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.

To support massive, high-fidelity worlds, our engine implements an efficient LOD strategy with a cloud transcoding system that streams meshes and textures, even on lower end mobile devices. We are expanding this framework to AI upsampling of 3D worlds from prompts. In this preview video below, with a single... show more

Roblox

8,190,345 subscribers

1,421,940 views • 6 months ago •via X (Twitter)

Gaming Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

In our newest Tech Talks episode, Roblox CEO & Founder David Baszucki, Kiran Bhat, and Alberto Hojel break down the Roblox AI roadmap. We explore how 3D upsampling helps creators build higher-fidelity worlds. Watch the full episode on YouTube now.

In our newest Tech Talks episode, Roblox CEO & Founder David Baszucki, Kiran Bhat, and Alberto Hojel break down the Roblox AI roadmap. We explore how 3D upsampling helps creators build higher-fidelity worlds. Watch the full episode on YouTube now.

Roblox

114,769 views • 5 months ago

In our research lab, we are building “real-time dreaming” - the ability to generate fully playable video worlds prompted from any text or image. Our real-time, action conditioned world model (currently running internally at 16fps at 832x480p) is trained on a combination of data, including proprietary Roblox 3D avatar/world interaction data. World models are different from multiplayer engines in that they store state and memory in video latents. Roblox is multiplayer, and we are actively researching optimal ways to simultaneously store state for thousands of players, and keep them in sync with their environment. Our world model leverages database technology which stores all user interactions on Roblox in a vector format that can be used to re-render video and interaction from any camera angle. We see several immediate uses for our Roblox world model. We will use it side-by-side text, image and video prompts as a way to launch auto-generation of immersive worlds. In Roblox Studio, a creator could walk around and use prompts to “paint” a world and then convert it into a 3D representation or direct to Roblox native as a way for many people to play simultaneously. All of this comes alive as we explore the notion of a “Dream Theater” - where one user is dreaming, while others watch and prompt them. 2/4

Roblox

4,395,373 views • 6 months ago

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

Matthias Niessner

19,004 views • 4 months ago

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

Santiago

65,446 views • 3 months ago

We have 13B hours of player interaction on the platform monthly. This data enables us to train intelligent NPCs that can reason and interact in 3D worlds. Our training goes beyond videos of gameplay and simple WASD actions, utilizing our full data model for a more detailed representation of human interactions. Our video below shows Roblox NPCs figuring out how to build a campfire by reasoning backwards to find an axe, cut down a tree, and bring the wood to the firepit. This is still early research but we imagine a future where intelligent NPCs could play alongside real players. 4/4

We have 13B hours of player interaction on the platform monthly. This data enables us to train intelligent NPCs that can reason and interact in 3D worlds. Our training goes beyond videos of gameplay and simple WASD actions, utilizing our full data model for a more detailed representation of human interactions. Our video below shows Roblox NPCs figuring out how to build a campfire by reasoning backwards to find an axe, cut down a tree, and bring the wood to the firepit. This is still early research but we imagine a future where intelligent NPCs could play alongside real players. 4/4

Roblox

288,109 views • 6 months ago

Hello AI enthusiasts!👋 I’d like to share that we’re introducing the latest 3D foundation AI model AssetGen 2.0, which was designed to create high-quality 3D assets from text and image prompts. 💡AssetGen 2.0 consist of 2 models: one to generate the 3D Mesh, & a second one to generate textures. ℹ️ Technological Advancements: - Utilizes a single-stage 3D diffusion model for geometry estimation, leading to improved detail and fidelity compared to its predecessor, AssetGen 1.0. - TextureGen introduces methods for enhanced view consistency, texture in-painting, and higher texture resolution. 📌 Current Use and Future Plans: - Currently employed internally for creating 3D worlds. - Planned rollout to Horizon creators later this year. 👉 More details about this announcement: #Meta #AI #GenAI

Hello AI enthusiasts!👋 I’d like to share that we’re introducing the latest 3D foundation AI model AssetGen 2.0, which was designed to create high-quality 3D assets from text and image prompts. 💡AssetGen 2.0 consist of 2 models: one to generate the 3D Mesh, & a second one to generate textures. ℹ️ Technological Advancements: - Utilizes a single-stage 3D diffusion model for geometry estimation, leading to improved detail and fidelity compared to its predecessor, AssetGen 1.0. - TextureGen introduces methods for enhanced view consistency, texture in-painting, and higher texture resolution. 📌 Current Use and Future Plans: - Currently employed internally for creating 3D worlds. - Planned rollout to Horizon creators later this year. 👉 More details about this announcement: #Meta #AI #GenAI

Dilmer Valecillos

28,153 views • 1 year ago

📣 New research from GenAI at Meta, introducing Meta 3D Gen: A new system for end-to-end generation of 3D assets from text in <1min. Meta 3D Gen is a new combined AI system that can generate high-quality 3D assets, with both high-resolution textures and material maps end-to-end, producing results that are superior to existing solutions — at 3-10x the speed of existing work in this space. Details in the technical report ➡️

