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.

Today, we’re launching a new capability that connects everything we’ve been building directly to the robotics world: free USDZ export. Turn any real-world space into a robot training ground. For FREE. Capture with your smartphone or a 360 cam → get a simulation-ready USDZ (Gaussian splat + aligned mesh)... show more

Over the Reality 🌐

91,186 subscribers

28,572 views • 6 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Big news! World Labs' Marble is officially compatible with NVIDIA Robotics' Isaac Sim. Instead of showcasing their highlight reel, our team at Lightwheel created a full environment from a 360 pano using Marble and showed you can train directly in sim. The only non-generated assets are the robot arms, coffee, and bowl. Everything else was generated with Marble. Not sure how to do this yourself? NVIDIA wrote a technical blog with full instructions. You will learn how to: 1. Export scenes from World Labs' Marble as Gaussian splats 2. Convert to USD using NVIDIA Omniverse NuRec 3. Import into NVIDIA Isaac Sim 4. Add a robot and run the simulation Read the guide ➡️ #WorldModels #Robotics

Big news! World Labs' Marble is officially compatible with NVIDIA Robotics' Isaac Sim. Instead of showcasing their highlight reel, our team at Lightwheel created a full environment from a 360 pano using Marble and showed you can train directly in sim. The only non-generated assets are the robot arms, coffee, and bowl. Everything else was generated with Marble. Not sure how to do this yourself? NVIDIA wrote a technical blog with full instructions. You will learn how to: 1. Export scenes from World Labs' Marble as Gaussian splats 2. Convert to USD using NVIDIA Omniverse NuRec 3. Import into NVIDIA Isaac Sim 4. Add a robot and run the simulation Read the guide ➡️ #WorldModels #Robotics

Jonathan Stephens

13,783 views • 7 months ago

Introducing powered by Over the Reality. FreeGaussian is a new way to transform your existing photos, videos, and 360 captures for free into high-quality 3D Gaussian splats, directly in your browser. Whether you already have: ↳ a 360 recording captured with any 360 camera ↳ a set of photos ↳ or even a simple video from a place you visited you can now turn it into a photorealistic 3D Gaussian splat. Just go to upload your content, and let the reconstruction happen. Once it’s ready, you can download your 3D Gaussian splat and point cloud, and use them across your own projects, pipelines, or applications.

Introducing powered by Over the Reality. FreeGaussian is a new way to transform your existing photos, videos, and 360 captures for free into high-quality 3D Gaussian splats, directly in your browser. Whether you already have: ↳ a 360 recording captured with any 360 camera ↳ a set of photos ↳ or even a simple video from a place you visited you can now turn it into a photorealistic 3D Gaussian splat. Just go to upload your content, and let the reconstruction happen. Once it’s ready, you can download your 3D Gaussian splat and point cloud, and use them across your own projects, pipelines, or applications.

Over the Reality 🌐

86,231 views • 3 months ago

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

42,804 views • 5 months ago

One more thing 🚀 Qwen’s agentic capability is no longer limited to the digital world — we’re bringing it into physical world. With our in-house robotic agentic system and navigation model, Qwen can now control a robot to execute tasks in real-world. #qwen #embodied #robotics

One more thing 🚀 Qwen’s agentic capability is no longer limited to the digital world — we’re bringing it into physical world. With our in-house robotic agentic system and navigation model, Qwen can now control a robot to execute tasks in real-world. #qwen #embodied #robotics

xiong-hui (barry) chen

24,907 views • 2 months ago

NVIDIA just gave every robotics beginner a cheat code. You don’t need expensive hardware. You don’t need to burn motors. You don’t need to break prototypes. You can skip all of that. Because you can build the entire robot… virtually. With Isaac Sim, you design everything in simulation: Chassis. Wheels. Joints. All running on real physics. You add sensors—RGB cameras, 2D LiDAR—so your robot can actually see. You wire up control systems using ROS 2 and OmniGraph. You stream live sensor data straight into RViz. And suddenly… You’re not guessing anymore. You’re thinking like a robot. That’s the real shift. Simulation isn’t just practice. It’s leverage. You iterate faster. You break nothing. You ship something that actually works—before touching the real world. If you’re trying to get into robotics or physical AI… This isn’t optional. This is the new starting line.

