Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Construction sites change fast. Constant site revisits are expensive and time-consuming. With Scaniverse, teams can capture and operationalize real-world environments with precision at scale using high-fidelity textured meshes and Gaussian splats. Monitor progress remotely, improve collaboration, document site conditions, and reduce unnecessary visits — all from a phone or...

NianticSpatial's profile picture

Niantic Spatial 🌎

963,115 subscribers

16,573 görüntüleme • 2 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Our product team walks through the full journey: Capture → Reconstruct → Localize Scaniverse creates high-fidelity 3D inputs from the real world—built for reconstruction, localization, and semantic understanding. Watch the full YouTube playlist: #NianticSpatial #Scaniverse #Reconstruction #VPS #GeospatialAI #AI #PhysicalAI
1:26

Our product team walks through the full journey: Capture → Reconstruct → Localize Scaniverse creates high-fidelity 3D inputs from the real world—built for reconstruction, localization, and semantic understanding. Watch the full YouTube playlist: #NianticSpatial #Scaniverse #Reconstruction #VPS #GeospatialAI #AI #PhysicalAI

Niantic Spatial 🌎

10,949 görüntüleme • 3 ay önce

🌎 The world in your pocket, now in 3D. For a limited time, upgrade to a Scaniverse Annual Plan by June 30 and get: ✅12 months for the price of 10 + up to 105,000 bonus cloud processing credits. ⏰Upgrade today! #NianticSpatial #Scaniverse #Reconstruction #3DScanning #GaussianSplat #360Capture #DigitalTwin #AI #GeospatialAI #PhysicalAI #VPS
0:29

🌎 The world in your pocket, now in 3D. For a limited time, upgrade to a Scaniverse Annual Plan by June 30 and get: ✅12 months for the price of 10 + up to 105,000 bonus cloud processing credits. ⏰Upgrade today! #NianticSpatial #Scaniverse #Reconstruction #3DScanning #GaussianSplat #360Capture #DigitalTwin #AI #GeospatialAI #PhysicalAI #VPS

Niantic Spatial 🌎

11,326 görüntüleme • 1 ay önce

How do you go from scanning a real-world space → using it in an app, workflow, or environment? Our product team walks through Scaniverse step-by-step, from capturing spaces to generating production-ready 3D assets and enabling precise, real-world positioning. In the first video, Senior Product Manager, Bec Maxworth, walks through your entry point into Scaniverse from signing up to getting started so you can start building high-fidelity 3D models in minutes. Dive into the full walkthrough here: #NianticSpatial #Scaniverse #Reconstruction #VPS #GeospatialAI #AI #PhysicalAI
0:31

How do you go from scanning a real-world space → using it in an app, workflow, or environment? Our product team walks through Scaniverse step-by-step, from capturing spaces to generating production-ready 3D assets and enabling precise, real-world positioning. In the first video, Senior Product Manager, Bec Maxworth, walks through your entry point into Scaniverse from signing up to getting started so you can start building high-fidelity 3D models in minutes. Dive into the full walkthrough here: #NianticSpatial #Scaniverse #Reconstruction #VPS #GeospatialAI #AI #PhysicalAI

Niantic Spatial 🌎

10,739 görüntüleme • 3 ay önce

Today, Niantic Spatial introduces Scaniverse — our flagship product and the gateway to our spatial intelligence platform and Large Geospatial Model. Here’s what’s new: 🔹Scaniverse (iOS mobile + web): Capture once, generate multiple outputs—VPS maps, meshes, and Gaussian splats (Android coming soon) 🔹Collaborative mapping: Multi-user scans fused into a single, continuously improving model 🔹 On-device validation: Preview VPS coverage and test localization in real time 🔹VPS 2.0: Global-scale positioning—centimeter-accurate where mapped, reliable everywhere else (even where GPS fails) 🔹NSDK 4.0 (coming soon): A unified SDK across Unity, Swift, Android, and ROS 2 Read more: #NianticSpatial #Scaniverse #VPS #GeospatialAI #AI
1:00

