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。

Apple and Meta are still missing the point when it comes to spatial productivity. Going monitor-free or showing the weather in 3d space isn't enough. There's not enough value in replacing a frictionless setup like a laptop and mouse unless the spatial environment unlocks something radically more powerful: a... show more

Greg Madisᯅn

9,138 subscribers

75,936 次观看 • 1 年前 •via X (Twitter)

科学技术教育艺术

Anya Rossi• Live Now

Private livecam show

11 条评论

Adrian 的头像

Adrian1 年前

I think about this a lot too! The value proposition has to go beyond “3D for 3D’s sake.” Hybrid approaches (2D + 3D) might be the way forward - leveraging spatial tools where they truly add value, while keeping the best of current systems. I explored this idea in my master thesis

Greg Madisᯅn 的头像

Greg Madisᯅn1 年前

This is really great Adrian!

UserInterface 的头像

UserInterface3 年前

How to Detect an Apple AirTag Tracker Without an Apple Device

eric provencher 的头像

eric provencher1 年前

Love it Greg!

Frode A. Hegland 的头像

Frode A. Hegland1 年前

Nice

Shahryar Qureshi 的头像

Shahryar Qureshi1 年前

That was awesome

𝕏𝙰𝚍 的头像

𝕏𝙰𝚍1 年前

hopefully the #visionOS widgets and spatial persistence across user sessions announced today at #WWDC25 would enables this finally 🤔

Clyde DeSouza 的头像

Clyde DeSouza1 年前

Tl;Dr: there's no strain on elbow or triceps when using a mouse. Until apple and @RealityLabs figure out a way to fluidly control "cursor" precision based on index finger (or thumb) tracking while yr wrist is at rest... We never going to replace the joy of a mouse input.

Michael Blix 的头像

Michael Blix1 年前

Great stuff!

MadMonkMani 的头像

MadMonkMani1 年前

Very cool, interesting to see what sort of interactive tools/mediums could exist in this space that don't currently exist physically. Given the progression of generative tools curious if users will be able to prompt and buildout their own tool sets and mediums of interaction. Obviously could see markets for this as users design tools that other users can buy, mutate, or otherwise repurpose.

Intellipedia.AI 的头像

Intellipedia.AI1 年前

There needs to be heavy integration of voice and eye commands too offload at least 50% of the work from constant contactless hand and arm waving. Ergonomically that's going to be a stressor on joints and ligaments and muscles. Lots of carpal tunnel type of health risk there.

相关视频

Spatial computing workstation 🥽✨ ∙ Place apps and webpages anywhere around you ∙ Any size and aspect ratio ∙ Keyboard and mouse support ∙ Work in your room or in a virtual environment I think this is pretty awesome and you can actually get some work done like that. Yes, of course higher resolution screens are welcome, as well as more polished software. But it's still cool. Meta Quest 3 + Fluid app *this low-resolution screen recording doesn't show the actual quality in the headset

Spatial computing workstation 🥽✨ ∙ Place apps and webpages anywhere around you ∙ Any size and aspect ratio ∙ Keyboard and mouse support ∙ Work in your room or in a virtual environment I think this is pretty awesome and you can actually get some work done like that. Yes, of course higher resolution screens are welcome, as well as more polished software. But it's still cool. Meta Quest 3 + Fluid app *this low-resolution screen recording doesn't show the actual quality in the headset

Ben Geskin

894,181 次观看 • 2 年前

a demo of using both the gpt-oss-20b and qwen3-coder-480b in the hyperspace agentic browser. this spatial, AI-native UI is designed as an extension of the spatial space of our brain - which places some things more in recency to us, and adjacent to each other. pinch to zoom.

a demo of using both the gpt-oss-20b and qwen3-coder-480b in the hyperspace agentic browser. this spatial, AI-native UI is designed as an extension of the spatial space of our brain - which places some things more in recency to us, and adjacent to each other. pinch to zoom.