NVIDIA just gave every robotics beginner a cheat code. You don’t need expensive hardware. You don’t need to burn motors. You don’t need to break prototypes. You can skip all of that. Because you can build the entire robot… virtually. With Isaac Sim, you design everything in simulation: Chassis. Wheels. Joints. All running on real physics. You add sensors—RGB cameras, 2D LiDAR—so your robot can actually see. You wire up control systems using ROS 2 and OmniGraph. You stream live sensor data straight into RViz. And suddenly… You’re not guessing anymore. You’re thinking like a robot. That’s the real shift. Simulation isn’t just practice. It’s leverage. You iterate faster. You break nothing. You ship something that actually works—before touching the real world. If you’re trying to get into robotics or physical AI… This isn’t optional. This is the new starting line.

Nainsi Dwivedi

26,312 views • 2 months ago

Here is how you turn a #GaussianSplatting into a walkable world with 2 clicks. First of all, do yourself a favour and try out PostShot. The splat you see was created from a 3-minute video taken with my phone. It ran for around 12 hours on a laptop with a 3060, and the output was beyond my expectations! That being said, whatever tool or app you use to create your Splat, you can import it directly into arrival.space from there you can: - Clean it up and compress it thanks to the direct integration with Supersplat Editor - Generate a rough mesh (that you can export with a paid plan and adjust in Blender ) - Explore it freely on the #web or in #VR Make sure to drop your Space in the comments. Would love to see it!

Here is how you turn a #GaussianSplatting into a walkable world with 2 clicks. First of all, do yourself a favour and try out PostShot. The splat you see was created from a 3-minute video taken with my phone. It ran for around 12 hours on a laptop with a 3060, and the output was beyond my expectations! That being said, whatever tool or app you use to create your Splat, you can import it directly into arrival.space from there you can: - Clean it up and compress it thanks to the direct integration with Supersplat Editor - Generate a rough mesh (that you can export with a paid plan and adjust in Blender ) - Explore it freely on the #web or in #VR Make sure to drop your Space in the comments. Would love to see it!

Gabriele Romagnoli

12,086 views • 1 year ago

It’s long been a dream of roboticists to be able to teach a robot in simulation so as to skip the long and expensive process of collecting large amounts of real-world training data. However, building simulations for robot tasks is extremely hard. Ideally, we could go from real data to a useful simulation. This is exactly what Guangqi Jiang and his co-authors do. they use 3d Gaussian splatting to reconstructed scenes which let them create interactive environments that, when combined with a physcs engine, allow for training robot policies that show zero-shot sim-to-real transfer (i.e., using no real-world demonstrations). To learn more, watch Episode 56 of Robopapers with Michael Cho - Rbt/Acc and Chris Paxton now!

It’s long been a dream of roboticists to be able to teach a robot in simulation so as to skip the long and expensive process of collecting large amounts of real-world training data. However, building simulations for robot tasks is extremely hard. Ideally, we could go from real data to a useful simulation. This is exactly what Guangqi Jiang and his co-authors do. they use 3d Gaussian splatting to reconstructed scenes which let them create interactive environments that, when combined with a physcs engine, allow for training robot policies that show zero-shot sim-to-real transfer (i.e., using no real-world demonstrations). To learn more, watch Episode 56 of Robopapers with Michael Cho - Rbt/Acc and Chris Paxton now!

