Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Google and Meta just dropped a joint AI model that understands full 360° scene geometry. Depth, normals, sky masks, metric depth — state of the art. Code already public. THE SPATIAL COMPUTING INFRASTRUCTURE LAYER IS BEING QUIETLY BUILT.

0xMarioNawfal

253,455 subscribers

39,927 Aufrufe • vor 2 Monaten •via X (Twitter)

Nachrichten & Politik Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀 One universal model enables SoTA for: 🔥 Mono Depth Estimation 🔥 Multi-View SfM 🔥 Multi-View Stereo 🔥 Depth Completion 🔥 Registration … and many more possibilities! – plus everything is metric 🎯 We release code for data processing, training, benchmarking & ablations – everything Apache 2.0! Details & Links 👇

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀 One universal model enables SoTA for: 🔥 Mono Depth Estimation 🔥 Multi-View SfM 🔥 Multi-View Stereo 🔥 Depth Completion 🔥 Registration … and many more possibilities! – plus everything is metric 🎯 We release code for data processing, training, benchmarking & ablations – everything Apache 2.0! Details & Links 👇

Nikhil Keetha

123,025 Aufrufe • vor 11 Monaten

📁 Fei-Fei Li, former Google Chief Scientist, says the industry is dangerously fixated on language models. Most of the real economy is physical, perceptual and spatial. Once AI fully understands the visual world, it stops being a chatbot and starts becoming infrastructure.

📁 Fei-Fei Li, former Google Chief Scientist, says the industry is dangerously fixated on language models. Most of the real economy is physical, perceptual and spatial. Once AI fully understands the visual world, it stops being a chatbot and starts becoming infrastructure.

Jon Hernandez

216,225 Aufrufe • vor 3 Monaten

The robot’s “eyes” just received a big upgrade. LingBot-Depth 2.0, a depth-completion model with half the depth error just dropped. 12/16 benchmarks topped. Glass, mirrors, and transparent objects are so easy for us humans, but so hard for robots, because they do not behave like ordinary surfaces in a camera pipeline. A robot that misunderstands a balcony window or a table edge, will have a completely false planning inside a false world. Huge implecation. LingBot-Depth 2.0 takes an RGB image plus a broken depth map from a sensor and then outputs a cleaner depth map and a usable 3D point cloud. Numbers on LingBot-Depth 2.0 - Excels on glass, mirrors & transparent objects — where traditional depth cameras fail - Training data: 3M → 150M (50x scale-up) - 12 out of 16 first-place rankings on depth completion benchmarks - RMSE cut in half: 0.132 → 0.062 on the hardest indoor scenes LingBot-Vision trained on boundaries, because object edges carry the geometry robots need. No human boundary labels are used, which makes this approach easier to scale. The open-sourced LingBot-Vision is the general vision backbone, and LingBot-Depth 2.0 is the depth model built on it.

The robot’s “eyes” just received a big upgrade. LingBot-Depth 2.0, a depth-completion model with half the depth error just dropped. 12/16 benchmarks topped. Glass, mirrors, and transparent objects are so easy for us humans, but so hard for robots, because they do not behave like ordinary surfaces in a camera pipeline. A robot that misunderstands a balcony window or a table edge, will have a completely false planning inside a false world. Huge implecation. LingBot-Depth 2.0 takes an RGB image plus a broken depth map from a sensor and then outputs a cleaner depth map and a usable 3D point cloud. Numbers on LingBot-Depth 2.0 - Excels on glass, mirrors & transparent objects — where traditional depth cameras fail - Training data: 3M → 150M (50x scale-up) - 12 out of 16 first-place rankings on depth completion benchmarks - RMSE cut in half: 0.132 → 0.062 on the hardest indoor scenes LingBot-Vision trained on boundaries, because object edges carry the geometry robots need. No human boundary labels are used, which makes this approach easier to scale. The open-sourced LingBot-Vision is the general vision backbone, and LingBot-Depth 2.0 is the depth model built on it.

