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。

Fei-Fei Li on what simulation can do for robotics that real-world data can't: "You play out events that haven't happened, or cannot happen... And while you play it out, you learn how to act in it." "That's really important in robotics, because we cannot possibly have enough real-world data... show more

a16z

1,076,694 subscribers

35,794 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 条评论

Oleg Bilozor 的头像

Oleg Bilozor3 个月前

The thing that gets me is 'events that cannot happen.' You're not just filling data gaps, you're training on physics edge cases that would take decades to encounter in the real world, if they ever happened at all.

sindikitil 的头像

sindikitil3 个月前

Simulation lets you stress-edge cases that'd take decades to hit in meatspace. The long-tail distribution problem.

Winston B. 的头像

Winston B.3 个月前

Billions of hours of simulation only matter if they're the scenarios that almost never happen on real roads, the ones that decide whether a policy holds up under pressure. Same case for robotics generally. The data you need most is the data you'd otherwise wait years to collect naturally, so simulation ends up being the only practical way to get it.

踏空 Sidelined Capital 的头像

踏空 Sidelined Capital3 个月前

The expensive part is deciding which impossible events teach robustness and which teach the robot to exploit a simulator bug.

Bobby 的头像

Bobby3 个月前

Semper Fidelis

Fred Almeida 的头像

Fred Almeida3 个月前

I was doing this in 2016. Nothing new. We were even coding at the kernal level to improve the number of simulations. in 2017 we were at 12x the speed of 2016. We thought everyone was doing this (imposter syndrome sucks) but they weren't. Today we can train in an hour (constrained RL + SP + CL) what would take 1000 years in real world data. Even at the edge of the technology. People still don't understand this. Almost everyone that thinks they understand AI but haven't worked in it for the last 15 years will have a hard time understanding the foundations.

Ted | unfair.so 的头像

Ted | unfair.so3 个月前

training robots by building worlds = minecraft

PromptKing | Evidence & Integrity for Agentic AI 的头像

PromptKing | Evidence & Integrity for Agentic AI3 个月前

The same logic applies to agent governance. You cannot wait for the model swap, the budget breach, or the unauthorized escalation to discover whether the boundary held. You have to play the trajectory out first — under the actual policy — before the work is allowed to run. That’s why simulate-before-enforce exists. The events that would break the proof are the ones you must never let happen for real. One outcome. Many models. One law. One proof.

Our Ascent Live 的头像

Our Ascent Live3 个月前

The future of robotics should not only be technically intelligent @drfeifei. It should be publicly shaped. Citizen-led. AI-enhanced. 📡🗽

相关视频

World Labs CEO Dr. Fei-Fei Li & SceniX Co-Founder Yunzhu Li on the data bottleneck in robotics and how world models help: "The lack of data in training, the lack of data in evaluation, this is very, very different from language models, where data is abundant on the internet." "And we know that in order for robotics to work, we have to somehow unlock the power of scaling law. But where does that come from?" "It's a profound problem that everybody's battling with in robotics." "We see a lot of unlock in being able to do this whole process through the modeling of the environments." "Being able to create these digital worlds... that's just going to unlock so much more potential for being able to replace all the costly and the unsafe data in the real environments with the data generated from the worlds for robots to be able to do scalable learning and evaluations." Fei-Fei Li Yunzhu Li martin_casado

World Labs CEO Dr. Fei-Fei Li & SceniX Co-Founder Yunzhu Li on the data bottleneck in robotics and how world models help: "The lack of data in training, the lack of data in evaluation, this is very, very different from language models, where data is abundant on the internet." "And we know that in order for robotics to work, we have to somehow unlock the power of scaling law. But where does that come from?" "It's a profound problem that everybody's battling with in robotics." "We see a lot of unlock in being able to do this whole process through the modeling of the environments." "Being able to create these digital worlds... that's just going to unlock so much more potential for being able to replace all the costly and the unsafe data in the real environments with the data generated from the worlds for robots to be able to do scalable learning and evaluations." Fei-Fei Li Yunzhu Li martin_casado

a16z

80,437 次观看 • 3 个月前

We're hiring in robot learning at World Labs! Join me, Fei-Fei Li, and the team to define and scale the next generation of world models for robot learning! Atlas for Robotics: Real-to-Sim-to-Real: Apply:

