正在加载视频...

视频加载失败

返回首页

Today, we released Lyra 2.0, a framework for generating persistent, explorable 3D worlds at scale, from NVIDIA Research. Generating large-scale, complex environments is difficult for AI models. Current models often “forget” what spaces look like and lose track of movement over time, causing objects to shift, blur, or appear...

NVIDIAAIDev's profile picture

NVIDIA AI Developer

111,286 subscribers

433,343 次观看 • 1 个月前 •via X (Twitter)

教育科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Generating 3D Worlds from a Single Image AI can now turn any photo into a 3D world. World Labs AI creates spaces with an understanding of what it’s building, making it possible to add physics and place new objects inside. Explore here (World Labs demos): marble.worldlabs .ai
0:18

Generating 3D Worlds from a Single Image AI can now turn any photo into a 3D world. World Labs AI creates spaces with an understanding of what it’s building, making it possible to add physics and place new objects inside. Explore here (World Labs demos): marble.worldlabs .ai

Leon

89,924 次观看 • 8 个月前

Turning mobile photos into robot-ready 3D worlds just got easier. 🤖 With NVIDIA Omniverse NuRec, developers can reconstruct lifelike environments for robotics simulation using a smartphone. Learn how ➡️
0:10

Turning mobile photos into robot-ready 3D worlds just got easier. 🤖 With NVIDIA Omniverse NuRec, developers can reconstruct lifelike environments for robotics simulation using a smartphone. Learn how ➡️

NVIDIA Omniverse

20,122 次观看 • 7 个月前

Meta just dropped a new paper. "A Recipe for Generating 3D Worlds From a Single Image" Turn a single image into a high-quality 3D world ready for VR. 10 wild examples:
0:16

Meta just dropped a new paper. "A Recipe for Generating 3D Worlds From a Single Image" Turn a single image into a high-quality 3D world ready for VR. 10 wild examples:

Angry Tom

214,383 次观看 • 1 年前

The concept of creating an exact digital replica of the physical world has always fascinated me: environments that look and behave exactly like our everyday reality, precisely captured in the digital domain. This is the essence of 𝐖𝐨𝐫𝐥𝐝 𝐌𝐨𝐝𝐞𝐥𝐬, simulated realities indistinguishable from our own. Generating these models is the core mission behind what we are building at SpAItial AI. True World Models must capture both photorealistic appearance and underlying physics, spatially-consistent across the environment. For static scenes, current models already deliver impressive results, unlocking downstream applications from gaming to 3D design. However, the true frontier lies in modeling dynamics, which will enable the training of AI agents whose learned behaviors can bridge the sim-to-real gap, thus unlocking countless real-world applications.
0:18

The concept of creating an exact digital replica of the physical world has always fascinated me: environments that look and behave exactly like our everyday reality, precisely captured in the digital domain. This is the essence of 𝐖𝐨𝐫𝐥𝐝 𝐌𝐨𝐝𝐞𝐥𝐬, simulated realities indistinguishable from our own. Generating these models is the core mission behind what we are building at SpAItial AI. True World Models must capture both photorealistic appearance and underlying physics, spatially-consistent across the environment. For static scenes, current models already deliver impressive results, unlocking downstream applications from gaming to 3D design. However, the true frontier lies in modeling dynamics, which will enable the training of AI agents whose learned behaviors can bridge the sim-to-real gap, thus unlocking countless real-world applications.

Matthias Niessner

21,565 次观看 • 3 个月前

Today, we’re introducing Meta’s latest 3D foundation model, AssetGen 2.0, which was designed to create high-quality 3D assets from text and image prompts. AssetGen 2.0 consists of two models developed within Meta: one to generate 3D meshes and another to generate textures. Read More:
0:17

Today, we’re introducing Meta’s latest 3D foundation model, AssetGen 2.0, which was designed to create high-quality 3D assets from text and image prompts. AssetGen 2.0 consists of two models developed within Meta: one to generate 3D meshes and another to generate textures. Read More:

Jake Steinerman 🌎

92,257 次观看 • 1 年前

.Tencent Hy HY-World 2.0 has landed,fully OPEN SOURCE ! We kept hearing the same thing: world models look great, but you can't use the output. So we made one you can, real 3D assets you can edit, rearrange, and ship into production. Prompt to engine-ready 3D. For real this time： ✨Directly outputs editable, production-ready 3D assets ✨Seamlessly plugs into existing game pipelines ✨Multimodal input: text, image, videos 🪄Character mode: freely explore streets, buildings, and open worlds with realistic physics, collisions, and no time limits 🔗GitHub:
0:11