Rohan Paul

25,312 Aufrufe • vor 1 Monat

China just open-sourced AI that makes $200 cameras outperform $2,000 sensors. Ant Group dropped: → 3.2M training samples → Full code + models → Fixes depth cameras on glass, mirrors, metal A $200 consumer camera + free AI now beats $800 pro sensors. China is giving away the entire robotics stack. This is infrastructure-level disruption. ⬇️

China just open-sourced AI that makes $200 cameras outperform $2,000 sensors. Ant Group dropped: → 3.2M training samples → Full code + models → Fixes depth cameras on glass, mirrors, metal A $200 consumer camera + free AI now beats $800 pro sensors. China is giving away the entire robotics stack. This is infrastructure-level disruption. ⬇️

Shruti

284,466 Aufrufe • vor 6 Monaten

In collaboration with Intel, our Depth Fusion showcases the power of our LDM3D diffusion model in generating 360° views from text prompts provided by the user. The LDM3D diffusion model generates a 2D RGB image and its corresponding relative depth map providing a complete RGBD representation corresponding to the text prompt. The LDM 3D model is a specialized version of the stable diffusion V 1.4 model that has been modified to fit both image and depth map data.The model was then fine tuned on a subset of the Laion400M data set - large scale image caption data set. The depth maps used to fine tune our model were generated by the DPTBeiT large 512 depth estimation model that provides highly accurate relative depth estimates for each pixel. We take the generated 2D RGB image and depth map and use them to compute a 360° projection using touchdesigner. Touchdesigner is a versatile platform that allows for the creation of immersive and interactive multimedia experiences. Our application harnesses the power of touchdesigner to bring the generated 360° views to life, providing users with a unique and engaging way to experience their text prompts, whether it’s a description of a tranquil forest, a noisy cityscape or a futuristic sci fi world. Our depth fusion can bring these concepts to life in a vivid and immersive detail. - Scottie Fox, VP Engineering Blockade Labs ScottieFox #AI #VR #3D #gamedev #stablediffusion

In collaboration with Intel, our Depth Fusion showcases the power of our LDM3D diffusion model in generating 360° views from text prompts provided by the user. The LDM3D diffusion model generates a 2D RGB image and its corresponding relative depth map providing a complete RGBD representation corresponding to the text prompt. The LDM 3D model is a specialized version of the stable diffusion V 1.4 model that has been modified to fit both image and depth map data.The model was then fine tuned on a subset of the Laion400M data set - large scale image caption data set. The depth maps used to fine tune our model were generated by the DPTBeiT large 512 depth estimation model that provides highly accurate relative depth estimates for each pixel. We take the generated 2D RGB image and depth map and use them to compute a 360° projection using touchdesigner. Touchdesigner is a versatile platform that allows for the creation of immersive and interactive multimedia experiences. Our application harnesses the power of touchdesigner to bring the generated 360° views to life, providing users with a unique and engaging way to experience their text prompts, whether it’s a description of a tranquil forest, a noisy cityscape or a futuristic sci fi world. Our depth fusion can bring these concepts to life in a vivid and immersive detail. - Scottie Fox, VP Engineering Blockade Labs ScottieFox #AI #VR #3D #gamedev #stablediffusion

Blockade Labs

11,439 Aufrufe • vor 3 Jahren

EIF Insights Part 1: Power is everything. It’s reshaping the grid. Capital is everything. It’s reshaping infrastructure. Flexibility is everything. It’s reshaping computing. And distributed computing is the future. We’re moving toward clusters of computing infrastructure—built where power is abundant, scalable, and increasingly renewable. Instead of moving electrons long distances to compute, we can move compute closer to the electrons. The convergence is accelerating. Power isn’t just power anymore. Compute isn’t just compute anymore. The two are rapidly becoming one interconnected infrastructure layer. That convergence will create new technologies, new business models, and entirely new investment opportunities at the intersection of power and computing. $SLNH Soluna