We're hiring in robot learning at World Labs! Join me, Fei-Fei Li, and the team to define and scale the next generation of world models for robot learning! Atlas for Robotics: Real-to-Sim-to-Real: Apply:

Yunzhu Li

177,209 次观看 • 1 个月前

Fei-Fei Li (Fei-Fei Li) on limitations of LLMs. "There's no language out there in nature. You don't go out in nature and there's words written in the sky for you.. There is a 3D world that follows laws of physics." Language is purely generated signal.

Fei-Fei Li (Fei-Fei Li) on limitations of LLMs. "There's no language out there in nature. You don't go out in nature and there's words written in the sky for you.. There is a 3D world that follows laws of physics." Language is purely generated signal.

Rohan Paul

1,854,870 次观看 • 1 年前

World Labs' Dr. Fei-Fei Li on why the 3D world and spatial intelligence are fundamentally different from language models: "Language is fundamentally a purely generated signal. There's no language out there. You don't go out in the nature and there's words written in the sky for you." "Whatever data you feed in, you pretty much can just somehow regurgitate with enough generalizability the same data out, and that's language to language." "But the 3D world is not. There is a 3D world out there that follows laws of physics, that has its own structures due to materials and many other things. And to fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing similar ideas or useful ideas from language and LLMs, but this is fundamentally philosophically, to me, a different problem." Fei-Fei Li

World Labs' Dr. Fei-Fei Li on why the 3D world and spatial intelligence are fundamentally different from language models: "Language is fundamentally a purely generated signal. There's no language out there. You don't go out in the nature and there's words written in the sky for you." "Whatever data you feed in, you pretty much can just somehow regurgitate with enough generalizability the same data out, and that's language to language." "But the 3D world is not. There is a 3D world out there that follows laws of physics, that has its own structures due to materials and many other things. And to fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing similar ideas or useful ideas from language and LLMs, but this is fundamentally philosophically, to me, a different problem." Fei-Fei Li

a16z

53,621 次观看 • 1 个月前

World Labs CEO Dr. Fei-Fei Li explains says "world model" has become an overloaded term & explains what each kind of world model does: "Right now there are three ways of calling world models when it comes to spatial intelligence." "One is what I call a renderer, when the model puts beautiful pixels on the screen." "Another kind of world model is what we call a planner. That is more for machines, more for robots." "The third kind, which I think is the linchpin of the three, is a simulator." "A simulator could become a renderer. The simulator could become a planner. But this layer is a huge critical path to unlock spatial intelligence. And that's what World Labs is working on." Fei-Fei Li at Bloomberg Tech live with Emily Chang

World Labs CEO Dr. Fei-Fei Li explains says "world model" has become an overloaded term & explains what each kind of world model does: "Right now there are three ways of calling world models when it comes to spatial intelligence." "One is what I call a renderer, when the model puts beautiful pixels on the screen." "Another kind of world model is what we call a planner. That is more for machines, more for robots." "The third kind, which I think is the linchpin of the three, is a simulator." "A simulator could become a renderer. The simulator could become a planner. But this layer is a huge critical path to unlock spatial intelligence. And that's what World Labs is working on." Fei-Fei Li at Bloomberg Tech live with Emily Chang

a16z

112,217 次观看 • 5 个月前

The moment is right to push forward into a new frontier for AI — one that is as fundamental as language, says Fei-Fei Li. That frontier is visual spatial intelligence. With Justin Johnson (Justin Johnson), her cofounder at World Labs, and a16z's martin_casado, Fei-Fei explains what unlocking this technology could mean, and why we’re in the midst of a “Cambrian explosion”:

