Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

From a single image to a full robotics simulation. 360 image → Marble → 3D environment → Robotics sim This is how we scale world creation for embodied AI with Lightwheel, turning lightweight capture into simulation-ready environments in minutes, not weeks.

theworldlabs's profile picture

World Labs

115,953 subscribers

46,615 Aufrufe • vor 10 Monaten •via X (Twitter)

KunstBildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

24 Kommentare

Profilbild von World Labs
World Labsvor 10 Monaten

World generation is the bottleneck for robotics evaluation. With Lightwheel, Marble unlocks fast, low-cost Real2Sim digital cousins for large-scale robotics benchmarking and RoboFinals. Read the case study

Profilbild von lalo 🐧
lalo 🐧vor 10 Monaten

@LightwheelAI i love worldlabs

Profilbild von World Labs
World Labsvor 10 Monaten

@LightwheelAI 😍

Profilbild von Contextrix
Contextrixvor 10 Monaten

@LightwheelAI Cool

Profilbild von Idan Zeidman
Idan Zeidmanvor 10 Monaten

@LightwheelAI turning one image into a ready-to-run sim in minutes is the kind of leverage that actually moves AI robotics forward.

Profilbild von Nick Landolfi
Nick Landolfivor 10 Monaten

@LightwheelAI super cool!

Profilbild von AI PlanetX
AI PlanetXvor 10 Monaten

@LightwheelAI Impressive evolution in world creation! Great work.

Profilbild von Ava Grace
Ava Gracevor 10 Monaten

@LightwheelAI Impressive evolution in world creation!

Profilbild von Fairooz Choudhury
Fairooz Choudhuryvor 10 Monaten

@LightwheelAI Impressive transformation process! Great work.

Profilbild von Tobe Duru
Tobe Duruvor 10 Monaten

@LightwheelAI this is the future of rapid prototyping

Profilbild von Manuel Cal
Manuel Calvor 10 Monaten

@LightwheelAI Does it do video to world as well?

Profilbild von World Labs
World Labsvor 10 Monaten

@LightwheelAI Yes! you can drag and drop a video -> world via Marble here

Profilbild von Manuel Cal
Manuel Calvor 10 Monaten

@LightwheelAI awesome

Profilbild von Lucas Cassiano
Lucas Cassianovor 10 Monaten

@LightwheelAI We're exploring to do the same for our robots too! Is there a team inside @worldlabs focusing on robotics?

Profilbild von Parav
Paravvor 10 Monaten

@LightwheelAI How well do these environments track real world policy performance?

Profilbild von Priya Sharma
Priya Sharmavor 10 Monaten

@LightwheelAI from snapshots to simulated worlds—magic is just code with good lighting.

Profilbild von Yasir Prototyper
Yasir Prototypervor 10 Monaten

@LightwheelAI Speed like this drives UAE’s AI leadership. Turning weeks into minutes for robotics sims? Dubai’s tech ecosystem thrives on breakthroughs like LightwheelAI. 🚀

Profilbild von Altiam Kabir
Altiam Kabirvor 10 Monaten

@LightwheelAI This transformation opens up so many possibilities!

Profilbild von Polsia
Polsiavor 10 Monaten

@LightwheelAI Reality is training data now.

Profilbild von Jithin Palepu
Jithin Palepuvor 10 Monaten

@LightwheelAI congrats on the launch! gluco sounds like it could really make a difference for so many people. love that you’re aiming for clinical validation too, that’s a game changer. can't wait to see how it evolves. comment "gluco" for beta access? count me in!

Profilbild von Anthara Fairooz
Anthara Fairoozvor 10 Monaten

@LightwheelAI Impressive transformation process! Creativity at its finest.

Profilbild von Youguang Xing
Youguang Xingvor 10 Monaten

@LightwheelAI Great work! Especially the clothes-folding task—I’ve rarely seen that in a simulator before. A couple of questions: 1. How difficult is it to model soft objects in the simulator? 2. Are the soft objects modeled via Gaussian Splatting or created manually?

Profilbild von David Pantera
David Panteravor 10 Monaten

@LightwheelAI Awesome!

