正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

🚀Create complex, modular 3D assets and scenes.🚀 Introducing #MoCA (Mixture-of-Components Attention), a new sparse attention method for compositional 3D generation. It scales to many components. paper: code:

Tengfei Wang

3,688 subscribers

27,212 次观看 • 10 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 条评论

Prakhar Kaushik 的头像

Prakhar Kaushik10 个月前

Great visuals, but impossible to validate scientifically. This is the ~10th paper from this team on the same closed-source dataset. Without public splits, we can't even confirm the eval data isn't in training. The real 'novelty' here seems to be the private dataset, not the model

W. S. Waldo 的头像

W. S. Waldo10 个月前

There are already several tools out there for generating meshes from 3D parts and they all produce similar results. What's needed isn't another approach to part generation, but an improvement in the fidelity and accuracy of the parts generated.

huh ok good point 的头像

huh ok good point10 个月前

This rocks :O thanks so much for sharing!

Himanshu Kumar 的头像

Himanshu Kumar10 个月前

Oh wow, that's some serious stuff, Tengfei! This MoCA sounds quite promising, no?

Mitleidstour 的头像

Mitleidstour10 个月前

😱

Rich kids of base 的头像

Rich kids of base10 个月前

Nice

Yuval Karmi 的头像

Yuval Karmi10 个月前

that is cool !!

Cris Lenta 的头像

Cris Lenta10 个月前

love this!

Jonathan Korstad 的头像

Jonathan Korstad10 个月前

🔥

相关视频

🚀 Introducing #DreamCraft3D, our breakthrough hierarchical technique for 3D content generation. Leading the way in AIGC, we're redefining 3D generation: Project page: Paper: Code:

🚀 Introducing #DreamCraft3D, our breakthrough hierarchical technique for 3D content generation. Leading the way in AIGC, we're redefining 3D generation: Project page: Paper: Code:

DeepSeek

16,667 次观看 • 3 年前

How can we generate and evaluate physically grounded articulated 3D assets? 🚀 Introducing ARTISAN: a multi-agent generation pipeline and a comprehensive benchmark 🔗 Project: 💻 Code and datasets:

How can we generate and evaluate physically grounded articulated 3D assets? 🚀 Introducing ARTISAN: a multi-agent generation pipeline and a comprehensive benchmark 🔗 Project: 💻 Code and datasets:

Chuanxia Zheng

19,215 次观看 • 7 天前

New paper release: Learning Agile Perceptive Traversal of Sparse 3D Structures for Humanoids Paper Videos We study how to do learning and sim2real for 3d traversal, such as monkey bars and overhanging obstacles.

New paper release: Learning Agile Perceptive Traversal of Sparse 3D Structures for Humanoids Paper Videos We study how to do learning and sim2real for 3d traversal, such as monkey bars and overhanging obstacles.

C. Zhang

83,345 次观看 • 1 个月前

Sharing our new work: UniForge3D generates detailed 3D meshes from sparse-view inputs with high fidelity! The code has been released and welcome to try it! Paper: Project Page: Code:

Sharing our new work: UniForge3D generates detailed 3D meshes from sparse-view inputs with high fidelity! The code has been released and welcome to try it! Paper: Project Page: Code:

Yuan Liu

28,328 次观看 • 4 天前

Been pushing Rive's new 3D and shader support to see what's possible 🚀 Using AI + scripting, I was able to: • Import 3D models • Generate cameras and lights • Create custom shaders (wireframe, AO, sketch, toon) • Build materials • Project animated textures onto 3D geometry • Place 2D components directly in 3D space It's pretty wild to see how quickly Rive is evolving into a true all-in-one platform for interactive design.

Been pushing Rive's new 3D and shader support to see what's possible 🚀 Using AI + scripting, I was able to: • Import 3D models • Generate cameras and lights • Create custom shaders (wireframe, AO, sketch, toon) • Build materials • Project animated textures onto 3D geometry • Place 2D components directly in 3D space It's pretty wild to see how quickly Rive is evolving into a true all-in-one platform for interactive design.