Today, Niantic Spatial introduces Scaniverse — our flagship product and the gateway to our spatial intelligence platform and Large Geospatial Model. Here’s what’s new: 🔹Scaniverse (iOS mobile + web): Capture once, generate multiple outputs—VPS maps, meshes, and Gaussian splats (Android coming soon) 🔹Collaborative mapping: Multi-user scans fused into a single, continuously improving model 🔹 On-device validation: Preview VPS coverage and test localization in real time 🔹VPS 2.0: Global-scale positioning—centimeter-accurate where mapped, reliable everywhere else (even where GPS fails) 🔹NSDK 4.0 (coming soon): A unified SDK across Unity, Swift, Android, and ROS 2 Read more: #NianticSpatial #Scaniverse #VPS #GeospatialAI #AI

Niantic Spatial 🌎

115,509 görüntüleme • 3 ay önce

📲💻Capture and scan with Scaniverse, then bring your sites directly into NSDK 4.0. A unified spatial data pipeline connects capture → reconstruction → localization → runtime—so your scans are immediately usable in your XR projects. Build with Unity, Swift, Kotlin, and early ROS2 support, and deploy high-performance experiences across mobile and robotic systems within your existing workflows. 🔗Get started today: #NianticSpatial #Scaniverse #NDSK #GeospatialAI #PhysicalAI #AI #XR #VR #Robotics #Unity #Kotlin #Swift
0:29

📲💻Capture and scan with Scaniverse, then bring your sites directly into NSDK 4.0. A unified spatial data pipeline connects capture → reconstruction → localization → runtime—so your scans are immediately usable in your XR projects. Build with Unity, Swift, Kotlin, and early ROS2 support, and deploy high-performance experiences across mobile and robotic systems within your existing workflows. 🔗Get started today: #NianticSpatial #Scaniverse #NDSK #GeospatialAI #PhysicalAI #AI #XR #VR #Robotics #Unity #Kotlin #Swift

Niantic Spatial 🌎

10,781 görüntüleme • 3 ay önce

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.
2:46

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 🌐

347,044 görüntüleme • 2 ay önce

Have you ever seen a robot walk along a waterfront, understand its surroundings, and look out at the sea? 🤖 Thanks to Over the Reality, this is possible. Places like this are mapped every day by our global community of 360 mappers. Using our technology, they are transformed into high-fidelity machine-readable 3D Gaussian Splats. This data can be used to: • navigate robots through the physical world • train AI and Visual Models • power VPS localization • anchor persistent XR content to real-world locations This is just one of more than 250,000 real-world locations already mapped by the Over the Reality community. And unlike traditional datasets, these places can be explored directly through a smartphone, browser, or XR headset, allowing anyone to navigate and experience them in first person. From city streets and waterfronts to landmarks and cultural sites, we're building one of the world's largest machine-readable maps for AI, robotics, and spatial computing.
0:36

Have you ever seen a robot walk along a waterfront, understand its surroundings, and look out at the sea? 🤖 Thanks to Over the Reality, this is possible. Places like this are mapped every day by our global community of 360 mappers. Using our technology, they are transformed into high-fidelity machine-readable 3D Gaussian Splats. This data can be used to: • navigate robots through the physical world • train AI and Visual Models • power VPS localization • anchor persistent XR content to real-world locations This is just one of more than 250,000 real-world locations already mapped by the Over the Reality community. And unlike traditional datasets, these places can be explored directly through a smartphone, browser, or XR headset, allowing anyone to navigate and experience them in first person. From city streets and waterfronts to landmarks and cultural sites, we're building one of the world's largest machine-readable maps for AI, robotics, and spatial computing.

