Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Gaussian Splats are interesting technology, I saw one open-source scene last night and put it into one of my game. Want to share it here, this is how future web games might look like. 📷 Especially since now with AI synthetic data can be created.

Cem

2,108 subscribers

98,167 views • 1 month ago •via X (Twitter)

Gaming Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Gaussian Splats and AI combined can create really interesting scenes. 📷Here is an example

Gaussian Splats and AI combined can create really interesting scenes. 📷Here is an example

Cem

147,121 views • 1 month ago

I've been implementing multi-object combined LODs (actual LODs this time) for gaussian splats. It is insanely cool, due to the way I select LOD's I *always* render the same amount of splats no matter how many splats are in the scene. This scene has 108M total combined splats.

I've been implementing multi-object combined LODs (actual LODs this time) for gaussian splats. It is insanely cool, due to the way I select LOD's I always render the same amount of splats no matter how many splats are in the scene. This scene has 108M total combined splats.

Mykhailo Moroz

33,401 views • 24 days ago

The next frontier of AI is physical. 🤖 From simulation to synthetic data, developers are training robots to understand the real world with NVIDIA Cosmos, Isaac simulation frameworks and open-source physics engine, Newton. Watch the video to see how partners like Hon Hai Technology Group (Foxconn), Hexagon, Humanoid, Noble Machines, and Skild AI are building the future. 🎥

The next frontier of AI is physical. 🤖 From simulation to synthetic data, developers are training robots to understand the real world with NVIDIA Cosmos, Isaac simulation frameworks and open-source physics engine, Newton. Watch the video to see how partners like Hon Hai Technology Group (Foxconn), Hexagon, Humanoid, Noble Machines, and Skild AI are building the future. 🎥

NVIDIA Robotics

21,664 views • 3 months ago

I left a server online with VNC wide open to see how it would be interacted with. This is one of the more interesting interactions:

I left a server online with VNC wide open to see how it would be interacted with. This is one of the more interesting interactions:

James Woolley

743,376 views • 1 year ago

How is the Web changing due to AI? This visit to TinyFish yesterday goes deeply into just how. TinyFish makes a new kind of web browser. One that is started virtually. It is like a Google Chrome in the cloud. But it is very smart, can read and use any website, and your AI agents can talk to it. Here we talk about what it all means for business and the future of robots, brain computer interfaces, and AI glasses. It lets you build systems that can look at MANY websites at the same time and build new kinds of apps to do all sorts of new things.

How is the Web changing due to AI? This visit to TinyFish yesterday goes deeply into just how. TinyFish makes a new kind of web browser. One that is started virtually. It is like a Google Chrome in the cloud. But it is very smart, can read and use any website, and your AI agents can talk to it. Here we talk about what it all means for business and the future of robots, brain computer interfaces, and AI glasses. It lets you build systems that can look at MANY websites at the same time and build new kinds of apps to do all sorts of new things.

Robert Scoble

16,341 views • 6 months ago

This week on my podcast, The Most Interesting Thing in AI, I had the pleasure of talking with Audrey Tang about two big topics: How can AI help democracy? Audrey has helped get Taiwan to use the tools of modern technology to strengthen democracy even as they have frayed it around the world. What is the secret, and could it work in the U.S? How can we build humanistic and pluralistic values into the most powerful AI? Audrey has a great theory about the two races in AI---one vertical, and one horizontal---and how, with the tools of open-source, it's possible that we can align all future models with our highest ambitions. It’s a brilliant framework for thinking about the future of AI. I hope you'll listen to our conversation: Produced by Atlantic Re:think with PwC.

This week on my podcast, The Most Interesting Thing in AI, I had the pleasure of talking with Audrey Tang about two big topics: How can AI help democracy? Audrey has helped get Taiwan to use the tools of modern technology to strengthen democracy even as they have frayed it around the world. What is the secret, and could it work in the U.S? How can we build humanistic and pluralistic values into the most powerful AI? Audrey has a great theory about the two races in AI---one vertical, and one horizontal---and how, with the tools of open-source, it's possible that we can align all future models with our highest ambitions. It’s a brilliant framework for thinking about the future of AI. I hope you'll listen to our conversation: Produced by Atlantic Re:think with PwC.

nxthompson

28,514 views • 1 year ago

World Foundation Models (WFM) are the future of Physical AI, and we believe this future should be open-sourced. We are partnering with Valeo Group to build one of the largest open-source, multi-camera WFMs — redefining how Physical AI interacts with the real world.

World Foundation Models (WFM) are the future of Physical AI, and we believe this future should be open-sourced. We are partnering with Valeo Group to build one of the largest open-source, multi-camera WFMs — redefining how Physical AI interacts with the real world.