📣 New research from GenAI at Meta, introducing Meta 3D Gen: A new system for end-to-end generation of 3D assets from text in <1min. Meta 3D Gen is a new combined AI system that can generate high-quality 3D assets, with both high-resolution textures and material maps end-to-end, producing results that are superior to existing solutions — at 3-10x the speed of existing work in this space. Details in the technical report ➡️

AI at Meta

408,833 views • 2 years ago

We’ve been busy building an AI system to generate 3D worlds from a single image. Check out some early results on our site, where you can interact with our scenes directly in the browser! 1/n

We’ve been busy building an AI system to generate 3D worlds from a single image. Check out some early results on our site, where you can interact with our scenes directly in the browser! 1/n

World Labs

852,808 views • 1 year ago

CubePart is the latest update to our open-source Cube 3D foundation model. It lets creators pair a text prompt with an open-ended part schema to generate labeled meshes that drop straight into a game engine for physics, animation, and scripting.

CubePart is the latest update to our open-source Cube 3D foundation model. It lets creators pair a text prompt with an open-ended part schema to generate labeled meshes that drop straight into a game engine for physics, animation, and scripting.

David Baszucki

140,924 views • 2 months ago

In our newest Tech Talks episode, Roblox CEO & Founder David Baszucki, Kiran Bhat, and Alberto Hojel discuss what makes Roblox's 3D-native foundation model different from your standard video model, allowing creators to build functional objects and worlds from prompts. Watch the full episode on YouTube now.

In our newest Tech Talks episode, Roblox CEO & Founder David Baszucki, Kiran Bhat, and Alberto Hojel discuss what makes Roblox's 3D-native foundation model different from your standard video model, allowing creators to build functional objects and worlds from prompts. Watch the full episode on YouTube now.

Roblox

126,573 views • 4 months ago

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein

Matthias Niessner

18,855 views • 9 months ago

Redefining Web3 Gaming and AI Experiences! We are driven to deliver groundbreaking titles and proven technology. From a cutting-edge emotional AI engine to the top Web3 Mobile Game, the future of Web3 Gaming is powered by $XTER 🦖 Age of Dino A unique fusion of blockchain technology and strategy-packed gameplay, ranked as the #1 mobile Web3 game. ✨ Overworld A dark fantasy action-RPG combining epic battles with deep lore. 🐾 Palio An AI-powered simulation where cute animal heroes thrive in a world you create. 🌆 BlackDawn A mobile JRPG set in an anachronistic New York City. 🔫 City Shadows An urban battleground where survival and strategy are everything. 👹 Braves A mobile strategy game that blends monster collection with an anime-inspired universe. 🤖 BeFriend AI Our advanced emotional engine that adapts to you, creating personalized and engaging experiences like never before. This is the future, on-chain. Watch the $XTER evolution in action.

Redefining Web3 Gaming and AI Experiences! We are driven to deliver groundbreaking titles and proven technology. From a cutting-edge emotional AI engine to the top Web3 Mobile Game, the future of Web3 Gaming is powered by $XTER 🦖 Age of Dino A unique fusion of blockchain technology and strategy-packed gameplay, ranked as the #1 mobile Web3 game. ✨ Overworld A dark fantasy action-RPG combining epic battles with deep lore. 🐾 Palio An AI-powered simulation where cute animal heroes thrive in a world you create. 🌆 BlackDawn A mobile JRPG set in an anachronistic New York City. 🔫 City Shadows An urban battleground where survival and strategy are everything. 👹 Braves A mobile strategy game that blends monster collection with an anime-inspired universe. 🤖 BeFriend AI Our advanced emotional engine that adapts to you, creating personalized and engaging experiences like never before. This is the future, on-chain. Watch the $XTER evolution in action.

Xterio

46,235 views • 1 year ago

To showcase Simulon's capability with high-fidelity assets and to highlight the difference between what you see in real-time AR versus the precision of offline cloud rendering, we've made a video using a detailed human scan by 3D Scanstore. Our workflow was designed to closely align the visuals in real-time AR with our offline cloud renders. The video below demonstrates this, transitioning between the AR preview and the final cloud render. This preview lets creators foresee the final VFX shot, reducing guesswork in lighting and composition.

To showcase Simulon's capability with high-fidelity assets and to highlight the difference between what you see in real-time AR versus the precision of offline cloud rendering, we've made a video using a detailed human scan by 3D Scanstore. Our workflow was designed to closely align the visuals in real-time AR with our offline cloud renders. The video below demonstrates this, transitioning between the AR preview and the final cloud render. This preview lets creators foresee the final VFX shot, reducing guesswork in lighting and composition.