RoboPapers

20,434 views • 7 months ago

We’ve just stepped into the future. Our AI, CERE, no longer just talks… It walks, moves, and interacts with you in real time! Cere Thanks to our integration with Robot TEMI, CERE is now embodied as a physical being: Meet Robot CERE! And with its GenAI integration, it can now talk to you on the spot. We’ve brought artificial intelligence into the physical world. Unveiled today at the expo — Tomorrow, it might be in your home, your office, or even on the street. Get ready: Technology is no longer just code — Cerebrum Tech #CERE #RobotCERE #ArtificialIntelligence #Robotics #CerebrumTech #AI #FutureTech

We’ve just stepped into the future. Our AI, CERE, no longer just talks… It walks, moves, and interacts with you in real time! Cere Thanks to our integration with Robot TEMI, CERE is now embodied as a physical being: Meet Robot CERE! And with its GenAI integration, it can now talk to you on the spot. We’ve brought artificial intelligence into the physical world. Unveiled today at the expo — Tomorrow, it might be in your home, your office, or even on the street. Get ready: Technology is no longer just code — Cerebrum Tech #CERE #RobotCERE #ArtificialIntelligence #Robotics #CerebrumTech #AI #FutureTech

Dr. R.Erdem ERKUL

367,264 views • 1 year ago

🐍Get ready for a wild spin with our new slot game, Medusa Money! 😂Every spin is a chance to dive into a quirky world! 🎁Free Coins: 💰Will you turn your luck to stone or strike it rich? Spin now and find out in Medusa Money!

🐍Get ready for a wild spin with our new slot game, Medusa Money! 😂Every spin is a chance to dive into a quirky world! 🎁Free Coins: 💰Will you turn your luck to stone or strike it rich? Spin now and find out in Medusa Money!

Cash Frenzy Casino

10,560 views • 1 month ago

Today, we’re launching a new way to create with AI. With OpenArt Worlds, you can generate a fully navigable 3D environment from a single prompt or image, step inside it, and capture shots exactly the way you envision them. No more starting over. No more inconsistent scenes. You build the world once - and create inside it. • Move through your scene freely • Find your angles • Add characters and elements • Capture production-ready shots

Today, we’re launching a new way to create with AI. With OpenArt Worlds, you can generate a fully navigable 3D environment from a single prompt or image, step inside it, and capture shots exactly the way you envision them. No more starting over. No more inconsistent scenes. You build the world once - and create inside it. • Move through your scene freely • Find your angles • Add characters and elements • Capture production-ready shots

OpenArt

7,300,394 views • 4 months ago

Gamma is now on Claude! You can generate a presentation with Gamma directly in your Claude chat. Connect Gamma and instantly turn any conversation into something you'd share with your team or present to the world. You can also: - Connect to Gmail, Slack, or HubSpot ("turn this email into a deck") - Fully edit your presentation in Gamma for any tweaks Take that research task, strategy proposal, or project summary and turn it into a polished presentation. Think with Claude. Visualize with Gamma.

Gamma is now on Claude! You can generate a presentation with Gamma directly in your Claude chat. Connect Gamma and instantly turn any conversation into something you'd share with your team or present to the world. You can also: - Connect to Gmail, Slack, or HubSpot ("turn this email into a deck") - Fully edit your presentation in Gamma for any tweaks Take that research task, strategy proposal, or project summary and turn it into a polished presentation. Think with Claude. Visualize with Gamma.

Gamma

80,285 views • 4 months ago

Robot simulation is getting a big upgrade! 🔥 Normally, building a simulation environment, a kitchen, warehouse, office takes days or weeks. You have to model the geometry, add textures, set lighting, generate collision meshes… all before a robot can even interact with it. Marble by World Labs removes most of that work. You type a text prompt or give it an image, and it generates a full 3D scene with depth, lighting, and a collider mesh you can export into engines like MuJoCo. That means researchers can quickly create lots of different environments to train robots on, which is exactly what domain randomization needs. If we want robots to learn faster, we need to create worlds faster. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Robot simulation is getting a big upgrade! 🔥 Normally, building a simulation environment, a kitchen, warehouse, office takes days or weeks. You have to model the geometry, add textures, set lighting, generate collision meshes… all before a robot can even interact with it. Marble by World Labs removes most of that work. You type a text prompt or give it an image, and it generates a full 3D scene with depth, lighting, and a collider mesh you can export into engines like MuJoCo. That means researchers can quickly create lots of different environments to train robots on, which is exactly what domain randomization needs. If we want robots to learn faster, we need to create worlds faster. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