.Tencent Hy HY-World 2.0 has landed,fully OPEN SOURCE ! We kept hearing the same thing: world models look great, but you can't use the output. So we made one you can, real 3D assets you can edit, rearrange, and ship into production. Prompt to engine-ready 3D. For real this time： ✨Directly outputs editable, production-ready 3D assets ✨Seamlessly plugs into existing game pipelines ✨Multimodal input: text, image, videos 🪄Character mode: freely explore streets, buildings, and open worlds with realistic physics, collisions, and no time limits 🔗GitHub:

Tencent AI

116,403 次观看 • 1 个月前

CSM 3D AI: New image-to-3D AI program AI is reshaping the future of 3D design. This amazing tool transforms still images into 3D models, and the best part? You can animate them effortlessly using AI. Link in comment!
0:13

CSM 3D AI: New image-to-3D AI program AI is reshaping the future of 3D design. This amazing tool transforms still images into 3D models, and the best part? You can animate them effortlessly using AI. Link in comment!

el.cine

54,393 次观看 • 1 年前

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.
0:18

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,017 次观看 • 1 年前

With Hunyuan3D World Model 1.0 now released and open-sourced, we're excited to showcase the technical highlights behind this impressive innovation: ✅360° Panoramic Generation: Creates complete, immersive “world scenes”, far beyond localized views. ✅Explorable 3D Scene Generation: Generates diverse, spatially consistent 3D worlds from text/image for truly immersive exploration. ✅Interactive/Editable: Achieves separation of foreground objects, background terrain, ground, and sky, for seamless secondary editing. ✅Exportable Mesh: Generated scenes can be exported as 3D meshes for direct import into mainstream game engines and modeling software. ✅Industry-Leading SOTA Evaluation: Surpasses state-of-the-art open-source models in generation quality. As the industry's first open-source model for physical simulation and explorable world generation, Hunyuan3D World Model 1.0 aims to foster a collaborative community ecosystem with developers and enthusiasts. ✨ Try it now: 🤗 Hugging Face:
0:07

With Hunyuan3D World Model 1.0 now released and open-sourced, we're excited to showcase the technical highlights behind this impressive innovation: ✅360° Panoramic Generation: Creates complete, immersive “world scenes”, far beyond localized views. ✅Explorable 3D Scene Generation: Generates diverse, spatially consistent 3D worlds from text/image for truly immersive exploration. ✅Interactive/Editable: Achieves separation of foreground objects, background terrain, ground, and sky, for seamless secondary editing. ✅Exportable Mesh: Generated scenes can be exported as 3D meshes for direct import into mainstream game engines and modeling software. ✅Industry-Leading SOTA Evaluation: Surpasses state-of-the-art open-source models in generation quality. As the industry's first open-source model for physical simulation and explorable world generation, Hunyuan3D World Model 1.0 aims to foster a collaborative community ecosystem with developers and enthusiasts. ✨ Try it now: 🤗 Hugging Face:

Tencent Hy

23,150 次观看 • 10 个月前

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”
0:18

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Bilawal Sidhu

92,760 次观看 • 2 年前

Experimenting with image-to-world: creating consistent 3D environments from a single photo. As someone who studied architecture, this feels like a glimpse into the future of spatial creation and I’m excited to see where World Labs takes it.
0:17

Experimenting with image-to-world: creating consistent 3D environments from a single photo. As someone who studied architecture, this feels like a glimpse into the future of spatial creation and I’m excited to see where World Labs takes it.

Ian Curtis

61,148 次观看 • 9 个月前

Trending: Step1X-3D for generating high-fidelity 3D assets with versatile textures! Apache-2.0 with exceptional results in terms of geometry and texture mapping🔥🔥
0:16

Trending: Step1X-3D for generating high-fidelity 3D assets with versatile textures! Apache-2.0 with exceptional results in terms of geometry and texture mapping🔥🔥

Gradio

36,405 次观看 • 1 年前

Harness the power of generative AI without just prompting and hoping for the best. From Unbound Slop to Tripo to Unreal Engine, we love this workflow for generating 3D models.
0:17

Harness the power of generative AI without just prompting and hoping for the best. From Unbound Slop to Tripo to Unreal Engine, we love this workflow for generating 3D models.