Over the Reality 🌐

31,824 görüntüleme • 1 ay önce

Mind blown by this new CVPR 2026 paper: tttLRM🤯 It introduces a Test-Time Training layer for long-context autoregressive 3D reconstruction with linear complexity. Multiple image observations are compressed into fast weights that keep updating during inference, forming an implicit scene representation that can be decoded into explicit formats such as 3D Gaussian Splats. Progressive 3D reconstruction from streaming inputs is getting wild🥳It’s interesting to see how AI inference and real-world capture are starting to converge.
0:20

Mind blown by this new CVPR 2026 paper: tttLRM🤯 It introduces a Test-Time Training layer for long-context autoregressive 3D reconstruction with linear complexity. Multiple image observations are compressed into fast weights that keep updating during inference, forming an implicit scene representation that can be decoded into explicit formats such as 3D Gaussian Splats. Progressive 3D reconstruction from streaming inputs is getting wild🥳It’s interesting to see how AI inference and real-world capture are starting to converge.

KIRI Engine - 3D Scanner App

16,949 görüntüleme • 4 ay önce

Accessibility is the magic here. Anyone with a phone can do this. Capture > upload > process > boom - you’ve got a real environment stored as a 3DGS asset. Right before HalfRez in Chicago, I shot a few quick videos while walking around the city. Nothing planned, nothing fancy - just some passive captures while killing time. I processed them remotely, and now I’ve got three little Chicago Gaussian splats I can pull up whenever I want. Gaussian splats shine for exactly this: grabbing pieces of the real world and turning them into reusable 3D assets. I can drop them straight into OTOY Octane 2026 and treat them almost like standard 3D geometry. They’re perfect for: building out larger environments creating real-world set extensions capturing everyday places in tiny, efficient packages and storing “location assets” you can reuse later If you travel, or just find yourself in unique places, don’t forget the opportunity to take that world home with you!
1:49

Accessibility is the magic here. Anyone with a phone can do this. Capture > upload > process > boom - you’ve got a real environment stored as a 3DGS asset. Right before HalfRez in Chicago, I shot a few quick videos while walking around the city. Nothing planned, nothing fancy - just some passive captures while killing time. I processed them remotely, and now I’ve got three little Chicago Gaussian splats I can pull up whenever I want. Gaussian splats shine for exactly this: grabbing pieces of the real world and turning them into reusable 3D assets. I can drop them straight into OTOY Octane 2026 and treat them almost like standard 3D geometry. They’re perfect for: building out larger environments creating real-world set extensions capturing everyday places in tiny, efficient packages and storing “location assets” you can reuse later If you travel, or just find yourself in unique places, don’t forget the opportunity to take that world home with you!

Spenser Dickerson

19,831 görüntüleme • 8 ay önce

Another city. Another full 3D Gaussian Splat reconstruction. This entire neighborhood was captured while walking with an Insta360 X5, then processed with our GPU pipeline and transformed into a high-fidelity, machine-readable 3D environment with Over the Reality. What you’re seeing is not an isolated virtual world. It’s a 3D digital twin of a real-world location, built from structured spatial data where every building, street, and detail can become usable by AI, robotics, and XR. And it’s happening at scale, across cities in more than 180 countries every day. Have an Insta360 X5 and want to become a mapper? Apply here: Want to build a 3D Gaussian Splat from a video you already recorded? Do it for free at powered by Over the Reality.
2:42

Another city. Another full 3D Gaussian Splat reconstruction. This entire neighborhood was captured while walking with an Insta360 X5, then processed with our GPU pipeline and transformed into a high-fidelity, machine-readable 3D environment with Over the Reality. What you’re seeing is not an isolated virtual world. It’s a 3D digital twin of a real-world location, built from structured spatial data where every building, street, and detail can become usable by AI, robotics, and XR. And it’s happening at scale, across cities in more than 180 countries every day. Have an Insta360 X5 and want to become a mapper? Apply here: Want to build a 3D Gaussian Splat from a video you already recorded? Do it for free at powered by Over the Reality.