The moment is right to push forward into a new frontier for AI — one that is as fundamental as language, says Fei-Fei Li. That frontier is visual spatial intelligence. With Justin Johnson (Justin Johnson), her cofounder at World Labs, and a16z's martin_casado, Fei-Fei explains what unlocking this technology could mean, and why we’re in the midst of a “Cambrian explosion”:

a16z

477,081 次观看 • 2 年前

Asked why humanoid robots still can't load a dishwasher after $6 billion in funding, Fei-Fei Li says the number is too small: Emily Chang: "Funding for humanoids hit $6 billion, but they still can't load my dishwasher as fast as I can. They still can't go get my Amazon packages. Will world models, world labs, close the gap between hype and reality?" "That's a loaded question, Emily." "First of all, robotics is gonna be one of the most important revolution in human industrialization." "$6 billion is too small, right?" "If you look at self-driving cars investment, if you look at language models investment, it took way more than six billion dollars." The $6 billion is Chang's total for humanoid funding, not Li's own measurement. Chang also says World Labs, which Li co-founded, has raised $1 billion of its own. - Fei-Fei Li (Fei-Fei Li), co-founder and CEO of World Labs and Stanford professor, with Emily Chang on The Circuit (Bloomberg TV), August 19, 2026.

Asked why humanoid robots still can't load a dishwasher after $6 billion in funding, Fei-Fei Li says the number is too small: Emily Chang: "Funding for humanoids hit $6 billion, but they still can't load my dishwasher as fast as I can. They still can't go get my Amazon packages. Will world models, world labs, close the gap between hype and reality?" "That's a loaded question, Emily." "First of all, robotics is gonna be one of the most important revolution in human industrialization." "$6 billion is too small, right?" "If you look at self-driving cars investment, if you look at language models investment, it took way more than six billion dollars." The $6 billion is Chang's total for humanoid funding, not Li's own measurement. Chang also says World Labs, which Li co-founded, has raised $1 billion of its own. - Fei-Fei Li (Fei-Fei Li), co-founder and CEO of World Labs and Stanford professor, with Emily Chang on The Circuit (Bloomberg TV), August 19, 2026.

Karl Mehta

42,888 次观看 • 1 个月前

BREAKING: $AMD AMD Acquires World Labs in $8.2 Billion Deal for AI Expertise. Stanford professor and World Labs founder Fei-Fei Li sits down with Jany Talk to break down what everyone gets wrong about AI - and why she still believes in people, not machines. Fei-Fei Li co-created ImageNet before most of the world understood why data would matter more than algorithms. She's spent a decade building computer vision and robotics from the ground up. Now, as the founder of World Labs, she's betting on spatial intelligence as the missing piece of AGI - and she's here to tell you why almost everyone is thinking about AI wrong. Fei-Fei Li: "AI Is a Tool, Not the World" - On Curiosity, AGI and Being Human. Full interview here:

BREAKING: $AMD AMD Acquires World Labs in $8.2 Billion Deal for AI Expertise. Stanford professor and World Labs founder Fei-Fei Li sits down with Jany Talk to break down what everyone gets wrong about AI - and why she still believes in people, not machines. Fei-Fei Li co-created ImageNet before most of the world understood why data would matter more than algorithms. She's spent a decade building computer vision and robotics from the ground up. Now, as the founder of World Labs, she's betting on spatial intelligence as the missing piece of AGI - and she's here to tell you why almost everyone is thinking about AI wrong. Fei-Fei Li: "AI Is a Tool, Not the World" - On Curiosity, AGI and Being Human. Full interview here:

NextFin

173,375 次观看 • 1 个月前

I don't know if you really understand what these people just did... They built an AI that looks at a few casual real-world videos or photos and instantly turns them into a full 3D playground. You can MOVE THE CAMERA HOWEVER YOU WANT, change the lighting, move objects around, and even let physics play out like in the real world. View events from impossible angles because Atlas knows what was there. This is massive! Let's take robotics. Until now training robots meant collecting tons of expensive real-world data. Now a handful of recordings can become thousands of different simulated situations. Robots can practice the same task in new rooms, with different objects and lighting without anyone having to film it all again. For the industry it means we can train robots way faster and cheaper. Home robots, warehouse robots, whatever... they can learn new environments at scale instead of staying stuck in the lab. This is one of the first real bridges between “cool AI video models” and actual physical machines that have to work in the real world. Blog: The team behind World Labs: Fei-Fei Li, Justin Johnson, Ben Mildenhall and Yunzhu Li. The video is from David Pantera. Follow for more insights into robotics and AI. —— Weekly robotics and AI insights. Subscribe free:

I don't know if you really understand what these people just did... They built an AI that looks at a few casual real-world videos or photos and instantly turns them into a full 3D playground. You can MOVE THE CAMERA HOWEVER YOU WANT, change the lighting, move objects around, and even let physics play out like in the real world. View events from impossible angles because Atlas knows what was there. This is massive! Let's take robotics. Until now training robots meant collecting tons of expensive real-world data. Now a handful of recordings can become thousands of different simulated situations. Robots can practice the same task in new rooms, with different objects and lighting without anyone having to film it all again. For the industry it means we can train robots way faster and cheaper. Home robots, warehouse robots, whatever... they can learn new environments at scale instead of staying stuck in the lab. This is one of the first real bridges between “cool AI video models” and actual physical machines that have to work in the real world. Blog: The team behind World Labs: Fei-Fei Li, Justin Johnson, Ben Mildenhall and Yunzhu Li. The video is from David Pantera. Follow for more insights into robotics and AI. —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

274,295 次观看 • 2 个月前

Today at Stanford, Fei-Fei Li (Fei-Fei Li),Cofounder/CEO World Labs, gave one of the clearest explanations I’ve heard of what a World Model really is. She broke it down into three layers: 1️⃣ Rendering — What does the world look like? This is where most of today’s video generation models operate: generating increasingly realistic and beautiful pixels. The question is: Can AI generate what the world looks like? The primary consumer is humans. 2️⃣ Simulation — How does the world actually work? Fei-Fei gave a simple example: “How will this bottle move? If I pour the water out, how will the water flow?” This goes far beyond generating something that looks realistic. The model needs to understand physics, spatial relationships, cause and effect, and how the world changes over time. The consumers are both humans and machines. 3️⃣ Planning — What should happen next? This is where things get really interesting. AI doesn't just render the world or simulate what might happen. It uses its understanding of the world to decide: What should I do next? At this layer, the primary consumer is the machine itself. And this connects directly to two enormous opportunities: Autonomous driving and robotics. The progression is powerful: Rendering → Simulation → Planning The real promise of World Models isn't simply generating better videos. It's building AI that can understand the world, predict what happens next, and ultimately take intelligent action in the physical world.

Today at Stanford, Fei-Fei Li (Fei-Fei Li),Cofounder/CEO World Labs, gave one of the clearest explanations I’ve heard of what a World Model really is. She broke it down into three layers: 1️⃣ Rendering — What does the world look like? This is where most of today’s video generation models operate: generating increasingly realistic and beautiful pixels. The question is: Can AI generate what the world looks like? The primary consumer is humans. 2️⃣ Simulation — How does the world actually work? Fei-Fei gave a simple example: “How will this bottle move? If I pour the water out, how will the water flow?” This goes far beyond generating something that looks realistic. The model needs to understand physics, spatial relationships, cause and effect, and how the world changes over time. The consumers are both humans and machines. 3️⃣ Planning — What should happen next? This is where things get really interesting. AI doesn't just render the world or simulate what might happen. It uses its understanding of the world to decide: What should I do next? At this layer, the primary consumer is the machine itself. And this connects directly to two enormous opportunities: Autonomous driving and robotics. The progression is powerful: Rendering → Simulation → Planning The real promise of World Models isn't simply generating better videos. It's building AI that can understand the world, predict what happens next, and ultimately take intelligent action in the physical world.

