D editing support! So you can select, move, and delete stuff, even relight stuff. This type of editing has been more tedious to do with NeRFs and their implicit black box representations. 📲 More tests cooking! Much more to unpack here including simpler explanations. If you enjoyed this post, you might enjoy my feed: Bilawal Sidhu
0:35

3D scanning and rendering is moving so fast - got my splats up and running and I'm mind blown getting ~100fps for this complex 3D scene ⬇️ 🤯 1. WAY faster than NeRF: For comparison, NeRFs would takes around 10 seconds per frame (!) Instead I'm zipping around with FPV controls without breaking a sweat - though I do crash a few times towards the end of the video lol 2. Old Meets New: Gaussian Splatting is cool in that it fuses classical graphics and deep learning techniques. Like NeRFs, this is still a radiance field - just without the slower (ne)ural rendering part. 3. Explicit Representation: Instead you represent a 3D scene as a collection of ellipsoidal "splats" called gaussians. Each gaussian has a position, size, and color. Rendering in real-time is done by projecting into the image plane and alpha blending. 4. Photorealistic Effects: Gaussian splatting use spherical harmonics to represent the view-dependent effects and lighting - allowing surfaces to change color when viewed from different angles, enabling greater photorealism. It doesn't use a neural network, but the training loop is similar to deep learning. 5. Enables Direct Editing: But it's not just speed - with Gaussian Splatting you also get 3D editing support! So you can select, move, and delete stuff, even relight stuff. This type of editing has been more tedious to do with NeRFs and their implicit black box representations. 📲 More tests cooking! Much more to unpack here including simpler explanations. If you enjoyed this post, you might enjoy my feed: Bilawal Sidhu

Bilawal Sidhu

337,090 次观看 • 2 年前

“Casper is a controlled execution environment made for real businesses.” Matt Schaffnit, CEO of Casper, sat down with David Meehan to break down what Casper is building and what’s coming next. 0:48 - What Is Casper 1:40 - What Is Parking Blocks? 3:00 - Matt’s Role 3:44 - What’s in the Pipeline Watch the full conversation below!
5:00

“Casper is a controlled execution environment made for real businesses.” Matt Schaffnit, CEO of Casper, sat down with David Meehan to break down what Casper is building and what’s coming next. 0:48 - What Is Casper 1:40 - What Is Parking Blocks? 3:00 - Matt’s Role 3:44 - What’s in the Pipeline Watch the full conversation below!

Genzio Media | Rolly Mode

10,839 次观看 • 3 个月前