NATIX Network

260,572 views • 5 months ago

one year ago i saw this mitski quote in a video, and since then, though I don't like how i look, I started taking pictures of myself, and taking pictures to everything, like, i don't post it, but i have it there, for my future me, and that makes me happy somehow.

one year ago i saw this mitski quote in a video, and since then, though I don't like how i look, I started taking pictures of myself, and taking pictures to everything, like, i don't post it, but i have it there, for my future me, and that makes me happy somehow.

random mitski's.

51,535 views • 1 year ago

🚨 Jensen Huang says everyone panicked about the AI data when MOST training data was never REAL to begin with. Ilya Sutskever told the industry pre-training was over. "Ilya said, 'We're out of data,' or something like that. 'Pre-training is over,' or something like that," Huang says. "The industry panicked, you know, that this is the end of AI." "And of course, of course that's obviously not true. We're gonna keep on scaling the amount of data that we have to train with." "A lot of that data is probably gonna be synthetic." That's where the panic came from — synthetic data sounds like cheating. "Most of the data that we are training, that we teach each other with, inform each other with, is synthetic." "It's synthetic because it didn't come out of nature." "You created it. I'm consuming it. I modify it, augment it, I regenerate it, somebody else consumes it." The textbook in your hand is synthetic. The post you're reading is synthetic. The lecture you took is synthetic. Nature didn't make any of it. Humans did. AI just learned to do the same thing — faster. "Training is now limited by compute," Huang says. "Data is now limited by compute." The data wall wasn't a wall. It was a mirror. If you're new here, follow @AiEvolutio for the latest on ChatGPT, Claude, and the AI tools shaping how we work and create. — Jensen Huang ( NVIDIA ), NVIDIA CEO, on Lex Fridman's ( Lex Fridman ) podcast

🚨 Jensen Huang says everyone panicked about the AI data when MOST training data was never REAL to begin with. Ilya Sutskever told the industry pre-training was over. "Ilya said, 'We're out of data,' or something like that. 'Pre-training is over,' or something like that," Huang says. "The industry panicked, you know, that this is the end of AI." "And of course, of course that's obviously not true. We're gonna keep on scaling the amount of data that we have to train with." "A lot of that data is probably gonna be synthetic." That's where the panic came from — synthetic data sounds like cheating. "Most of the data that we are training, that we teach each other with, inform each other with, is synthetic." "It's synthetic because it didn't come out of nature." "You created it. I'm consuming it. I modify it, augment it, I regenerate it, somebody else consumes it." The textbook in your hand is synthetic. The post you're reading is synthetic. The lecture you took is synthetic. Nature didn't make any of it. Humans did. AI just learned to do the same thing — faster. "Training is now limited by compute," Huang says. "Data is now limited by compute." The data wall wasn't a wall. It was a mirror. If you're new here, follow @AiEvolutio for the latest on ChatGPT, Claude, and the AI tools shaping how we work and create. — Jensen Huang ( NVIDIA ), NVIDIA CEO, on Lex Fridman's ( Lex Fridman ) podcast

AI Evolution

15,565 views • 1 month ago

For me, the most important part of video creation right now is consistency. So I created my own GPT to achieve that. It's called AI Cinematic Consistency—and today, I want to share it with you and test it publicly. Let me explain why this matters 🧵 And here is the video I created using it.

For me, the most important part of video creation right now is consistency. So I created my own GPT to achieve that. It's called AI Cinematic Consistency—and today, I want to share it with you and test it publicly. Let me explain why this matters 🧵 And here is the video I created using it.

Jesus Plaza

395,188 views • 1 year ago

Instant Skinned Gaussian Avatars for Web, Mobile and VR Applications Short summary: In our system, we animate a background 3D mesh and have the Gaussian splats follow the mesh’s vertices. During preprocessing, splats are assigned to mesh vertices, and their relative transformations are stored. Once this data is saved, you can instantly use it in your applications without further preprocessing. At runtime, we animate the background 3D mesh, update the Gaussian splats in parallel, and resort all Gaussian splats every frame based on the viewer’s perspective.

Instant Skinned Gaussian Avatars for Web, Mobile and VR Applications Short summary: In our system, we animate a background 3D mesh and have the Gaussian splats follow the mesh’s vertices. During preprocessing, splats are assigned to mesh vertices, and their relative transformations are stored. Once this data is saved, you can instantly use it in your applications without further preprocessing. At runtime, we animate the background 3D mesh, update the Gaussian splats in parallel, and resort all Gaussian splats every frame based on the viewer’s perspective.

MrNeRF

66,016 views • 8 months ago

. Brian Murphy: "Can you put into words how flabbergasted you guys are that you're 24 games under since the Devers trade?" MINASIAN: "It's difficult to put into words... I wouldn't say it'a attributed to acquiring Rafi. It needs to be better, when I sit back and evaluate this, it's no one person."

. Brian Murphy: "Can you put into words how flabbergasted you guys are that you're 24 games under since the Devers trade?" MINASIAN: "It's difficult to put into words... I wouldn't say it'a attributed to acquiring Rafi. It needs to be better, when I sit back and evaluate this, it's no one person."