PaulFang

12,066 次观看 • 3 个月前

Fei-Fei Li: “There’s nothing artificial about AI. It’s inspired by people. It’s created by people. And most importantly, it impacts people.” Watch the full interview with World Labs CEO Fei-Fei Li on Lenny's Podcast (Lenny Rachitsky):

Fei-Fei Li: “There’s nothing artificial about AI. It’s inspired by people. It’s created by people. And most importantly, it impacts people.” Watch the full interview with World Labs CEO Fei-Fei Li on Lenny's Podcast (Lenny Rachitsky):

a16z

63,672 次观看 • 11 个月前

World Labs CEO Dr. Fei-Fei Li says AI must change how we teach and evaluate students: "AI must change learning. AI must change K-16 learning." "The most precious resource of our entire world is human capital." "When we have gotten the technology that can answer standardized tests... when AI can do better than an average human, it's not about humans are bad. It's about we need to change the education system." "We need to change how we evaluate. We need to change the way we empower teachers to educate the next generation of students where they can use these tools, be empowered, and do things that we can never imagine." "All of the kids today should not be scared of AI. They should feel the human agency to lead AI, to use AI in the right way, and to use AI to make the impact that they want to make for the world." Fei-Fei Li at Bloomberg Tech live with Emily Chang

World Labs CEO Dr. Fei-Fei Li says AI must change how we teach and evaluate students: "AI must change learning. AI must change K-16 learning." "The most precious resource of our entire world is human capital." "When we have gotten the technology that can answer standardized tests... when AI can do better than an average human, it's not about humans are bad. It's about we need to change the education system." "We need to change how we evaluate. We need to change the way we empower teachers to educate the next generation of students where they can use these tools, be empowered, and do things that we can never imagine." "All of the kids today should not be scared of AI. They should feel the human agency to lead AI, to use AI in the right way, and to use AI to make the impact that they want to make for the world." Fei-Fei Li at Bloomberg Tech live with Emily Chang

a16z

82,062 次观看 • 5 个月前

World Labs CEO Fei-Fei Li on the need for world models: "There's no language out there. You don't go out in nature and there's words written in the sky for you." "There is a 3D world out there that follows laws of physics, that has its own structures due to materials. To fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing useful ideas from language and LLMs, but this is fundamentally, philosophically a different problem."

World Labs CEO Fei-Fei Li on the need for world models: "There's no language out there. You don't go out in nature and there's words written in the sky for you." "There is a 3D world out there that follows laws of physics, that has its own structures due to materials. To fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing useful ideas from language and LLMs, but this is fundamentally, philosophically a different problem."

a16z

204,772 次观看 • 2 个月前

"China is a powerhouse in AI” World Labs CEO Fei-Fei Li lists the countries that are leading the charge in the space Subscribe to The Mishal Husain Show wherever you get your podcasts

"China is a powerhouse in AI” World Labs CEO Fei-Fei Li lists the countries that are leading the charge in the space Subscribe to The Mishal Husain Show wherever you get your podcasts

Bloomberg

26,680 次观看 • 11 个月前

Godmother of AI and World Labs CEO Fei-Fei Li says the real existential threat was never AI: "Any threat to human society, including existential, is within ourselves."

Godmother of AI and World Labs CEO Fei-Fei Li says the real existential threat was never AI: "Any threat to human society, including existential, is within ourselves."