Varun

182,308 次观看 • 1 年前

This is the FUTURE I have been dreaming about for YEARS Spatial apps/overlays placed in your real space that can compliment each other AND interact with your real world A volumetric GameBoy able to print 3D cards that are able to manifest directly to your real life 3D printer

This is the FUTURE I have been dreaming about for YEARS Spatial apps/overlays placed in your real space that can compliment each other AND interact with your real world A volumetric GameBoy able to print 3D cards that are able to manifest directly to your real life 3D printer

Brad Lynch

65,370 次观看 • 1 个月前

Godot will support spatial containers in the upcoming 4.8 release and we are excited to see how developers use these new engine's capabilities. Spatial Containers bring new capabilities to XR applications to work in shared spatial environments. Read more:

Godot will support spatial containers in the upcoming 4.8 release and we are excited to see how developers use these new engine's capabilities. Spatial Containers bring new capabilities to XR applications to work in shared spatial environments. Read more:

Godot Engine

32,822 次观看 • 15 天前

“Do you know where a sidewalk begins and ends?” — a simple question from Niantic Spatial CEO, Inhi Cho Suh, that gets to the heart of what today’s AI is missing. For robots, this isn’t theoretical. To safely navigate something as everyday as a sidewalk, they need to understand boundaries, context, and change in real time. Learn about how Niantic Spatial is building the missing piece in Physical AI. #NianticSpatial #HumanX #GeospatialAI #Robotics #AI #PhysicalAI

“Do you know where a sidewalk begins and ends?” — a simple question from Niantic Spatial CEO, Inhi Cho Suh, that gets to the heart of what today’s AI is missing. For robots, this isn’t theoretical. To safely navigate something as everyday as a sidewalk, they need to understand boundaries, context, and change in real time. Learn about how Niantic Spatial is building the missing piece in Physical AI. #NianticSpatial #HumanX #GeospatialAI #Robotics #AI #PhysicalAI

Niantic Spatial 🌎

18,736 次观看 • 6 个月前

Fei-Fei Li says real AI needs eyes. Not to look, but to move in 3D space. Spatial intelligence gave animals agency, and machines will need it too. And once AI can act in space, we can simulate limitless environments -- to train, explore, and create alongside them.

Fei-Fei Li says real AI needs eyes. Not to look, but to move in 3D space. Spatial intelligence gave animals agency, and machines will need it too. And once AI can act in space, we can simulate limitless environments -- to train, explore, and create alongside them.

vitrupo

171,665 次观看 • 1 年前

for physical AI to work in the real world, it needs high-fidelity 3D models of the real world. not just for visualization — for localization, spatial reasoning, and real-to-sim workflows that close the gap between training and deployment. at Niantic Spatial 🌎, we're turning Spexi drone imagery into exactly that — city-scale Gaussian splats grounded in the environments that matter most.

for physical AI to work in the real world, it needs high-fidelity 3D models of the real world. not just for visualization — for localization, spatial reasoning, and real-to-sim workflows that close the gap between training and deployment. at Niantic Spatial 🌎, we're turning Spexi drone imagery into exactly that — city-scale Gaussian splats grounded in the environments that matter most.

asim ᯅ

49,566 次观看 • 5 个月前

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Zhiyang (Frank) Dou

14,728 次观看 • 1 年前

You like a hump from a mouse but the sides from another mouse? How about you just paint on the part you like in 3D and find a mouse that matches both on While you're at it, why not use the new Morph feature to compare two mice in a way that will make it very obvious how they differ in 3D? Also, why not use the new Craft feature to build a NEW shape for you, then search the closest in the database or download a 3D-printable STL out of the box to test it out? All this and much more in V2 of The craft feature and multi-mouse painting is currently only for Lifetime Supporters, which has a one-time, lifetime regionalized payment, as I try to make FMM a more viable endeavor. You can still paint like/dislike on a single mouse and explore the options that way! If you decide to support me, you also get access to a private Discord channel where I will make sure to respond ASAP at any point, and lifetime access to any future feature. If you have any questions about FMM or anything else, feel free to ask here!

