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.

These are not 3D reconstructions but 3D-native generation! Check out our new work, GAE, to generate videos and geometry simultaneously! Code and models are already released!

Yuan Liu

2,108 subscribers

36,355 views • 6 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

3 Comments

Jin Cao5 days ago

Very cool!!!

Badrinath Singhal5 days ago

This is so cool!

X46 days ago

You’re the right person. I was just posting and if you leave X for a few seconds to read a paper and come back it blows off your post into nirvana @nikitabier However, the same information-density gain from existing data polarization in images adds to 3D and spatial resolution, would also increase the GAE quality. Would love to hear what you think about this ICLR Awarded paper:

Related Videos

We are thrilled to announce a major upgrade to our open-source 3D generation model, introducing two groundbreaking new versions: 3D 2.0 MV (Multi-View Generation) and 3D 2.0 Mini! 3D 2.0 MV : 3D 2.0Mini:

We are thrilled to announce a major upgrade to our open-source 3D generation model, introducing two groundbreaking new versions: 3D 2.0 MV (Multi-View Generation) and 3D 2.0 Mini! 3D 2.0 MV : 3D 2.0Mini:

Tencent HY

134,410 views • 1 year ago

Tencent ARC releases GAE: a geometry-native latent space for 3D-consistent world generation GAE compresses 3,072-channel geometry features into a compact 128-channel latent that decodes into RGB, depth, camera trajectories, and point clouds from the same generated state. It halves camera-trajectory error and cuts FVD by up to 23% on standard benchmarks.

Tencent ARC releases GAE: a geometry-native latent space for 3D-consistent world generation GAE compresses 3,072-channel geometry features into a compact 128-channel latent that decodes into RGB, depth, camera trajectories, and point clouds from the same generated state. It halves camera-trajectory error and cuts FVD by up to 23% on standard benchmarks.

DailyPapers

25,488 views • 5 days ago

Today we presented our work on Action Recognition with 3D pose and tracking at #CVPR. We also released our code, models, and dataset of 1.5 million human trajectories. Code: Project Page:

Today we presented our work on Action Recognition with 3D pose and tracking at #CVPR. We also released our code, models, and dataset of 1.5 million human trajectories. Code: Project Page:

Jathushan Rajasegaran

132,016 views • 3 years ago

We just released HaMeR, our latest work for Hand Mesh Recovery! We reconstruct hands in 3D from a single image with big improvements in accuracy and robustness. Code and models are available. Also colab and Hugging Face demo!

We just released HaMeR, our latest work for Hand Mesh Recovery! We reconstruct hands in 3D from a single image with big improvements in accuracy and robustness. Code and models are available. Also colab and Hugging Face demo!

Georgios Pavlakos

38,336 views • 2 years ago

Today we are sharing three new research papers, each exploring a new way to generate 3D content by leveraging large-scale generative models and 2D priors. These projects were led by our incredible interns Hao Zhang @BDuisterhof @DrTunnels [1/4]

Today we are sharing three new research papers, each exploring a new way to generate 3D content by leveraging large-scale generative models and 2D priors. These projects were led by our incredible interns Hao Zhang @BDuisterhof @DrTunnels [1/4]

World Labs

122,868 views • 3 months ago

Built an MCP tool to generate 3D models and use them in ThreeJS or any app seamlessly. Check it out 🙏

Built an MCP tool to generate 3D models and use them in ThreeJS or any app seamlessly. Check it out 🙏

Visionary x AI

152,129 views • 1 year ago

Is 3D scene generation much closer to being solved all of a sudden? It has been a few days since the release of OpenAI Sora. We run our COLMAP-Free 3D Gaussian Splatting on the released videos. Our method does not need to pre-process cameras and it seems we can directly just get 3D from the videos. Check out our results here. 🧵👇 (1/n

Is 3D scene generation much closer to being solved all of a sudden? It has been a few days since the release of OpenAI Sora. We run our COLMAP-Free 3D Gaussian Splatting on the released videos. Our method does not need to pre-process cameras and it seems we can directly just get 3D from the videos. Check out our results here. 🧵👇 (1/n

Xiaolong Wang

157,437 views • 2 years ago

🔥 HUGE: Today, we are thrilled to unveil a massive breakthrough in AI and 3D: ✨Introducing Primfusion v0 💫 For the first time ever in 3D, easily convert your 3D meshes, scans, and high-poly models into easy-to-edit, goopy primitives in Womp. Trained solely on geometry principles, never your style. Join the waitlist ➡️ Questions/Concerns? Check out our FAQ ➡️ #womp3d #3dmodeling

🔥 HUGE: Today, we are thrilled to unveil a massive breakthrough in AI and 3D: ✨Introducing Primfusion v0 💫 For the first time ever in 3D, easily convert your 3D meshes, scans, and high-poly models into easy-to-edit, goopy primitives in Womp. Trained solely on geometry principles, never your style. Join the waitlist ➡️ Questions/Concerns? Check out our FAQ ➡️ #womp3d #3dmodeling

Womp

136,303 views • 2 years ago

🔥Excited to share the first released work from our IEI lab! Congrats to AnteaWu 🎉 This work is motivated by the lack of quantitative evaluation for physics alignment in video world models. With tools like MegaSam and CoTracker, we can directly reconstruct dynamic 3D scenes, enabling quantitative evaluation of physical alignment. Both code and data are released — feel free to try it out! It should work, but if it doesn’t, contact AnteaWu directly : )

🔥Excited to share the first released work from our IEI lab! Congrats to AnteaWu 🎉 This work is motivated by the lack of quantitative evaluation for physics alignment in video world models. With tools like MegaSam and CoTracker, we can directly reconstruct dynamic 3D scenes, enabling quantitative evaluation of physical alignment. Both code and data are released — feel free to try it out! It should work, but if it doesn’t, contact AnteaWu directly : )