Over the Reality 🌐

400,097 görüntüleme • 2 ay önce

4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos Abstract: We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bias, 4DGT unifies static and dynamic components, enabling the modeling of complex, time-varying environments with varying object lifespans. We introduced a novel density control strategy in training, which allows our 4DGT to handle longer space-time input while maintaining efficient rendering at runtime. Our model processes 64 consecutive posed frames in a rolling-window fashion, predicting consistent 4D Gaussians in the scene. Unlike optimization-based methods, 4DGT performs purely feed-forward inference, reducing reconstruction time from hours to seconds and scaling effectively to long video sequences. Trained only on large-scale monocular posed video datasets, 4DGT can significantly outperform prior Gaussian-based networks in real-world videos and achieve on-par accuracy with optimization-based methods on cross-domain videos.
5:19

4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos Abstract: We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bias, 4DGT unifies static and dynamic components, enabling the modeling of complex, time-varying environments with varying object lifespans. We introduced a novel density control strategy in training, which allows our 4DGT to handle longer space-time input while maintaining efficient rendering at runtime. Our model processes 64 consecutive posed frames in a rolling-window fashion, predicting consistent 4D Gaussians in the scene. Unlike optimization-based methods, 4DGT performs purely feed-forward inference, reducing reconstruction time from hours to seconds and scaling effectively to long video sequences. Trained only on large-scale monocular posed video datasets, 4DGT can significantly outperform prior Gaussian-based networks in real-world videos and achieve on-par accuracy with optimization-based methods on cross-domain videos.

MrNeRF

34,782 görüntüleme • 1 yıl önce

Mansa AI is an enterprise-grade AI + Web3 platform designed to move artificial intelligence from experimentation into real-world execution. Built for creators, developers, and businesses, it focuses on deploying AI that actually works across modern digital systems, not just in isolated demos. 🚀 Production-ready AI infrastructure Mansa AI enables teams to deploy AI systems designed for live environments, handling real workflows, real data, and real operational demands without constant manual oversight. 🧠 Autonomous AI agents At its core, Mansa AI allows users to build autonomous agents that automate decision-making, coordinate tasks, monitor live signals, and execute complex workflows across dynamic environments. ⚙️ Fully customizable logic Agents can be configured with custom behaviors, triggers, and responses. From content generation and analytics to operational automation and intelligent orchestration, logic adapts to specific business strategies. 🔗 Web3 and off-chain integration Mansa AI bridges blockchain ecosystems with traditional systems, enabling cross-chain coordination, smart contract interactions, and seamless integration with existing enterprise infrastructure. 📊 Real-world use cases The platform supports automation for operations, customer engagement, analytics, data pipelines, content workflows, and AI-driven optimization across products and teams. 📈 Built for scale Whether launching as a startup or deploying across enterprise systems, Mansa AI is designed to scale AI operations without adding complexity or fragmentation. Mansa AI transforms artificial intelligence into deployable infrastructure. By combining autonomy, customization, interoperability, and scalability, it enables teams to own, operate, and grow intelligent systems that deliver real value in production environments.
2:00

Mansa AI is an enterprise-grade AI + Web3 platform designed to move artificial intelligence from experimentation into real-world execution. Built for creators, developers, and businesses, it focuses on deploying AI that actually works across modern digital systems, not just in isolated demos. 🚀 Production-ready AI infrastructure Mansa AI enables teams to deploy AI systems designed for live environments, handling real workflows, real data, and real operational demands without constant manual oversight. 🧠 Autonomous AI agents At its core, Mansa AI allows users to build autonomous agents that automate decision-making, coordinate tasks, monitor live signals, and execute complex workflows across dynamic environments. ⚙️ Fully customizable logic Agents can be configured with custom behaviors, triggers, and responses. From content generation and analytics to operational automation and intelligent orchestration, logic adapts to specific business strategies. 🔗 Web3 and off-chain integration Mansa AI bridges blockchain ecosystems with traditional systems, enabling cross-chain coordination, smart contract interactions, and seamless integration with existing enterprise infrastructure. 📊 Real-world use cases The platform supports automation for operations, customer engagement, analytics, data pipelines, content workflows, and AI-driven optimization across products and teams. 📈 Built for scale Whether launching as a startup or deploying across enterprise systems, Mansa AI is designed to scale AI operations without adding complexity or fragmentation. Mansa AI transforms artificial intelligence into deployable infrastructure. By combining autonomy, customization, interoperability, and scalability, it enables teams to own, operate, and grow intelligent systems that deliver real value in production environments.