KNBR

34,708 views • 1 month ago

THIS IS IT. Kickstarter for our Game Finder vs Dating App vs Deck Builder is go! If you share one of my things this year, this is the one. We'd love for this to fund and shake up game discovery. But can only do it with your help. Back and share here:

THIS IS IT. Kickstarter for our Game Finder vs Dating App vs Deck Builder is go! If you share one of my things this year, this is the one. We'd love for this to fund and shake up game discovery. But can only do it with your help. Back and share here:

Andy Robertson

10,559 views • 1 year ago

✨SuperSplat 1.13.0 is here✨ Open source 3D Gaussian Splat Editor 🏃 Support for loading and playback of 4DGS (AKA animated gaussian splats) TRY SUPERSPLAT:

✨SuperSplat 1.13.0 is here✨ Open source 3D Gaussian Splat Editor 🏃 Support for loading and playback of 4DGS (AKA animated gaussian splats) TRY SUPERSPLAT:

Will Eastcott

76,763 views • 1 year ago

"you promised your grandpa it would be your last attempt to come back here. and now you’ve done it" marc: my grandpa saw it lived it up close and was super direct with me he told me “enough already” and i said “one last chance” and i’m sure he’s enjoying it now just like we are.

"you promised your grandpa it would be your last attempt to come back here. and now you’ve done it" marc: my grandpa saw it lived it up close and was super direct with me he told me “enough already” and i said “one last chance” and i’m sure he’s enjoying it now just like we are.

#9

124,271 views • 9 months ago

This is the power of VFX and AI now.. Creating volumetric effects in AI and then using AfterEffects and Premiere to layer and edit + Topaz Labs to upscale, you can visually achieve the same effects that would have taken me A LOT longer in Cinema4D/Blender. This is really amazing, only because if I can do this now with what we have, imagine where it will be in 6-mo 🔥 it will only get better. Soon we’ll be able to do a lot more within 3D environments with gaussian splats and volumetric effects. It won’t be long after that before Cinema, blender and others integrate gaussian splats and generative prompting directly into the software design and render process. At that point things are going to get REALLY BADASS! I’m chillin tonight, finally a night off lol. But tomorrow I’ll show you guys how I did this ❤️

This is the power of VFX and AI now.. Creating volumetric effects in AI and then using AfterEffects and Premiere to layer and edit + Topaz Labs to upscale, you can visually achieve the same effects that would have taken me A LOT longer in Cinema4D/Blender. This is really amazing, only because if I can do this now with what we have, imagine where it will be in 6-mo 🔥 it will only get better. Soon we’ll be able to do a lot more within 3D environments with gaussian splats and volumetric effects. It won’t be long after that before Cinema, blender and others integrate gaussian splats and generative prompting directly into the software design and render process. At that point things are going to get REALLY BADASS! I’m chillin tonight, finally a night off lol. But tomorrow I’ll show you guys how I did this ❤️

Dustin Hollywood

19,760 views • 7 months ago

I put my heart into this one, & I hope you'll spare a few minutes of your day to listen. This is "America, Stand Up." The clips in the video are not mine; however, I did the best I could with what I had. I hope you like/share it with those who might like it. (Justin Gaethje 🇺🇸)

I put my heart into this one, & I hope you'll spare a few minutes of your day to listen. This is "America, Stand Up." The clips in the video are not mine; however, I did the best I could with what I had. I hope you like/share it with those who might like it. (Justin Gaethje 🇺🇸)

J∅kër Kîng 👑

166,425 views • 23 days ago

🔥 INSANE: Free Kimi K2.6 might be the best open-source AI coder right now. It runs on NVIDIA’s own servers with a free API endpoint. No subscription. No credit card. No complicated setup. And because it’s OpenAI-compatible, you can plug it into tools like Claude Code, Roo, and Cline fast. This is one AI coding model I’d actually test ASAP.

🔥 INSANE: Free Kimi K2.6 might be the best open-source AI coder right now. It runs on NVIDIA’s own servers with a free API endpoint. No subscription. No credit card. No complicated setup. And because it’s OpenAI-compatible, you can plug it into tools like Claude Code, Roo, and Cline fast. This is one AI coding model I’d actually test ASAP.

Julian Goldie SEO

31,458 views • 2 months ago

60 million Gaussian splats. One massive dark fantasy world ready to explore! ⚔️ Created entirely with Marble, this persistent world is brought to life in-browser via our Spark 2.0 LoD system and Three.js Fly through it yourself and learn more about how it was made 👇

60 million Gaussian splats. One massive dark fantasy world ready to explore! ⚔️ Created entirely with Marble, this persistent world is brought to life in-browser via our Spark 2.0 LoD system and Three.js Fly through it yourself and learn more about how it was made 👇

World Labs

43,014 views • 2 months ago