You like a hump from a mouse but the sides from another mouse? How about you just paint on the part you like in 3D and find a mouse that matches both on While you're at it, why not use the new Morph feature to compare two mice in a way that will make it very obvious how they differ in 3D? Also, why not use the new Craft feature to build a NEW shape for you, then search the closest in the database or download a 3D-printable STL out of the box to test it out? All this and much more in V2 of The craft feature and multi-mouse painting is currently only for Lifetime Supporters, which has a one-time, lifetime regionalized payment, as I try to make FMM a more viable endeavor. You can still paint like/dislike on a single mouse and explore the options that way! If you decide to support me, you also get access to a private Discord channel where I will make sure to respond ASAP at any point, and lifetime access to any future feature. If you have any questions about FMM or anything else, feel free to ask here!

bardOZ (Giovanni Laerte Frongia)

17,837 次观看 • 1 个月前

MC: To get to this point and become such a well-matched partnership, did you have to go through a lot of trial and error? Do you have any rules for working together or for being partners? 💚: For me, I wouldn’t really call them rules. I think it’s more like basic things that should already be there. For example, Love and I give each other space. When it comes to personal matters, we don’t interfere unless we come to each other for advice. We don’t have to ask things like, ‘Hey, what are you doing today?’ or anything like that. It’s not necessary to that extent. When we’re working, we focus on work. But when we’re apart, that’s our personal space, and that’s already okay. That alone is enough. I think if there’s something about work that doesn’t feel right, we just talk about it. #Flex1045xGirlRulesSeries #GirlRulesSeries #MilkLove #มิ้ลค์เลิฟ

MC: To get to this point and become such a well-matched partnership, did you have to go through a lot of trial and error? Do you have any rules for working together or for being partners? 💚: For me, I wouldn’t really call them rules. I think it’s more like basic things that should already be there. For example, Love and I give each other space. When it comes to personal matters, we don’t interfere unless we come to each other for advice. We don’t have to ask things like, ‘Hey, what are you doing today?’ or anything like that. It’s not necessary to that extent. When we’re working, we focus on work. But when we’re apart, that’s our personal space, and that’s already okay. That alone is enough. I think if there’s something about work that doesn’t feel right, we just talk about it. #Flex1045xGirlRulesSeries #GirlRulesSeries #MilkLove #มิ้ลค์เลิฟ

𝗠𝗜𝗩𝗡 - 𝗠𝗶𝗹𝗸 𝗣𝗮𝗻𝘀𝗮 𝟭𝘀𝘁 𝗩𝗡𝗙𝗣

114,453 次观看 • 8 个月前

Lambda Surgical founder Roman Stolyarov argues surgeons are quietly operating with less spatial information than a Tesla on the highway: "Surgeons today, they experience one of the same set of problems across many different procedures performed around the body. You just don't know how big things are. You're operating off of a camera. It's an instrument that's decades old. It gives you a projection of space. It doesn't really tell you anything about the space or the volume you're in. You don't know where your instruments are, and you can only see what you see. You can't really see below the surface of the tissue." "As I'm going through 10 years now in this space, I buy a Tesla and I experience full self-driving. You read so much about factory automation and autonomous drones, and you start to see how much physical AI has moved forward in the mobile robotic space in a way that it really hasn't yet in the surgical space." "If you look deeper, it's really all formulated on our ability to create a model of the world, of the spatial world specifically. We have to be able to first measure the environment we're in in three dimensions. We live in a three-dimensional world. And then to map and to model it. That capability is largely absent in 300 million plus surgeries that exist today." "We are developing the first 3D camera for surgery that enables a surgeon to, for the first time, have the full dimensionality of what they're doing in the operating room." Roman Stolyarov

Lambda Surgical founder Roman Stolyarov argues surgeons are quietly operating with less spatial information than a Tesla on the highway: "Surgeons today, they experience one of the same set of problems across many different procedures performed around the body. You just don't know how big things are. You're operating off of a camera. It's an instrument that's decades old. It gives you a projection of space. It doesn't really tell you anything about the space or the volume you're in. You don't know where your instruments are, and you can only see what you see. You can't really see below the surface of the tissue." "As I'm going through 10 years now in this space, I buy a Tesla and I experience full self-driving. You read so much about factory automation and autonomous drones, and you start to see how much physical AI has moved forward in the mobile robotic space in a way that it really hasn't yet in the surgical space." "If you look deeper, it's really all formulated on our ability to create a model of the world, of the spatial world specifically. We have to be able to first measure the environment we're in in three dimensions. We live in a three-dimensional world. And then to map and to model it. That capability is largely absent in 300 million plus surgeries that exist today." "We are developing the first 3D camera for surgery that enables a surgeon to, for the first time, have the full dimensionality of what they're doing in the operating room." Roman Stolyarov

MTS

11,033 次观看 • 3 个月前

Most Powerful Spatial AI for 3D Segmentation in #GaussianSplatting Major upgrade to our #SpatialAI! By defining just a few camera views, you can now segment extremely complex 3D objects with intricate geometries, including construction beams, industrial machinery, and beyond. ✅ No #3DGS retraining is required. Our spatial AI works seamlessly with any existing splats, enabling fast, on-the-fly 3D segmentation in photorealistic environments.