King

155,637 görüntüleme • 7 ay önce

People will steal anything today. One of my subs had a ton of Dewalt tools stolen from a job site. While it doesn’t prevent every theft, I install Soliom wireless solar powered cameras at my sites and land. As long as you can get just a single bar on your cell phone in the area where you want the camera, you’ll get video feed. It’s motion activated and has cloud storage for all activity, just like a Ring camera, but needs no electricity or charging. Has standard def and high definition feed. Great for land, secluded areas and job sites with no electricity yet. I can also control camera from my phone. Highly recommend. I’m in Atlanta this weekend but can monitor work being done 300 miles away. You can either buy a SIM card from your wireless provider to use in the camera or pay $6/month for the camera cloud plan.
0:49

People will steal anything today. One of my subs had a ton of Dewalt tools stolen from a job site. While it doesn’t prevent every theft, I install Soliom wireless solar powered cameras at my sites and land. As long as you can get just a single bar on your cell phone in the area where you want the camera, you’ll get video feed. It’s motion activated and has cloud storage for all activity, just like a Ring camera, but needs no electricity or charging. Has standard def and high definition feed. Great for land, secluded areas and job sites with no electricity yet. I can also control camera from my phone. Highly recommend. I’m in Atlanta this weekend but can monitor work being done 300 miles away. You can either buy a SIM card from your wireless provider to use in the camera or pay $6/month for the camera cloud plan.

BowTiedBroke

92,343 görüntüleme • 1 yıl önce

World Labs and VIVE Mars are making it easier to turn ideas into shoot-ready 3D scenes, fast. World Labs new AI world-builder lets you create detailed virtual environments from a simple text or image prompt, then composite them live. Once the scene is ready, you can step straight into production using VIVE Mars CamTrack. Sign up at a discounted rate to start building worlds, and see how the full workflow comes together with VIVE Mars CamTrack and Marble. 👉 👉
2:24

World Labs and VIVE Mars are making it easier to turn ideas into shoot-ready 3D scenes, fast. World Labs new AI world-builder lets you create detailed virtual environments from a simple text or image prompt, then composite them live. Once the scene is ready, you can step straight into production using VIVE Mars CamTrack. Sign up at a discounted rate to start building worlds, and see how the full workflow comes together with VIVE Mars CamTrack and Marble. 👉 👉

HTC VIVE

40,988 görüntüleme • 8 ay önce

Introducing Nano Banana 2, our best image model yet 🍌🍌 It uses Gemini’s understanding of the world and is powered by real-time information and images from web search. That means it can better reflect real-world conditions in high-fidelity. Check out "Window Seat," a demo using Nano Banana 2’s world understanding to generate more accurate views from any window in the world, pulling live local weather info with 2K/4K specs. The precision is mind blowing. Rolling out today as the new default in the Google Gemini, Search (across 141 countries), and Flow + available in preview via Google AI Studio and Vertex AI. Also available in Google Google Antigravity.
0:28

Introducing Nano Banana 2, our best image model yet 🍌🍌 It uses Gemini’s understanding of the world and is powered by real-time information and images from web search. That means it can better reflect real-world conditions in high-fidelity. Check out "Window Seat," a demo using Nano Banana 2’s world understanding to generate more accurate views from any window in the world, pulling live local weather info with 2K/4K specs. The precision is mind blowing. Rolling out today as the new default in the Google Gemini, Search (across 141 countries), and Flow + available in preview via Google AI Studio and Vertex AI. Also available in Google Google Antigravity.