15,498 views • 7 months ago

Introducing the Robora 3D Builder by our Co-Founder, Guang Cheng: a web based, drag and drop interface for rapid robotics prototyping. Designed for hobbyists and DIY enthusiasts, the MVP includes 5 - 8 essential hardware modules: wheeled bases, motors, servos, LiDAR, sensors, and an integrated starter brick for power and control. With a user friendly onboarding wizard, real time 3D visualization, and automatic component alignment, building a robot has never been easier. No coding or CAD required. Once your design is ready, export it as a URDF file or a parts list for quick prototyping, simulation, or assembly. Early access to the 3D Builder will be available through our Dapp shortly.

Introducing the Robora 3D Builder by our Co-Founder, Guang Cheng: a web based, drag and drop interface for rapid robotics prototyping. Designed for hobbyists and DIY enthusiasts, the MVP includes 5 - 8 essential hardware modules: wheeled bases, motors, servos, LiDAR, sensors, and an integrated starter brick for power and control. With a user friendly onboarding wizard, real time 3D visualization, and automatic component alignment, building a robot has never been easier. No coding or CAD required. Once your design is ready, export it as a URDF file or a parts list for quick prototyping, simulation, or assembly. Early access to the 3D Builder will be available through our Dapp shortly.

Robora

40,647 views • 10 months ago

Today I am extremely proud to introduce the Fury Autonomous Vehicle Orchestrator 🇺🇸 For the past 12 months, the Scout AI team has been building this quietly. Now we’re finally ready to unveil it to the world Just like AI agents are transforming the digital world, Fury Orchestrator brings that same agentic intelligence into the physical world for the U.S. warfighter It is the first agentic system that can take a commander’s high-level mission intent, spoken or typed in natural language, and turn it into coordinated autonomous action across a mixed fleet of unmanned assets More in 🧵

Today I am extremely proud to introduce the Fury Autonomous Vehicle Orchestrator 🇺🇸 For the past 12 months, the Scout AI team has been building this quietly. Now we’re finally ready to unveil it to the world Just like AI agents are transforming the digital world, Fury Orchestrator brings that same agentic intelligence into the physical world for the U.S. warfighter It is the first agentic system that can take a commander’s high-level mission intent, spoken or typed in natural language, and turn it into coordinated autonomous action across a mixed fleet of unmanned assets More in 🧵

Colby Adcock

213,401 views • 5 months ago

1/ 🧵 We’re thrilled to announce that Sol Strike is now LIVE on Devnet. 🎉 The wait is finally over. It’s time to jump into a completely new world of on-chain gaming. No downloads, no waiting, and no updates required. All the action is in your browser. Ready for the battle? 👇

1/ 🧵 We’re thrilled to announce that Sol Strike is now LIVE on Devnet. 🎉 The wait is finally over. It’s time to jump into a completely new world of on-chain gaming. No downloads, no waiting, and no updates required. All the action is in your browser. Ready for the battle? 👇

Sol Strike

19,975 views • 1 year ago

A big part of scaling robot learning to solve real-world problems is that we somehow need to get enough diverse, high-quality data to train our robots to perform useful things. GPT and its fellow large language models were bootstrapped and proved out on a massive dataset of real-world language data. Unfortunately, despite our best efforts, similarly massive datasets don’t really exist for robotics — so, in our unending pursuit of high-quality, useful data, we turn to simulation. I compared a couple recent works on sim-to-real robot manipulation, which discuss how to train perception-driven manipulation policies in simulation, in such a way that they’re useful in the real world. - DextraH-RGB, from NVIDIA - Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, also from NVIDIA — specifically the GEAR lab - Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, another GEAR lab paper - Local Policies Enable Zero-shot Long-Horizon Manipulation, from CMU (video from DextrAH-RGB)