Most Powerful Spatial AI for 3D Segmentation in #GaussianSplatting Major upgrade to our #SpatialAI! By defining just a few camera views, you can now segment extremely complex 3D objects with intricate geometries, including construction beams, industrial machinery, and beyond. ✅ No #3DGS retraining is required. Our spatial AI works seamlessly with any existing splats, enabling fast, on-the-fly 3D segmentation in photorealistic environments.

Gauzilla Pro

13,963 次观看 • 1 个月前

What might a spatial harness look like for robotics? In this recording I show how Auki makes it possible to get multiple robots and devices collaboratively maintaining spatial context, and how we use augmented reality to interface both with the robots and each other.

What might a spatial harness look like for robotics? In this recording I show how Auki makes it possible to get multiple robots and devices collaboratively maintaining spatial context, and how we use augmented reality to interface both with the robots and each other.

Nils

14,119 次观看 • 19 天前

Demis on why world models are his longest standing passion and explains benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️

Demis on why world models are his longest standing passion and explains benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️

Bearly AI

78,545 次观看 • 5 个月前

This is insane!🔥 This is a 720p (2D) video I shot of my kids 15 years ago! I used AI to upscale it, depth-map it, & used the depth map to convert it to 3D SBS, & then converted that to Spatial Video for Apple Vision Pro (MV-HEVC). My son is currently a senior in high school, and my daughter is a sophomore in college. This video has complete spatial depth when viewed in the Apple Vision Pro. Obviously, you can't appreciate that via this post. But it's like I'm there & I can see into this room. Talk about giving you the feels.🥹 This can be done with ANY video. 🤯 I'm working on refining the workflow, as it's a bit cumbersome. I plan to share it, but holy cow! I had to post this.

This is insane!🔥 This is a 720p (2D) video I shot of my kids 15 years ago! I used AI to upscale it, depth-map it, & used the depth map to convert it to 3D SBS, & then converted that to Spatial Video for Apple Vision Pro (MV-HEVC). My son is currently a senior in high school, and my daughter is a sophomore in college. This video has complete spatial depth when viewed in the Apple Vision Pro. Obviously, you can't appreciate that via this post. But it's like I'm there & I can see into this room. Talk about giving you the feels.🥹 This can be done with ANY video. 🤯 I'm working on refining the workflow, as it's a bit cumbersome. I plan to share it, but holy cow! I had to post this.

Blaine Brown

1,469,030 次观看 • 2 年前

Chatbots aren’t the revolution. They’re the distraction. Fei-Fei Li: “Language is a half-million-year-old luxury. Perception is a half-billion-year-old necessity.” Evolution didn’t optimize for conversation. It optimized for survival in three-dimensional space. Seeing threats, navigating obstacles, predicting what happens when you move. We’ve spent years celebrating AI that can write and summarize. But text processing is narrow. Spatial intelligence is fundamental. An agent that only reads prompts can’t function in a warehouse or a hospital. It needs to parse depth, understand physics, and act on what it sees in real time. We built AI that understands language. Now we’re building AI that understands space. Language models got the attention. Spatial intelligence gets the work done. The world runs on physics, not paragraphs. AI is learning to operate in it.

Chatbots aren’t the revolution. They’re the distraction. Fei-Fei Li: “Language is a half-million-year-old luxury. Perception is a half-billion-year-old necessity.” Evolution didn’t optimize for conversation. It optimized for survival in three-dimensional space. Seeing threats, navigating obstacles, predicting what happens when you move. We’ve spent years celebrating AI that can write and summarize. But text processing is narrow. Spatial intelligence is fundamental. An agent that only reads prompts can’t function in a warehouse or a hospital. It needs to parse depth, understand physics, and act on what it sees in real time. We built AI that understands language. Now we’re building AI that understands space. Language models got the attention. Spatial intelligence gets the work done. The world runs on physics, not paragraphs. AI is learning to operate in it.

Dustin

51,814 次观看 • 8 个月前