Sundar Pichai

921,937 görüntüleme • 5 ay önce

China’s construction tech is on another level! If you still picture construction sites with tones of workers swinging hammers, you’re officially stuck in the 90s. In China they’re out here building skyscrapers like it’s a speedrun challenge, with a tech stack that would make Silicon Valley jealous. AI-Powered Smart Sites Drones, IoT sensors, and AI are managing construction sites better than some human managers. Real-time safety alerts, automated progress tracking, and even predictive maintenance are standard tools, not fancy bonuses. Green Building Technologies Solar panels built into facades. Rainwater harvesting embedded into skyscrapers. Buildings that regulate their own temperature to save energy, not future dreams, but today’s standards. Robotics in Construction From brick-laying robots to rebar-tying machines, construction crews in China now have mechanical teammates with no lunch breaks, no grumbling. Welcome to Construction 2.0 (China Edition) Humans supervising, robots building! Gone are the days when a construction site meant a hundred+ guys with shovels. In China’s construction sites today, the machines are the real MVPs, humans mostly sip coffee and supervise. Bricklaying Human hands? Please. Robotic arms now lay bricks faster, straighter, and neater than your uncle’s weekend DIY projects. Some can lay 1,000+ bricks an hour and never ask for overtime. Excavation Remember digging trenches with shovels? That’s adorable. Now AI-guided autonomous excavators carve the earth with GPS-level precision while operators chill in air-conditioned control rooms. Concrete Pouring Giant robotic nozzles squeezing out entire building frames like they’re icing a wedding cake. Layers and layers, no sweat, no mess, no “oops, we need to redo that wall.” Welding You think shaky human hands are still melting steel together? Nah. Robot welders buzz and spark with perfect, tireless accuracy, even in places that are too risky for humans to reach. Inspection Sending humans to climb scaffolding 50 stories up? Very 2002. Now drones buzz around construction sites like paparazzi, scanning every beam, bolt, and brick, spotting defects before a human eye would even blink. Material Transport Why carry things manually when you can have self-driving forklifts and delivery bots moving steel, concrete, and pipes faster than an Amazon Prime truck? Site Monitoring Forget some guy in a neon vest wandering around with a clipboard. Today it’s AI-driven command centers tracking thousands of data points: worker safety, machinery health, material delivery schedules all from one giant screen. Project Planning Old: Paper blueprints and arguing architects. New: AI and BIM (Building Information Modeling) simulate the entire building in virtual reality before the first brick is even printed. This video shows how construction sites in China are now using robots to handle tasks like rebar placement, concrete pouring, and polishing, which has led to a 50% reduction in the workforce at some projects. The robots are proving to be more efficient, with one project's furnace robot achieving a 20% efficiency increase in just 5 days, saving 5% on labor costs. The construction company is developing even more advanced robots for future use as they work to improve smart construction technology for widespread real-time application. At China’s next-gen construction sites, humans don’t sweat, they strategize. Machines are not seen as luxury, they are seen as a necessity. Why does it matter? China is using 5G, AI, IoT, and robotics to build entire smart cities. And when the world comes looking for fast, sustainable, and scalable construction models… guess who’s already handing out the blueprints? Next time you hear: ‘Made in China,’ think bigger, it is: ‘Engineered for the future in China.’
0:36