EIF Insights Part 1: Power is everything. It’s reshaping the grid. Capital is everything. It’s reshaping infrastructure. Flexibility is everything. It’s reshaping computing. And distributed computing is the future. We’re moving toward clusters of computing infrastructure—built where power is abundant, scalable, and increasingly renewable. Instead of moving electrons long distances to compute, we can move compute closer to the electrons. The convergence is accelerating. Power isn’t just power anymore. Compute isn’t just compute anymore. The two are rapidly becoming one interconnected infrastructure layer. That convergence will create new technologies, new business models, and entirely new investment opportunities at the intersection of power and computing. $SLNH Soluna

John Belizaire

20,797 Aufrufe • vor 1 Monat

🤖 Ever seen a robot get confused by a glass door? That era is ending. Today, we're open-sourcing LingBot-Depth, a new spatial perception model that lets robots truly *see* the physical world, including transparent & reflective objects. It even surpasses top-tier industrial depth cameras in core metrics. A new sense of sight for embodied AI. #EmbodiedAI #Robotics #ComputerVision #OpenSource #DepthCamera

🤖 Ever seen a robot get confused by a glass door? That era is ending. Today, we're open-sourcing LingBot-Depth, a new spatial perception model that lets robots truly see the physical world, including transparent & reflective objects. It even surpasses top-tier industrial depth cameras in core metrics. A new sense of sight for embodied AI. #EmbodiedAI #Robotics #ComputerVision #OpenSource #DepthCamera

Robbyant

320,159 Aufrufe • vor 7 Monaten

Google just released Veo 2, a new state-of-the-art AI video model. In testing, Veo beat OpenAI Sora in BOTH quality and prompt adherence. The video compilation below is 100% created by AI (more details in thread):

Google just released Veo 2, a new state-of-the-art AI video model. In testing, Veo beat OpenAI Sora in BOTH quality and prompt adherence. The video compilation below is 100% created by AI (more details in thread):

Rowan Cheung

250,056 Aufrufe • vor 1 Jahr

We attacked the problem of robotics from an unusual angle: we started with phones. The spatial computing capability of the phone is much like that of a robot - it just has no arms and legs. That gave us the platform to build collaborative spatial computing for XR - that is immediately extendable to robotics proper. We started with simple robots - and soon we'll be showing you state of the art robots like the ones from Unitree integrated with the Auki network. Follow Phil Shaw | Auki Labs for behind the scenes looks.

We attacked the problem of robotics from an unusual angle: we started with phones. The spatial computing capability of the phone is much like that of a robot - it just has no arms and legs. That gave us the platform to build collaborative spatial computing for XR - that is immediately extendable to robotics proper. We started with simple robots - and soon we'll be showing you state of the art robots like the ones from Unitree integrated with the Auki network. Follow Phil Shaw | Auki Labs for behind the scenes looks.

Auki

45,632 Aufrufe • vor 1 Jahr

"This whole story and narrative that Google has already won is going to be harder to tell when the best model is actually an OpenAI model," D.A. Davidson's Gil Luria says. He also says that OpenAI will launch that "state-of-the-art" model "over the next few days, weeks."

"This whole story and narrative that Google has already won is going to be harder to tell when the best model is actually an OpenAI model," D.A. Davidson's Gil Luria says. He also says that OpenAI will launch that "state-of-the-art" model "over the next few days, weeks."

Yahoo Finance

12,410 Aufrufe • vor 6 Monaten

Most AI video work is just "generate and hope." This is different. Creator seungho__yeo ( IG ) rebuilt a live drum performance from the ground up. Using the drummer's actual motion data to redesign background mood, lighting, and spatial depth frame by frame. The pipeline: → Motion Tracking → Depth Mapping → AI Edit ( Seedance 2) → AI Relighting → Background Reconstruction → Cinematic Color Grading All built inside ComfyUI. This is what intentional AI production looks like. Not more generations, better direction. This is the level ComfyUI creators are working at.

Most AI video work is just "generate and hope." This is different. Creator seungho__yeo ( IG ) rebuilt a live drum performance from the ground up. Using the drummer's actual motion data to redesign background mood, lighting, and spatial depth frame by frame. The pipeline: → Motion Tracking → Depth Mapping → AI Edit ( Seedance 2) → AI Relighting → Background Reconstruction → Cinematic Color Grading All built inside ComfyUI. This is what intentional AI production looks like. Not more generations, better direction. This is the level ComfyUI creators are working at.