Xueyan Zou

10,239 views • 4 months ago

Generative art meets 3D - use our new Blender plugin for #stablediffusion to generate textures, videos and more, right inside the tool you already know. Download for free here:

Generative art meets 3D - use our new Blender plugin for #stablediffusion to generate textures, videos and more, right inside the tool you already know. Download for free here:

Stability AI

305,907 views • 3 years ago

⚙️Roblox Integration & Plugin We're working on a two-step Roblox integration. First, users can connect their Roblox account on our web app, generate 3D models, and upload them directly to Roblox. Next, we’ll add a Roblox plugin to generate 3D models within Roblox, already in your account. We'll also integrate our landscape generation into this process. 🖥 Discover the full details in the video!

⚙️Roblox Integration & Plugin We're working on a two-step Roblox integration. First, users can connect their Roblox account on our web app, generate 3D models, and upload them directly to Roblox. Next, we’ll add a Roblox plugin to generate 3D models within Roblox, already in your account. We'll also integrate our landscape generation into this process. 🖥 Discover the full details in the video!

NeuralAI

20,857 views • 1 year ago

3D AI is leveling up! Rodin 3D AI can create stunning, high-quality 3D models from just text or image inputs. And with its latest update, it can even generate 8K HDRI textures to bring your models to life. Check out the link in the comments!

3D AI is leveling up! Rodin 3D AI can create stunning, high-quality 3D models from just text or image inputs. And with its latest update, it can even generate 8K HDRI textures to bring your models to life. Check out the link in the comments!

el.cine

46,061 views • 1 year ago

We are releasing uCO3D! Built to supercharge 3D GenAI and digital-twin models, this evolution of CO3D features more and higher-quality object videos from 1k categories, 3D Gaussian Splats, and streamlined OSS tools. 💻Data&code: 📄Paper:

We are releasing uCO3D! Built to supercharge 3D GenAI and digital-twin models, this evolution of CO3D features more and higher-quality object videos from 1k categories, 3D Gaussian Splats, and streamlined OSS tools. 💻Data&code: 📄Paper:

David Novotny

16,702 views • 1 year ago

DiffusionGemma is out 🔥 it's compute-bound so 4x faster compared to other Gemma-4 models (1k tok/s on H100) 💨 also great on coding, generate and iterate on any code from 3D generation to front-end ⤵️

DiffusionGemma is out 🔥 it's compute-bound so 4x faster compared to other Gemma-4 models (1k tok/s on H100) 💨 also great on coding, generate and iterate on any code from 3D generation to front-end ⤵️

merve

40,717 views • 3 months ago

Meta Horizon Desktop Editor can now AI generate 3D models, textures, and skyboxes, adding to its existing audio and TypeScript AI generation features. Details here:

Meta Horizon Desktop Editor can now AI generate 3D models, textures, and skyboxes, adding to its existing audio and TypeScript AI generation features. Details here:

UploadVR

33,185 views • 1 year ago

I'm excited to share our new work, VistaDream, which generates a 3D Gaussian field from a single-view image. The codes have already been released. Project page: (with interactive demos) Code: Paper:

I'm excited to share our new work, VistaDream, which generates a 3D Gaussian field from a single-view image. The codes have already been released. Project page: (with interactive demos) Code: Paper:

Yuan Liu

79,610 views • 1 year ago

3D Gaussian Splats are cool, but they're static (Part 33). GGHead can generate and render 3D heads at 1K resolution in real-time.

3D Gaussian Splats are cool, but they're static (Part 33). GGHead can generate and render 3D heads at 1K resolution in real-time.

Dreaming Tulpa 🥓👑

104,552 views • 2 years ago

Unity's AI 3D generator just dropped and game devs are already worried 😅 Not because it doesn't work — but because it works just enough to flood Steam with another wave of zero-effort asset slop. Million-poly single meshes. Impossible to rig. Impossible to animate. But visually convincing enough to fool a thumbnail 👀 The real question isn't "can AI make 3D models?" It's "can it make 3D models that are actually usable in a pipeline?" Not yet. Not even close 🔥 #Blender3D #B3D #Unity #GameDev #AIArt #3DModeling #AssetCreation #IndieGameDev

Unity's AI 3D generator just dropped and game devs are already worried 😅 Not because it doesn't work — but because it works just enough to flood Steam with another wave of zero-effort asset slop. Million-poly single meshes. Impossible to rig. Impossible to animate. But visually convincing enough to fool a thumbnail 👀 The real question isn't "can AI make 3D models?" It's "can it make 3D models that are actually usable in a pipeline?" Not yet. Not even close 🔥 #Blender3D #B3D #Unity #GameDev #AIArt #3DModeling #AssetCreation #IndieGameDev

3DxDEV

122,916 views • 5 months ago

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,798 views • 3 years ago

Introducing V-DPM, for 4D reconstruction of in-the-wild videos. We build on top of VGGT, using Dynamic Point Maps for jointly representing 3D and motion. Joint work with: Eldar Insafutdinov , Lai Zihang , and Andrea Vedaldi. Visual Geometry Group (VGG). Check out the demo and code 👇

Introducing V-DPM, for 4D reconstruction of in-the-wild videos. We build on top of VGGT, using Dynamic Point Maps for jointly representing 3D and motion. Joint work with: Eldar Insafutdinov , Lai Zihang , and Andrea Vedaldi. Visual Geometry Group (VGG). Check out the demo and code 👇

Edgar Sucar

25,818 views • 8 months ago