Big Brain AI

16,543 次观看 • 1 个月前

World Labs co-founders Justin Johnson and Dr. Fei-Fei Li say LLMs use next-token prediction, but spatial intelligence has its own equivalent: Justin: "The soft definition of AI-completeness is there's this fundamental primitive that's an AI task. But if I could solve this AI task in its full, broadest generality, it would solve any intelligence problem." "The classic example in LLMs is that next-token prediction is AI-complete... I think from Ilya: there's a mystery novel, the thing has to read the whole novel, and the final sentence is, 'And the killer was.' Predict the next token. You could basically frame any kind of intelligence task in terms of that." "So clearly next-token prediction is something people believe is AI-complete." "New-view prediction, this primitive that we have in Atlas, especially generative new-view prediction, is also AI-complete." "I want to have a world where Martin is writing a proof of the Riemann hypothesis on the blackboard, and then the camera pans over to the next whiteboard." Fei-Fei: "Evolution had to solve new-viewpoint prediction by making animals move. Nature gave animals eyes, but nature didn't give trees eyes. Why? Because when you move, you see a new viewpoint... We do believe very strongly that next-viewpoint prediction is the equivalent of next-token prediction." Justin Johnson Fei-Fei Li martin_casado

World Labs co-founders Justin Johnson and Dr. Fei-Fei Li say LLMs use next-token prediction, but spatial intelligence has its own equivalent: Justin: "The soft definition of AI-completeness is there's this fundamental primitive that's an AI task. But if I could solve this AI task in its full, broadest generality, it would solve any intelligence problem." "The classic example in LLMs is that next-token prediction is AI-complete... I think from Ilya: there's a mystery novel, the thing has to read the whole novel, and the final sentence is, 'And the killer was.' Predict the next token. You could basically frame any kind of intelligence task in terms of that." "So clearly next-token prediction is something people believe is AI-complete." "New-view prediction, this primitive that we have in Atlas, especially generative new-view prediction, is also AI-complete." "I want to have a world where Martin is writing a proof of the Riemann hypothesis on the blackboard, and then the camera pans over to the next whiteboard." Fei-Fei: "Evolution had to solve new-viewpoint prediction by making animals move. Nature gave animals eyes, but nature didn't give trees eyes. Why? Because when you move, you see a new viewpoint... We do believe very strongly that next-viewpoint prediction is the equivalent of next-token prediction." Justin Johnson Fei-Fei Li martin_casado

a16z

89,108 次观看 • 2 个月前

World Labs co-founders Dr. Fei-Fei Li and Justin Johnson on compute as the constraint, and the Slack message that convinced them to go all-in on their Atlas model: Fei-Fei: "I think [we] have total conviction about the scaling law." "I do think the exact architecture choices and data mixtures is where the devil's in the details. I watched Justin and his team going from 'we really don't know how long this is gonna take,' to 'maybe sign of life,' to 'wow, this is gonna work.'" Justin: "We're basically at the beginning, and we're basically limited by compute at this point." "During development, we trained a sequence of models, the first couple rungs of the scaling ladder. Each time we made the model bigger, each time we trained it for longer, each time we put it on more chips, it got significantly better." Fei-Fei: "Here's a little bit of an insider story... There was one day in early summer... Ben and Justin feed [a smaller model] into the viewpoint generation... Remember that famous garden table from the NeRF paper?... Overnight we all saw the Slack from Ben that our camera flew under the table." "That morning, the three of us looked at each other in the eyes and said, 'That's it. We're gonna build this.' We made a decision within five seconds. No one has ever seen this result." Fei-Fei Li Justin Johnson Ben Mildenhall martin_casado

World Labs co-founders Dr. Fei-Fei Li and Justin Johnson on compute as the constraint, and the Slack message that convinced them to go all-in on their Atlas model: Fei-Fei: "I think [we] have total conviction about the scaling law." "I do think the exact architecture choices and data mixtures is where the devil's in the details. I watched Justin and his team going from 'we really don't know how long this is gonna take,' to 'maybe sign of life,' to 'wow, this is gonna work.'" Justin: "We're basically at the beginning, and we're basically limited by compute at this point." "During development, we trained a sequence of models, the first couple rungs of the scaling ladder. Each time we made the model bigger, each time we trained it for longer, each time we put it on more chips, it got significantly better." Fei-Fei: "Here's a little bit of an insider story... There was one day in early summer... Ben and Justin feed [a smaller model] into the viewpoint generation... Remember that famous garden table from the NeRF paper?... Overnight we all saw the Slack from Ben that our camera flew under the table." "That morning, the three of us looked at each other in the eyes and said, 'That's it. We're gonna build this.' We made a decision within five seconds. No one has ever seen this result." Fei-Fei Li Justin Johnson Ben Mildenhall martin_casado

a16z

42,237 次观看 • 1 个月前

For all of history, humanity shared one 3D world. World Labs co-founder Fei-Fei Li says spatial intelligence now lets us generate and reconstruct infinite universes for creativity, travel, storytelling, even socialization. “It suddenly will enable us to live in a multiverse way.”