ComfyUI

28,385 Aufrufe • vor 2 Monaten

🚨🇨🇳 China unveils its first full-stack green AI computing platform The platform was launched in the city of Hohhot in north China's Inner Mongolia Autonomous Region, CCTV reports 🔸The goal is to unify computing resources, cut costs, and accelerate nationwide AI adoption through low-carbon infrastructure 🔸The platform is fully compatible with domestically produced chips and mainstream computing architectures 🔸Connects over 10 leading models from major telecom operators and tech firms This signals a major push toward scalable, energy-efficient national AI infrastructure built to support the next wave of model deployment and AI-driven services

🚨🇨🇳 China unveils its first full-stack green AI computing platform The platform was launched in the city of Hohhot in north China's Inner Mongolia Autonomous Region, CCTV reports 🔸The goal is to unify computing resources, cut costs, and accelerate nationwide AI adoption through low-carbon infrastructure 🔸The platform is fully compatible with domestically produced chips and mainstream computing architectures 🔸Connects over 10 leading models from major telecom operators and tech firms This signals a major push toward scalable, energy-efficient national AI infrastructure built to support the next wave of model deployment and AI-driven services

Sputnik

19,070 Aufrufe • vor 2 Monaten

Runway released Gen-4.5 today and it is already ranked first on the Video Arena leaderboard. We sat down with CEO Cristóbal Valenzuela to discuss how a small team is currently beating Google and Meta in the race for state-of-the-art video generation. The full episode is below!

Runway released Gen-4.5 today and it is already ranked first on the Video Arena leaderboard. We sat down with CEO Cristóbal Valenzuela to discuss how a small team is currently beating Google and Meta in the race for state-of-the-art video generation. The full episode is below!

Weights & Biases

367,588 Aufrufe • vor 8 Monaten

Very excited to share our first public release after I joined Robbyant! We present Lingbot-Depth 👀 — a state-of-the-art depth foundation model trained with RGB-D MAE on millions of real & simulated RGBD pairs. 🔹 Camera depths as natural masks for RGB-D MAE modeling 🔹 Large-scale real + sim RGBD data curation pipeline What surprised us most: ✨ Significant improvement on transparent, reflective surfaces, and thin structures — traditionally the hardest cases for depth models. 👇These are some of hard causal-capture images we tested on. The results are pretty good! #DepthEstimation #FoundationModels #EmbodiedAI #3DVision #Robotics #RobbyAnt

Very excited to share our first public release after I joined Robbyant! We present Lingbot-Depth 👀 — a state-of-the-art depth foundation model trained with RGB-D MAE on millions of real & simulated RGBD pairs. 🔹 Camera depths as natural masks for RGB-D MAE modeling 🔹 Large-scale real + sim RGBD data curation pipeline What surprised us most: ✨ Significant improvement on transparent, reflective surfaces, and thin structures — traditionally the hardest cases for depth models. 👇These are some of hard causal-capture images we tested on. The results are pretty good! #DepthEstimation #FoundationModels #EmbodiedAI #3DVision #Robotics #RobbyAnt

Yinghao Xu

22,664 Aufrufe • vor 6 Monaten

The next economy won't be visible to humans. AI agents will transact, settle, and coordinate value at machine speed, and the only rails built for that are crypto. In this episode of The Journeyman, I explain why the major layer 1s aren't just crypto infrastructure. They're the coordination substrate for an invisible economy that's already being built. As ever, please enjoy!

The next economy won't be visible to humans. AI agents will transact, settle, and coordinate value at machine speed, and the only rails built for that are crypto. In this episode of The Journeyman, I explain why the major layer 1s aren't just crypto infrastructure. They're the coordination substrate for an invisible economy that's already being built. As ever, please enjoy!