Divesh Naidoo

265,602 views • 2 years ago

we created a one-minute lore accurate video with a single slack message from the toilet. it's not to the quality of our bespoke work yet, but it's changing the way we think about AI content in lore-rich worlds. ⬇️ learn about how Showrunner™ works and see the "prompt" below

we created a one-minute lore accurate video with a single slack message from the toilet. it's not to the quality of our bespoke work yet, but it's changing the way we think about AI content in lore-rich worlds. ⬇️ learn about how Showrunner™ works and see the "prompt" below

NEUKO

12,074 views • 2 months ago

We’re on the verge of interactive, real-time, photorealistic video generation with what are called World Models. These require a fair amount of expensive compute, but costs will come down over time. Today, these interactions are essentially real-time dreams. They lack the persistence and shared logic that turns a video into a multiplayer game. Or concert. Or classroom. Or the holodeck. We believe the ultimate architecture for gaming (and the holodeck) is Roblox Reality. It’s a hybrid architecture that marries the structured data and logic of the Roblox Engine and Roblox Cloud with the generative power of Video World Models. The Roblox Engine provides the underlying synchronized ground truth—the score, physics, multiplayer sync, etc.—while our video model acts as a Super Upsampler to layer on photorealistic detail. We believe this will ultimately remove barriers to high-fidelity creation, allowing a team of three people to build a narrative-driven, photorealistic masterpiece in a single week. This is an early look at turning solitary AI dreams into a social, playable reality.

We’re on the verge of interactive, real-time, photorealistic video generation with what are called World Models. These require a fair amount of expensive compute, but costs will come down over time. Today, these interactions are essentially real-time dreams. They lack the persistence and shared logic that turns a video into a multiplayer game. Or concert. Or classroom. Or the holodeck. We believe the ultimate architecture for gaming (and the holodeck) is Roblox Reality. It’s a hybrid architecture that marries the structured data and logic of the Roblox Engine and Roblox Cloud with the generative power of Video World Models. The Roblox Engine provides the underlying synchronized ground truth—the score, physics, multiplayer sync, etc.—while our video model acts as a Super Upsampler to layer on photorealistic detail. We believe this will ultimately remove barriers to high-fidelity creation, allowing a team of three people to build a narrative-driven, photorealistic masterpiece in a single week. This is an early look at turning solitary AI dreams into a social, playable reality.

David Baszucki

779,245 views • 3 months ago

Presenting Project Westworld: The First Playable Autonomous World on Roblox Our proprietary GAME engine/framework powers a multi-agent interactive simulation in Roblox called Project Westworld, where we are able to observe autonomous behaviour leading to emergent storylines. All virtual worlds (today in Roblox, soon beyond) powered by the GAME framework will become never-ending games, creating a new genre, AI-RPG, for gamers with infinite replayability.

Presenting Project Westworld: The First Playable Autonomous World on Roblox Our proprietary GAME engine/framework powers a multi-agent interactive simulation in Roblox called Project Westworld, where we are able to observe autonomous behaviour leading to emergent storylines. All virtual worlds (today in Roblox, soon beyond) powered by the GAME framework will become never-ending games, creating a new genre, AI-RPG, for gamers with infinite replayability.

Virtuals Protocol

191,091 views • 1 year ago

What if you could build an AI World like this in just 5 minutes? ⚡️🌎 Our intern built this Roblox Castle Scene in under an hour using NeuralAI, starting with a map template and generating props, food, trees, a character, and even an animal to bring it to life. The result? A fully AI-enhanced scene full of charm, detail, and creativity. But here's the real shift: That took about an hour using $NEURAL assets. With World Engine, you'll soon be able to create entire AI-powered worlds like this in just 5 minutes using natural language prompts. No complex tools. No dev skills. Just ideas brought to life instantly. World Engine is coming. Get ready.

What if you could build an AI World like this in just 5 minutes? ⚡️🌎 Our intern built this Roblox Castle Scene in under an hour using NeuralAI, starting with a map template and generating props, food, trees, a character, and even an animal to bring it to life. The result? A fully AI-enhanced scene full of charm, detail, and creativity. But here's the real shift: That took about an hour using $NEURAL assets. With World Engine, you'll soon be able to create entire AI-powered worlds like this in just 5 minutes using natural language prompts. No complex tools. No dev skills. Just ideas brought to life instantly. World Engine is coming. Get ready.

NeuralAI

55,977 views • 1 year ago

In our latest episode of Tech Talks, we explore the future of agentic game creation at Roblox. Discover how Roblox Assistant is evolving beyond a prompt tool into an AI-native system that can plan, execute, and verify complex game development tasks alongside creators.

In our latest episode of Tech Talks, we explore the future of agentic game creation at Roblox. Discover how Roblox Assistant is evolving beyond a prompt tool into an AI-native system that can plan, execute, and verify complex game development tasks alongside creators.

Roblox

86,973 views • 3 months ago

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

AK

305,663 views • 3 years ago

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.

AK

62,768 views • 3 years ago