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。

visionOS 26 is king. Just look at how it handles environment occlusion. Apps blend seamlessly with the real world, tucked behind static objects. This behavior is automatically applied to pinned widgets and Quick Look 3D models, and can be added to any entity in RealityKit.

Justin Ryan ᯅ

8,333 subscribers

10,632 次观看 • 1 年前 •via X (Twitter)

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

Playing around with World Labs' 3D generator and combining it with Runway vid2vid to blend myself and the background better. Although it's only a side perspective, you can tell it doesn't have that static image feel because of how the 3D environment is moving.

Playing around with World Labs' 3D generator and combining it with Runway vid2vid to blend myself and the background better. Although it's only a side perspective, you can tell it doesn't have that static image feel because of how the 3D environment is moving.

enigmatic_e

19,774 次观看 • 1 年前

Reworked my code and I can now import and manipulate multiple 3D models!! This now reminds me of the built-in Holograms apps on HoloLens. The simplest usecase is decorating your home with Sketchfab models ... would you make your home more personal with virtual objects? #visionOS

Reworked my code and I can now import and manipulate multiple 3D models!! This now reminds me of the built-in Holograms apps on HoloLens. The simplest usecase is decorating your home with Sketchfab models ... would you make your home more personal with virtual objects? #visionOS

Tina Debove ᯅ

21,603 次观看 • 3 年前

visionOS is just too beautiful to be just kept to Vision Pro…so we brought it to real life. It’s always so much fun to do these. I can’t get enough of how satisfying frosted glass Interfaces look in real life. It was quite complicated to rebuild AuraTap in the real world, especially with it having multiple overlapping layers. But It was totally worth it.

visionOS is just too beautiful to be just kept to Vision Pro…so we brought it to real life. It’s always so much fun to do these. I can’t get enough of how satisfying frosted glass Interfaces look in real life. It was quite complicated to rebuild AuraTap in the real world, especially with it having multiple overlapping layers. But It was totally worth it.

Phil Traut ᯅ

52,089 次观看 • 3 个月前

this is the future of CGI this new OpenMagic AI can add image, video or 3D product into real life video seamlessly with one click and.. it can even turn product image into 3D model automatically 10 wild examples:

this is the future of CGI this new OpenMagic AI can add image, video or 3D product into real life video seamlessly with one click and.. it can even turn product image into 3D model automatically 10 wild examples:

el.cine

120,995 次观看 • 1 年前

The concept of creating an exact digital replica of the physical world has always fascinated me: environments that look and behave exactly like our everyday reality, precisely captured in the digital domain. This is the essence of 𝐖𝐨𝐫𝐥𝐝 𝐌𝐨𝐝𝐞𝐥𝐬, simulated realities indistinguishable from our own. Generating these models is the core mission behind what we are building at SpAItial AI. True World Models must capture both photorealistic appearance and underlying physics, spatially-consistent across the environment. For static scenes, current models already deliver impressive results, unlocking downstream applications from gaming to 3D design. However, the true frontier lies in modeling dynamics, which will enable the training of AI agents whose learned behaviors can bridge the sim-to-real gap, thus unlocking countless real-world applications.

The concept of creating an exact digital replica of the physical world has always fascinated me: environments that look and behave exactly like our everyday reality, precisely captured in the digital domain. This is the essence of 𝐖𝐨𝐫𝐥𝐝 𝐌𝐨𝐝𝐞𝐥𝐬, simulated realities indistinguishable from our own. Generating these models is the core mission behind what we are building at SpAItial AI. True World Models must capture both photorealistic appearance and underlying physics, spatially-consistent across the environment. For static scenes, current models already deliver impressive results, unlocking downstream applications from gaming to 3D design. However, the true frontier lies in modeling dynamics, which will enable the training of AI agents whose learned behaviors can bridge the sim-to-real gap, thus unlocking countless real-world applications.