China’s construction tech is on another level! If you still picture construction sites with tones of workers swinging hammers, you’re officially stuck in the 90s. In China they’re out here building skyscrapers like it’s a speedrun challenge, with a tech stack that would make Silicon Valley jealous. AI-Powered Smart Sites Drones, IoT sensors, and AI are managing construction sites better than some human managers. Real-time safety alerts, automated progress tracking, and even predictive maintenance are standard tools, not fancy bonuses. Green Building Technologies Solar panels built into facades. Rainwater harvesting embedded into skyscrapers. Buildings that regulate their own temperature to save energy, not future dreams, but today’s standards. Robotics in Construction From brick-laying robots to rebar-tying machines, construction crews in China now have mechanical teammates with no lunch breaks, no grumbling. Welcome to Construction 2.0 (China Edition) Humans supervising, robots building! Gone are the days when a construction site meant a hundred+ guys with shovels. In China’s construction sites today, the machines are the real MVPs, humans mostly sip coffee and supervise. Bricklaying Human hands? Please. Robotic arms now lay bricks faster, straighter, and neater than your uncle’s weekend DIY projects. Some can lay 1,000+ bricks an hour and never ask for overtime. Excavation Remember digging trenches with shovels? That’s adorable. Now AI-guided autonomous excavators carve the earth with GPS-level precision while operators chill in air-conditioned control rooms. Concrete Pouring Giant robotic nozzles squeezing out entire building frames like they’re icing a wedding cake. Layers and layers, no sweat, no mess, no “oops, we need to redo that wall.” Welding You think shaky human hands are still melting steel together? Nah. Robot welders buzz and spark with perfect, tireless accuracy, even in places that are too risky for humans to reach. Inspection Sending humans to climb scaffolding 50 stories up? Very 2002. Now drones buzz around construction sites like paparazzi, scanning every beam, bolt, and brick, spotting defects before a human eye would even blink. Material Transport Why carry things manually when you can have self-driving forklifts and delivery bots moving steel, concrete, and pipes faster than an Amazon Prime truck? Site Monitoring Forget some guy in a neon vest wandering around with a clipboard. Today it’s AI-driven command centers tracking thousands of data points: worker safety, machinery health, material delivery schedules all from one giant screen. Project Planning Old: Paper blueprints and arguing architects. New: AI and BIM (Building Information Modeling) simulate the entire building in virtual reality before the first brick is even printed. This video shows how construction sites in China are now using robots to handle tasks like rebar placement, concrete pouring, and polishing, which has led to a 50% reduction in the workforce at some projects. The robots are proving to be more efficient, with one project's furnace robot achieving a 20% efficiency increase in just 5 days, saving 5% on labor costs. The construction company is developing even more advanced robots for future use as they work to improve smart construction technology for widespread real-time application. At China’s next-gen construction sites, humans don’t sweat, they strategize. Machines are not seen as luxury, they are seen as a necessity. Why does it matter? China is using 5G, AI, IoT, and robotics to build entire smart cities. And when the world comes looking for fast, sustainable, and scalable construction models… guess who’s already handing out the blueprints? Next time you hear: ‘Made in China,’ think bigger, it is: ‘Engineered for the future in China.’

Evrim Kanbur

71,826 görüntüleme • 1 yıl önce

Nvidia announces GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning paper page: Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar geometries and often leads to degenerate body parts. To tackle these problems, we first propose a primitive-based 3D Gaussian representation where Gaussians are defined inside pose-driven primitives to facilitate animation. Second, to stabilize and amortize the learning of millions of Gaussians, we propose to use neural implicit fields to predict the Gaussian attributes (e.g., colors). Finally, to capture fine avatar geometries and extract detailed meshes, we propose a novel SDF-based implicit mesh learning approach for 3D Gaussians that regularizes the underlying geometries and extracts highly detailed textured meshes. Our proposed method, GAvatar, enables the large-scale generation of diverse animatable avatars using only text prompts. GAvatar significantly surpasses existing methods in terms of both appearance and geometry quality, and achieves extremely fast rendering (100 fps) at 1K resolution.
5:36

Nvidia announces GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning paper page: Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar geometries and often leads to degenerate body parts. To tackle these problems, we first propose a primitive-based 3D Gaussian representation where Gaussians are defined inside pose-driven primitives to facilitate animation. Second, to stabilize and amortize the learning of millions of Gaussians, we propose to use neural implicit fields to predict the Gaussian attributes (e.g., colors). Finally, to capture fine avatar geometries and extract detailed meshes, we propose a novel SDF-based implicit mesh learning approach for 3D Gaussians that regularizes the underlying geometries and extracts highly detailed textured meshes. Our proposed method, GAvatar, enables the large-scale generation of diverse animatable avatars using only text prompts. GAvatar significantly surpasses existing methods in terms of both appearance and geometry quality, and achieves extremely fast rendering (100 fps) at 1K resolution.