Raoul Pal

119,449 Aufrufe • vor 2 Monaten

AI video just stopped being a gated research project. Lightricks just dropped LTX-2: A flagship open-source video foundation model. Not a wrapper. Not a limited API. The actual system: Weights, code, and recipes, all public. Here is everything you need to know:

AI video just stopped being a gated research project. Lightricks just dropped LTX-2: A flagship open-source video foundation model. Not a wrapper. Not a limited API. The actual system: Weights, code, and recipes, all public. Here is everything you need to know:

Alex Patrascu

17,126 Aufrufe • vor 7 Monaten

“Scientific progress is becoming computable.” DeepMind CEO Demis Hassabis says AI is becoming a scientific infrastructure layer, not just a productivity tool. At Google I/O, he introduced Gemini for Science: a new set of AI systems designed to help researchers read papers, write code, and generate hypotheses faster. The real shift is that research itself is starting to scale like software.

“Scientific progress is becoming computable.” DeepMind CEO Demis Hassabis says AI is becoming a scientific infrastructure layer, not just a productivity tool. At Google I/O, he introduced Gemini for Science: a new set of AI systems designed to help researchers read papers, write code, and generate hypotheses faster. The real shift is that research itself is starting to scale like software.

Jon Hernandez

25,478 Aufrufe • vor 3 Monaten

Large-scale Gaussian splats have reached a new level of realism. This is a well-known temple in Bangkok, reconstructed as a high-fidelity 3D environment from 360 captures. At this level, the boundary between video and 3D starts to disappear. But what you’re looking at is not a video. It’s a dense spatial representation of a real place, where geometry, texture, and structure are preserved and made machine-readable. This kind of 3D data can power Visual AI, Robotics navigation, VPS localization, XR experiences, world models, and next-generation spatial computing systems. Built with Over the Reality.

Large-scale Gaussian splats have reached a new level of realism. This is a well-known temple in Bangkok, reconstructed as a high-fidelity 3D environment from 360 captures. At this level, the boundary between video and 3D starts to disappear. But what you’re looking at is not a video. It’s a dense spatial representation of a real place, where geometry, texture, and structure are preserved and made machine-readable. This kind of 3D data can power Visual AI, Robotics navigation, VPS localization, XR experiences, world models, and next-generation spatial computing systems. Built with Over the Reality.

Over the Reality 🌐

347,340 Aufrufe • vor 3 Monaten

AI is not one model. It is a five layer industrial stack: energy, chips and systems, infrastructure software, models, and applications. When America leads across that stack, we lead the next wave of growth.

AI is not one model. It is a five layer industrial stack: energy, chips and systems, infrastructure software, models, and applications. When America leads across that stack, we lead the next wave of growth.

NVIDIA Newsroom

13,522 Aufrufe • vor 8 Monaten

In Ackman's latest interview he divides the AI market, stating that it is not a bubble at the foundational layer, but highly risky at the software/model layer. He sees "near infinite demand" for compute. He believes infrastructure providers such as Microsoft, Amazon, Meta, and even SpaceX will earn massive returns on their data center investments. He is highly skeptical of pure model layer businesses like OpenAI and Anthropic. He notes they face massive capital burn rates and an existential threat from open-source models such as Chinese model and SpaceX that are driving the cost of AI access effectively to zero. A business model reliant on charging for proprietary models will collapse if open-source alternatives are essentially free. $AMZN $META $MSFT $SPCX

In Ackman's latest interview he divides the AI market, stating that it is not a bubble at the foundational layer, but highly risky at the software/model layer. He sees "near infinite demand" for compute. He believes infrastructure providers such as Microsoft, Amazon, Meta, and even SpaceX will earn massive returns on their data center investments. He is highly skeptical of pure model layer businesses like OpenAI and Anthropic. He notes they face massive capital burn rates and an existential threat from open-source models such as Chinese model and SpaceX that are driving the cost of AI access effectively to zero. A business model reliant on charging for proprietary models will collapse if open-source alternatives are essentially free. $AMZN $META $MSFT $SPCX

CapexAndChill

138,008 Aufrufe • vor 1 Monat