Matthias Niessner

21,586 次观看 • 5 个月前

this is over.. for traditional film studios Higgsfield just dropped Product-to-Video, you can now drop any product into any environment and.. the actor can even interact with it this is best way to do product commercial with AI.. for free here's how:

this is over.. for traditional film studios Higgsfield just dropped Product-to-Video, you can now drop any product into any environment and.. the actor can even interact with it this is best way to do product commercial with AI.. for free here's how:

el.cine

376,455 次观看 • 11 个月前

This is how plug-and-play Shopify sections look on the free Dawn theme No apps needed. Just drag, drop, and fully customize to match your brand Comment “31” and I’ll show you how to do it (must be following)

Burkisoy

24,327 次观看 • 1 年前

This is some quietly impressive work on making video world models actually controllable in 4D space. VerseCrafter lets you take an input image, use something like Blender to animate the 3D camera path and object trajectories, then uses that to condition generation. Scribbling in 2D feels so crude in comparison. The authors represent everything in a shared 4D world state - static background as a point cloud, moving objects as 3D gaussian trajectories. The gaussians are an interesting choice because they capture position, shape, and orientation probabilistically rather than forcing rigid bounding boxes or category specific models like SMPL-X for human bodies. They bolt this onto frozen Wan2.1 with a lightweight adapter, so they get a strong video prior. They also built a pipeline to auto extract 4D annotations from real world videos to train this puppy. It doesn't look sexy yet, but IMO this is the interface video world models need - actual 3D authoring tools to exert control rather than crude scribbles and prompt incantations.

This is some quietly impressive work on making video world models actually controllable in 4D space. VerseCrafter lets you take an input image, use something like Blender to animate the 3D camera path and object trajectories, then uses that to condition generation. Scribbling in 2D feels so crude in comparison. The authors represent everything in a shared 4D world state - static background as a point cloud, moving objects as 3D gaussian trajectories. The gaussians are an interesting choice because they capture position, shape, and orientation probabilistically rather than forcing rigid bounding boxes or category specific models like SMPL-X for human bodies. They bolt this onto frozen Wan2.1 with a lightweight adapter, so they get a strong video prior. They also built a pipeline to auto extract 4D annotations from real world videos to train this puppy. It doesn't look sexy yet, but IMO this is the interface video world models need - actual 3D authoring tools to exert control rather than crude scribbles and prompt incantations.

Bilawal Sidhu

25,802 次观看 • 6 个月前

I simply mirrored the trees on the Z axis and added screen distortion to make it look like they were being reflected in the water. The skybox is just a static image. Truth is, there was no water from the start.

I simply mirrored the trees on the Z axis and added screen distortion to make it look like they were being reflected in the water. The skybox is just a static image. Truth is, there was no water from the start.

Potemki11

111,902 次观看 • 4 个月前

I see moments like this one and all I can think about is how much jongin how to suddenly give up with his quick enlistment. And now look at him, he got to tour as a soloist and got to finally promote with his group, all in the same year 🥹

I see moments like this one and all I can think about is how much jongin how to suddenly give up with his quick enlistment. And now look at him, he got to tour as a soloist and got to finally promote with his group, all in the same year 🥹

ami

57,020 次观看 • 7 个月前

.Tencent Hy HY-World 2.0 has landed,fully OPEN SOURCE ! We kept hearing the same thing: world models look great, but you can't use the output. So we made one you can, real 3D assets you can edit, rearrange, and ship into production. Prompt to engine-ready 3D. For real this time： ✨Directly outputs editable, production-ready 3D assets ✨Seamlessly plugs into existing game pipelines ✨Multimodal input: text, image, videos 🪄Character mode: freely explore streets, buildings, and open worlds with realistic physics, collisions, and no time limits 🔗GitHub:

.Tencent Hy HY-World 2.0 has landed,fully OPEN SOURCE ! We kept hearing the same thing: world models look great, but you can't use the output. So we made one you can, real 3D assets you can edit, rearrange, and ship into production. Prompt to engine-ready 3D. For real this time： ✨Directly outputs editable, production-ready 3D assets ✨Seamlessly plugs into existing game pipelines ✨Multimodal input: text, image, videos 🪄Character mode: freely explore streets, buildings, and open worlds with realistic physics, collisions, and no time limits 🔗GitHub:

Tencent AI

116,648 次观看 • 3 个月前

From a friend in the Birmingham region this morning 🥴🥴🥴 how can anyone look at this and think it is normal?