Unbound

26,381 次观看 • 1 个月前

As announced in partnership with NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on NVIDIA RTX AI PCs, SPAR3D enables real-time editing and complete structure generation of 3D objects from a single image in under a second. You can download the weights on Hugging Face and code on GitHub, or access the model through the Stability AI API. Learn more here: (1/3)
0:13

As announced in partnership with NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on NVIDIA RTX AI PCs, SPAR3D enables real-time editing and complete structure generation of 3D objects from a single image in under a second. You can download the weights on Hugging Face and code on GitHub, or access the model through the Stability AI API. Learn more here: (1/3)

Stability AI

181,402 次观看 • 1 年前

With 3M+ downloads and counting, NVIDIA Cosmos is redefining physical AI. Announced at #CORL25, new Cosmos updates are allowing developers to generate diverse data for accelerating training robot models at scale. 👏 Cosmos Predict 2.5 will combine three models into one powerful model—reducing complexity, powering up to 30s video generation, and enabling multi-view simulations. 👏 Cosmos Transfer 2.5 will be 3.5x smaller yet faster and sharper—generating photorealistic synthetic data from 3D scenes or spatial inputs. 🔗
0:15

With 3M+ downloads and counting, NVIDIA Cosmos is redefining physical AI. Announced at #CORL25, new Cosmos updates are allowing developers to generate diverse data for accelerating training robot models at scale. 👏 Cosmos Predict 2.5 will combine three models into one powerful model—reducing complexity, powering up to 30s video generation, and enabling multi-view simulations. 👏 Cosmos Transfer 2.5 will be 3.5x smaller yet faster and sharper—generating photorealistic synthetic data from 3D scenes or spatial inputs. 🔗

NVIDIA AI

40,267 次观看 • 8 个月前

Learn how to create film-quality 3D environments with Intro to Worldbuilding and Environments, a new workshop from DoubleJump Academy. The workshop covers various techniques for layout, procedural modeling for environments, lighting, and more: #sponsored #ad
0:10

Learn how to create film-quality 3D environments with Intro to Worldbuilding and Environments, a new workshop from DoubleJump Academy. The workshop covers various techniques for layout, procedural modeling for environments, lighting, and more: #sponsored #ad

80 LEVEL

18,910 次观看 • 4 个月前

NVIDIA finally released Neuralangelo's source code! The model can turn videos from any device into detailed 3D structures, fully replicating buildings, sculptures, or other real aworld objects or spaces virtually. Here's how it works: A model utilizes a 2D video with multiple angles of an object or scene. I selects frames from different viewpoints to understand depth, size, and shape. The AI creates an initial 3D representation, similar to a sculptor shaping a subject. The render is optimized to enhance details, like a sculptor refining texture. The outcome is a 3D object or scene suitable for virtual reality, digital twins, or robotics.
0:13

NVIDIA finally released Neuralangelo's source code! The model can turn videos from any device into detailed 3D structures, fully replicating buildings, sculptures, or other real aworld objects or spaces virtually. Here's how it works: A model utilizes a 2D video with multiple angles of an object or scene. I selects frames from different viewpoints to understand depth, size, and shape. The AI creates an initial 3D representation, similar to a sculptor shaping a subject. The render is optimized to enhance details, like a sculptor refining texture. The outcome is a 3D object or scene suitable for virtual reality, digital twins, or robotics.

Lior Alexander

478,001 次观看 • 2 年前

Hunyuan 3D-2.1 turns any flat image into studio-quality 3D models. And you can do it on this Hugging Face space for free.
0:11

Hunyuan 3D-2.1 turns any flat image into studio-quality 3D models. And you can do it on this Hugging Face space for free.

Rohan Paul

222,392 次观看 • 9 个月前

2023 was the year of AI avatars 2024 was the year of AI photos 2025 was the year of AI videos And I think it's becoming clear now that 2026 will be the year of AI world models Fully interactive explorable 3d worlds generated from one or multiple 2d images or a prompt In turn these 2d images can then be generated by AI too So soon you can generate fully explorable virtual 3d worlds based on your own imagination Next will be figuring out how to make those worlds interactive This is World Labs (unaffiliated, but I like it) As always a lot of big AI model companies are now working on the same thing: 3d world models, only World Labs has a real properly working demo (for now) Very exciting time again!
0:18

2023 was the year of AI avatars 2024 was the year of AI photos 2025 was the year of AI videos And I think it's becoming clear now that 2026 will be the year of AI world models Fully interactive explorable 3d worlds generated from one or multiple 2d images or a prompt In turn these 2d images can then be generated by AI too So soon you can generate fully explorable virtual 3d worlds based on your own imagination Next will be figuring out how to make those worlds interactive This is World Labs (unaffiliated, but I like it) As always a lot of big AI model companies are now working on the same thing: 3d world models, only World Labs has a real properly working demo (for now) Very exciting time again!

@levelsio

583,999 次观看 • 8 个月前

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.
0:12

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,801 次观看 • 1 年前