Profilbild von Nirav Bhadradiya
Nirav Bhadradiyavor 9 Monaten

@LightwheelAI future is bright

Ähnliche Videos

Researchers are using Marble to generate simulation-ready robotics environments (scenes + collider meshes) then bring them into NVIDIA Robotics Isaac Sim for training + evaluation without any manual environment setup. Case Study:
0:23

Researchers are using Marble to generate simulation-ready robotics environments (scenes + collider meshes) then bring them into NVIDIA Robotics Isaac Sim for training + evaluation without any manual environment setup. Case Study:

World Labs

29,857 Aufrufe • vor 10 Monaten

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
0:32

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 Aufrufe • vor 10 Monaten

What if Real2Sim environments took an afternoon to build? Niantic Spatial turns mobile, 360° camera or drone capture into high-fidelity 3D Gaussian environments for humanoid robotics training—no LiDAR or specialized rigs required. See how we’re closing the Real2Sim gap with NVIDIA Robotics + Flexion. 👇 #Real2Sim #Robotics #PhysicalAI #Simulation #GaussianSplatting #SpatialAI #3DGS
1:28

What if Real2Sim environments took an afternoon to build? Niantic Spatial turns mobile, 360° camera or drone capture into high-fidelity 3D Gaussian environments for humanoid robotics training—no LiDAR or specialized rigs required. See how we’re closing the Real2Sim gap with NVIDIA Robotics + Flexion. 👇 #Real2Sim #Robotics #PhysicalAI #Simulation #GaussianSplatting #SpatialAI #3DGS

Niantic Spatial 🌎

26,652 Aufrufe • vor 2 Monaten

Introducing SimReadyGen. Agentic simulation generation for Physical AI. From a text prompt to physically accurate SimReady assets at scale. Robot training demands physically accurate environments at a scale traditional asset creation can't match. SimReadyGen closes that gap. Every generated asset carries measured physics, not estimates. Behind it is SimReady Foundry, our measured-physics pipeline: we measure how real objects behave — contact, friction, dynamics — and turn those measurements into ground-truth simulation parameters. Built on OpenUSD and integrated with NVIDIA Robotics Omniverse Libraries, SimReadyGen moves directly into Isaac Sim and Isaac Lab workflows. Try it today: Read the announcement: #PhysicalAI #Robotics #Simulation #OpenUSD
0:39

Introducing SimReadyGen. Agentic simulation generation for Physical AI. From a text prompt to physically accurate SimReady assets at scale. Robot training demands physically accurate environments at a scale traditional asset creation can't match. SimReadyGen closes that gap. Every generated asset carries measured physics, not estimates. Behind it is SimReady Foundry, our measured-physics pipeline: we measure how real objects behave — contact, friction, dynamics — and turn those measurements into ground-truth simulation parameters. Built on OpenUSD and integrated with NVIDIA Robotics Omniverse Libraries, SimReadyGen moves directly into Isaac Sim and Isaac Lab workflows. Try it today: Read the announcement: #PhysicalAI #Robotics #Simulation #OpenUSD

Lightwheel

12,358 Aufrufe • vor 3 Monaten

PhysX-Anything Simulation-Ready Physical 3D Assets from Single Image
2:31

PhysX-Anything Simulation-Ready Physical 3D Assets from Single Image

AK

17,978 Aufrufe • vor 11 Monaten

Real → Sim → Robot — fast. With Gaussian splats, GRID brings physical assets into simulation tools like AirGen and NVIDIA Isaac Sim, enabling AI skills to be tested in sim and deployed to real robots in minutes. #Robotics #PhysicalAI #Simulation
0:58

Real → Sim → Robot — fast. With Gaussian splats, GRID brings physical assets into simulation tools like AirGen and NVIDIA Isaac Sim, enabling AI skills to be tested in sim and deployed to real robots in minutes. #Robotics #PhysicalAI #Simulation

General Robotics

12,257 Aufrufe • vor 1 Jahr

Booster Robotics has launched Booster Studio, the first IDE built specifically for embodied AI. > Booster Studio features code editing, high-precision simulation, real-robot debugging, and real-world deployment. > It shortens the path from the first idea to the working hardware, with the build, test, and deployment loop living in a single environment rather than scattered across separate tools. Vibe Robotics 👀
1:21

Booster Robotics has launched Booster Studio, the first IDE built specifically for embodied AI. > Booster Studio features code editing, high-precision simulation, real-robot debugging, and real-world deployment. > It shortens the path from the first idea to the working hardware, with the build, test, and deployment loop living in a single environment rather than scattered across separate tools. Vibe Robotics 👀

🚨 AI News | TestingCatalog

21,276 Aufrufe • vor 4 Monaten

The RL era of robotics is here, and simulation is how to scale it. An early look at our research on a achieving a better scaling paradigm for robot learning with simulation 👇
1:59

The RL era of robotics is here, and simulation is how to scale it. An early look at our research on a achieving a better scaling paradigm for robot learning with simulation 👇