From a friend in the Birmingham region this morning 🥴🥴🥴 how can anyone look at this and think it is normal?

Ant H (Fearmongerer)

25,339 次观看 • 1 年前

Any time I get a new barrel I patch it out and give it a quick inspection before screwing it on. Rifling is not supposed to look like this.👀 I'm ready of this run of luck with new stuff to be over any day now.

Any time I get a new barrel I patch it out and give it a quick inspection before screwing it on. Rifling is not supposed to look like this.👀 I'm ready of this run of luck with new stuff to be over any day now.

𝙼𝚁. 𝙻𝙴𝙰𝙳𝚂𝙻𝙸𝙽𝙶𝙴𝚁

402,173 次观看 • 8 个月前

FLOYD MIGHT NEED TO BE PLAYABLE IN THE NEXT GAME look how insane the combos can get with this character nahhhhh this is gas

FLOYD MIGHT NEED TO BE PLAYABLE IN THE NEXT GAME look how insane the combos can get with this character nahhhhh this is gas

Waz

93,770 次观看 • 1 个月前

Predicting how the environment changes over time is a key task in robotics, enabling all kinds of downstream tasks. Trace Anything is a very interesting look at how you can train models which predict the trajectory each point will take in the future -- you can use this for robot manipulation, video prediction, and more. Learn more ->

Predicting how the environment changes over time is a key task in robotics, enabling all kinds of downstream tasks. Trace Anything is a very interesting look at how you can train models which predict the trajectory each point will take in the future -- you can use this for robot manipulation, video prediction, and more. Learn more ->

Chris Paxton

56,845 次观看 • 7 个月前

This incredible new AI from WAN is about go VIRAL - here’s WHY WAN 2.2 is quickly proving stronger than I expected. This new open-source model doesn’t just swap characters - it can now blend real-world objects into your scene with surprising consistency. I explain how in more detail But first, check out the sorcery below 👇

This incredible new AI from WAN is about go VIRAL - here’s WHY WAN 2.2 is quickly proving stronger than I expected. This new open-source model doesn’t just swap characters - it can now blend real-world objects into your scene with surprising consistency. I explain how in more detail But first, check out the sorcery below 👇

Techguyver

47,891 次观看 • 10 个月前

They use real grass to hit off of for TGL. Here is a little behind the scenes look at how it gets in place. It’s quite the system! The engineering in the TGL setup is crazy.

They use real grass to hit off of for TGL. Here is a little behind the scenes look at how it gets in place. It’s quite the system! The engineering in the TGL setup is crazy.

Rick Golfs

130,701 次观看 • 1 年前

Now you can generate 3D animations directly from video. This is a behind the scenes look at 3D animator Jón Kristinsson using Move AI to capture and animate The Candy Man. Motion capture powered by AI. No suits or markers required.

Now you can generate 3D animations directly from video. This is a behind the scenes look at 3D animator Jón Kristinsson using Move AI to capture and animate The Candy Man. Motion capture powered by AI. No suits or markers required.

Move AI

457,835 次观看 • 2 年前

Former Biden-Harris staffer Ashely Allison on CNN NewsNight unintentionally reveals how the Democrat Party’s world view has become morally corrupt: “We are living in a hypocritical political environment right now, and it is hard to take any accusation and any stance of moral clarity with any real validity…”

Former Biden-Harris staffer Ashely Allison on CNN NewsNight unintentionally reveals how the Democrat Party’s world view has become morally corrupt: “We are living in a hypocritical political environment right now, and it is hard to take any accusation and any stance of moral clarity with any real validity…”

Steve Guest

77,560 次观看 • 1 个月前