A big part of scaling robot learning to solve real-world problems is that we somehow need to get enough diverse, high-quality data to train our robots to perform useful things. GPT and its fellow large language models were bootstrapped and proved out on a massive dataset of real-world language data. Unfortunately, despite our best efforts, similarly massive datasets don’t really exist for robotics — so, in our unending pursuit of high-quality, useful data, we turn to simulation. I compared a couple recent works on sim-to-real robot manipulation, which discuss how to train perception-driven manipulation policies in simulation, in such a way that they’re useful in the real world. - DextraH-RGB, from NVIDIA - Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, also from NVIDIA — specifically the GEAR lab - Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, another GEAR lab paper - Local Policies Enable Zero-shot Long-Horizon Manipulation, from CMU (video from DextrAH-RGB)

Chris Paxton

20,486 views • 1 year ago

today, we're launching Mosaic, the agentic video editor. in a world tending towards AI slop, create something real. no waitlist — public beta is now live at mosaic [dot] so. comment "MOSAIC" to get 1,000 free credits dropped into your account. this release comes with 7 key features (thread):

today, we're launching Mosaic, the agentic video editor. in a world tending towards AI slop, create something real. no waitlist — public beta is now live at mosaic [dot] so. comment "MOSAIC" to get 1,000 free credits dropped into your account. this release comes with 7 key features (thread):

Adish Jain ☕️

582,634 views • 9 months ago

turn any product photo into a full-blown ugc factory with n8n no models, no freelancers, no photoshop i built a workflow that takes a single product image and blends it into lifestyle shots of models -> exports ready-to-use ugc content in minutes here’s how it works: - drop any product photo into the flow - it pulls model shots from your folder auto-generates composites with your product placed naturally - saves finished images into a new folder we’ve been using it to spin out ad variants weekly want the json to try it? comment “UGC” + repost + follow and i’ll DM you the full build (must be following so i can DM)

turn any product photo into a full-blown ugc factory with n8n no models, no freelancers, no photoshop i built a workflow that takes a single product image and blends it into lifestyle shots of models -> exports ready-to-use ugc content in minutes here’s how it works: - drop any product photo into the flow - it pulls model shots from your folder auto-generates composites with your product placed naturally - saves finished images into a new folder we’ve been using it to spin out ad variants weekly want the json to try it? comment “UGC” + repost + follow and i’ll DM you the full build (must be following so i can DM)

J.B.

28,376 views • 10 months ago

Turning video into humanoid robot motion! 🤳🏼 Training humanoid robots needs huge amounts of motion data, but real-world capture doesn’t scale. Mocap is expensive, dangerous edge cases are rare, and you can’t ask humans to repeatedly fall or crash. Video2Robot tackles this by converting videos into physics-grounded humanoid simulations. Motion is generated to respect balance, inertia, ground contact, and joint limits, then directly retargeted to robot simulators. One prompt can generate a full humanoid motion sequence, including multi-agent interactions and failure cases like falls or collisions, scenarios that are hard or impossible to capture safely in the real world. The pipeline is model-agnostic and works with existing video generators, making it a practical way to scale data for robots. If robots are going to operate in the real world, they need to be trained on the failures too, not just the perfect demos. Here's the GitHub: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Turning video into humanoid robot motion! 🤳🏼 Training humanoid robots needs huge amounts of motion data, but real-world capture doesn’t scale. Mocap is expensive, dangerous edge cases are rare, and you can’t ask humans to repeatedly fall or crash. Video2Robot tackles this by converting videos into physics-grounded humanoid simulations. Motion is generated to respect balance, inertia, ground contact, and joint limits, then directly retargeted to robot simulators. One prompt can generate a full humanoid motion sequence, including multi-agent interactions and failure cases like falls or collisions, scenarios that are hard or impossible to capture safely in the real world. The pipeline is model-agnostic and works with existing video generators, making it a practical way to scale data for robots. If robots are going to operate in the real world, they need to be trained on the failures too, not just the perfect demos. Here's the GitHub: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

59,708 views • 7 months ago

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.

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 views • 2 months ago