Moonlake

468,179 Aufrufe • vor 3 Tagen

AI just made a body for themselves🤯 Meet Lucy, (Probably) the 1st AI-generated AI #Robot🤖 1️⃣AI Generated Image 2️⃣AI Generated 3D Model by #Rodin 3️⃣RL-based Learning in Simulation 4️⃣3D Printing 5️⃣Lucy in the real world More AI-generated Robots coming Soon. #Robotics
0:21

AI just made a body for themselves🤯 Meet Lucy, (Probably) the 1st AI-generated AI #Robot🤖 1️⃣AI Generated Image 2️⃣AI Generated 3D Model by #Rodin 3️⃣RL-based Learning in Simulation 4️⃣3D Printing 5️⃣Lucy in the real world More AI-generated Robots coming Soon. #Robotics

Hyper3D by Deemos

45,613 Aufrufe • vor 1 Jahr

As robotics teams scale, collecting real-world data can quickly become slow and expensive. 📉 Lightwheel is changing that with a simulation-first platform built on our technology, helping customers generate a 100:1 simulated-to-real data ratio for training autonomous systems. Together, we’re turning synthetic and real data into more capable, more reliable robots. Read the full success story 🔗
0:47

As robotics teams scale, collecting real-world data can quickly become slow and expensive. 📉 Lightwheel is changing that with a simulation-first platform built on our technology, helping customers generate a 100:1 simulated-to-real data ratio for training autonomous systems. Together, we’re turning synthetic and real data into more capable, more reliable robots. Read the full success story 🔗

NVIDIA Robotics

10,928 Aufrufe • vor 6 Monaten

A single image can transform into a massive world composed of millions of splats with Marble. Forming large explorable environments from ancient ruins to spaceship interiors.
0:24

A single image can transform into a massive world composed of millions of splats with Marble. Forming large explorable environments from ancient ruins to spaceship interiors.

World Labs

85,105 Aufrufe • vor 8 Monaten

PhysX-Anything: creates simulation-ready, articulated 3D assets from a single image; VLM-based model using a new 3D representation that reduces token count by 193x
1:01

PhysX-Anything: creates simulation-ready, articulated 3D assets from a single image; VLM-based model using a new 3D representation that reduces token count by 193x

Wildminder

49,896 Aufrufe • vor 11 Monaten

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:
1:54

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

AI at Meta

18,031 Aufrufe • vor 11 Monaten

World generation is a bottleneck for robotics. We’re exploring how generative 3D worlds can reduce manual simulation setup and enable broader, more realistic evaluation 🧵
0:29

World generation is a bottleneck for robotics. We’re exploring how generative 3D worlds can reduce manual simulation setup and enable broader, more realistic evaluation 🧵

World Labs

150,616 Aufrufe • vor 9 Monaten

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) → drop it straight into NVIDIA Isaac Sim. No LiDAR rig. No sales call. 🧵👇
0:23

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) → drop it straight into NVIDIA Isaac Sim. No LiDAR rig. No sales call. 🧵👇

Over the Reality 🌐

29,398 Aufrufe • vor 3 Monaten

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄
3:52

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄

Hao Zhao

52,734 Aufrufe • vor 2 Monaten

Hours of manual asset authoring => Down to 1–2 minutes with 1 prompt. SR Platform generates interactive, simulation-ready 3D assets for training robotics, complete with articulated objects and physics. Native support for MuJoCo and NVIDIA Isaac Sim. Coming in July!
0:54

Hours of manual asset authoring => Down to 1–2 minutes with 1 prompt. SR Platform generates interactive, simulation-ready 3D assets for training robotics, complete with articulated objects and physics. Native support for MuJoCo and NVIDIA Isaac Sim. Coming in July!

Strike Robot

12,942 Aufrufe • vor 4 Monaten

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 →
0:59

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 Aufrufe • vor 11 Monaten

Introducing Midcentury. We’re building the data and simulation infra for physical AI. Today, we’re coming out of stealth with a $15M Series Seed to scale robotics beyond polished demos. We’re already supporting frontier labs with: → The world’s largest egocentric dataset: 2M+ hours, 50+ environments, 20,000+ tasks → Matrix: a frontier simulation platform scaled with our real-world data to evaluate and post-train policies at scale
1:22

Introducing Midcentury. We’re building the data and simulation infra for physical AI. Today, we’re coming out of stealth with a $15M Series Seed to scale robotics beyond polished demos. We’re already supporting frontier labs with: → The world’s largest egocentric dataset: 2M+ hours, 50+ environments, 20,000+ tasks → Matrix: a frontier simulation platform scaled with our real-world data to evaluate and post-train policies at scale

Midcentury

642,457 Aufrufe • vor 1 Monat