AK

140,992 görüntüleme • 2 yıl önce

For robots to be useful, they must be able to interact with a wide variety of environments; and yet, scaling interaction data is difficult, expensive, and time consuming. Instead, much research revolves around sim-to-real manipulation — but mostly this has not been mobile manipulation. Recently, though, this has begun to change. Two recent papers from Tairan He and Haoru Xue show us how to unlock the potential of this technique, building policies which, without any real data at all, can move objects around in the world and open doors in the real world with a humanoid robot. Watch Episode #60 of RoboPapers now to learn more, hosted by Chris Paxton and Jiafei Duan. In this episode, we cover two papers:. First is VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation; and second is DoorMan: Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer.
1:13:32

For robots to be useful, they must be able to interact with a wide variety of environments; and yet, scaling interaction data is difficult, expensive, and time consuming. Instead, much research revolves around sim-to-real manipulation — but mostly this has not been mobile manipulation. Recently, though, this has begun to change. Two recent papers from Tairan He and Haoru Xue show us how to unlock the potential of this technique, building policies which, without any real data at all, can move objects around in the world and open doors in the real world with a humanoid robot. Watch Episode #60 of RoboPapers now to learn more, hosted by Chris Paxton and Jiafei Duan. In this episode, we cover two papers:. First is VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation; and second is DoorMan: Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer.

RoboPapers

30,767 görüntüleme • 6 ay önce

🚀 Announcing Echo — our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world — not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly — even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering — but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows — digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations — all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction — environments that don’t just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. 🌍 #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out:
1:07

🚀 Announcing Echo — our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world — not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly — even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering — but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows — digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations — all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction — environments that don’t just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. 🌍 #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out:

SpAItial AI

176,105 görüntüleme • 7 ay önce

Today we are excited to open up Neuracore to the academic community! Neuracore is a new data foundation built to accelerate robot learning by removing one of the field’s biggest bottlenecks: capturing and working with high-fidelity multimodal robotics data. For the first time, researchers can store, view, and work with robotics data in a cloud-native system built specifically for large-scale learning, and we are making this core platform completely free for academia. The platform lets teams capture every sensor at its native rate, store and visualize data without loss, and then train and deploy models locally using our open-source code (Link in the comments). We are rolling out access to select academic institutions first. Anyone with an academic email can sign up, and if your institution is not part of the initial rollout, you will be able to join the waitlist directly. Beyond providing this infrastructure, we see an opportunity to build a global community where engineers and researchers can share, collaborate, and advance the frontier of robot learning together. Supported by our recent $3M pre-seed round led by Earlybird VC, we are excited to take this mission even further. Our long-term goal is for Neuracore to become the natural home for cutting-edge robot learning algorithms and real-world robotics experimentation, helping accelerate the next wave of Physical AI.
1:00

Today we are excited to open up Neuracore to the academic community! Neuracore is a new data foundation built to accelerate robot learning by removing one of the field’s biggest bottlenecks: capturing and working with high-fidelity multimodal robotics data. For the first time, researchers can store, view, and work with robotics data in a cloud-native system built specifically for large-scale learning, and we are making this core platform completely free for academia. The platform lets teams capture every sensor at its native rate, store and visualize data without loss, and then train and deploy models locally using our open-source code (Link in the comments). We are rolling out access to select academic institutions first. Anyone with an academic email can sign up, and if your institution is not part of the initial rollout, you will be able to join the waitlist directly. Beyond providing this infrastructure, we see an opportunity to build a global community where engineers and researchers can share, collaborate, and advance the frontier of robot learning together. Supported by our recent $3M pre-seed round led by Earlybird VC, we are excited to take this mission even further. Our long-term goal is for Neuracore to become the natural home for cutting-edge robot learning algorithms and real-world robotics experimentation, helping accelerate the next wave of Physical AI.

Neuracore

40,620 görüntüleme • 8 ay önce