For all of history, humanity shared one 3D world. World Labs co-founder Fei-Fei Li says spatial intelligence now lets us generate and reconstruct infinite universes for creativity, travel, storytelling, even socialization. “It suddenly will enable us to live in a multiverse way.”

a16z

204,325 次观看 • 1 年前

Spatial intelligence enables the next interface. World Labs co-founders Fei-Fei Li and Justin Johnson say that blending digital and physical worlds simplifies UX and brings agents to the 3D world.

Spatial intelligence enables the next interface. World Labs co-founders Fei-Fei Li and Justin Johnson say that blending digital and physical worlds simplifies UX and brings agents to the 3D world.

a16z

33,088 次观看 • 1 年前

Old footage sitting in your camera roll could now be reconstructable as a 3D scene. World Labs co-founders Ben Mildenhall and Fei-Fei Li on how Atlas got there: Ben: "In a casual sense... I took three photos of this object, or six photos of this room. I look at the photos, I can understand in my mind how those piece together. I can fill in the gaps and get it." "But there's never really been any reconciliation between those data-driven priors and the brute force dense reconstruction, which is much more akin to scientific or medical imaging... When we say dense, we really mean dense." "This room, I want like 100, 200, 300 photos to capture it. And what we're trying to do is bring that down to like three. We're saying like 50, 100x reduction." "At that scale it completely flips that calculus on its head of what type of captures you reconstruct. You can go back to existing imagery you have. You can go to stuff you find on the internet and even build scenes out of that. You can go to casual videos and unearth a lot of footage that in the past we would never have treated as reconstructable, and bring it to life as 3D." "This is something we've been playing around with a lot with Atlas. Taking old clips. I've taken a bunch of my own old captures that never worked before and put them through the system and seen a reconstruction for the first time." Fei-Fei: "The Stanford demo is underappreciated. Anywhere between 3 to 25 images, you can reconstruct that entire Stanford quad... Everything you see is generated, but according to the laws of reconstruction. And this is really magical." Ben Mildenhall Fei-Fei Li

Old footage sitting in your camera roll could now be reconstructable as a 3D scene. World Labs co-founders Ben Mildenhall and Fei-Fei Li on how Atlas got there: Ben: "In a casual sense... I took three photos of this object, or six photos of this room. I look at the photos, I can understand in my mind how those piece together. I can fill in the gaps and get it." "But there's never really been any reconciliation between those data-driven priors and the brute force dense reconstruction, which is much more akin to scientific or medical imaging... When we say dense, we really mean dense." "This room, I want like 100, 200, 300 photos to capture it. And what we're trying to do is bring that down to like three. We're saying like 50, 100x reduction." "At that scale it completely flips that calculus on its head of what type of captures you reconstruct. You can go back to existing imagery you have. You can go to stuff you find on the internet and even build scenes out of that. You can go to casual videos and unearth a lot of footage that in the past we would never have treated as reconstructable, and bring it to life as 3D." "This is something we've been playing around with a lot with Atlas. Taking old clips. I've taken a bunch of my own old captures that never worked before and put them through the system and seen a reconstruction for the first time." Fei-Fei: "The Stanford demo is underappreciated. Anywhere between 3 to 25 images, you can reconstruct that entire Stanford quad... Everything you see is generated, but according to the laws of reconstruction. And this is really magical." Ben Mildenhall Fei-Fei Li

a16z

49,207 次观看 • 2 个月前