Sanu Sagar

18,218 次观看 • 4 个月前

Introducing Components! A big step towards achieving design systems in 3d. ✏️ 🌳Components & Instances 📝Overrides 🔃Component Swapping We are shipping it as a beta for everyone. We would love to know your feedback! Demo: Remix:

Introducing Components! A big step towards achieving design systems in 3d. ✏️ 🌳Components & Instances 📝Overrides 🔃Component Swapping We are shipping it as a beta for everyone. We would love to know your feedback! Demo: Remix:

Spline

161,290 次观看 • 3 年前

#ICCV2025 🤩3D world generation is cool, but it is cooler to play with the worlds using 3D actions 👆💨, and see what happens! — Introducing *WonderPlay*: Now you can create dynamic 3D scenes that respond to your 3D actions from a single image! Web: 🧵1/7

#ICCV2025 🤩3D world generation is cool, but it is cooler to play with the worlds using 3D actions 👆💨, and see what happens! — Introducing WonderPlay: Now you can create dynamic 3D scenes that respond to your 3D actions from a single image! Web: 🧵1/7

Hong-Xing (Koven) Yu

58,065 次观看 • 1 年前

Introducing ShapeR, a method for robust conditional 3D shape generation from casually captured sequences. ShapeR leverages a rectified flow transformer conditioned on per-object multimodal data to turn casual image sequences into full metric scene reconstructions. Project Page: Paper: Links to code and huggingface below ⬇️

Introducing ShapeR, a method for robust conditional 3D shape generation from casually captured sequences. ShapeR leverages a rectified flow transformer conditioned on per-object multimodal data to turn casual image sequences into full metric scene reconstructions. Project Page: Paper: Links to code and huggingface below ⬇️

Yawar Siddiqui

71,078 次观看 • 9 个月前

Community, attention!🚨 We've fully supercharged our website and documentation to offer a superior experience. Our new hubs offer better interfaces, in-depth information for all components, interactive code samples, and much more. ✨ Check it out:

Community, attention!🚨 We've fully supercharged our website and documentation to offer a superior experience. Our new hubs offer better interfaces, in-depth information for all components, interactive code samples, and much more. ✨ Check it out:

Particle Network

160,766 次观看 • 2 年前

Image to 3D, built for detail🤯 Rodin Gen-2.5 helps create high-poly 3D assets with native textures, batch results, and adjustable generation effort. Try it in Hyper3D!

Image to 3D, built for detail🤯 Rodin Gen-2.5 helps create high-poly 3D assets with native textures, batch results, and adjustable generation effort. Try it in Hyper3D!

Hyper3D by Deemos

5,781,061 次观看 • 3 个月前

📣 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

409,091 次观看 • 2 年前

🚀 Chakra UI v3 is here! 🚀 We're thrilled to announce the release of Chakra v3, a complete rewrite to boost performance, speed, and consistency across all components. 🟢 25+ new components 🟢 Improved design tokens 🟢 Component Snippets 🟢 Works in RSC and Next.js

🚀 Chakra UI v3 is here! 🚀 We're thrilled to announce the release of Chakra v3, a complete rewrite to boost performance, speed, and consistency across all components. 🟢 25+ new components 🟢 Improved design tokens 🟢 Component Snippets 🟢 Works in RSC and Next.js

Sage ⚡️

94,123 次观看 • 2 年前

🌟 Create anything in 3D! 🌟 Introducing CAT3D: a new method that generates high-fidelity 3D scenes from any number of real or generated images in one minute, powered by multi-view diffusion models. w/ lovely coauthors Aleksander Holynski, Ben Poole and an amazing team!

🌟 Create anything in 3D! 🌟 Introducing CAT3D: a new method that generates high-fidelity 3D scenes from any number of real or generated images in one minute, powered by multi-view diffusion models. w/ lovely coauthors Aleksander Holynski, Ben Poole and an amazing team!

Ruiqi Gao

153,337 次观看 • 2 年前

The code of GSPN #CVPR2025 is released! We proposed a new sqrt(N) complexity attention mechanism, which enables efficient high resolution image generation. We can generate 8k images with 42x speed up compared to self-attention in StableDiffusionXL! Code: Paper:

The code of GSPN #CVPR2025 is released! We proposed a new sqrt(N) complexity attention mechanism, which enables efficient high resolution image generation. We can generate 8k images with 42x speed up compared to self-attention in StableDiffusionXL! Code: Paper:

Xiaolong Wang

354,887 次观看 • 1 年前

🔥Introducing Open-Sora Plan v1.3! We introduce the🚀Skiparse 3D attention and 🚄WFVAE, significantly reducing the training cost of the model. This video is an alternate ending we created for #BlackMythWukong , generated by our v1.3. Welcome to star!🌟

🔥Introducing Open-Sora Plan v1.3! We introduce the🚀Skiparse 3D attention and 🚄WFVAE, significantly reducing the training cost of the model. This video is an alternate ending we created for #BlackMythWukong , generated by our v1.3. Welcome to star!🌟

Bin Lin

23,939 次观看 • 2 年前

Nvidia presents Edify 3D! The method can generate high-quality 3D assets from text descriptions. It uses a diffusion model to create detailed quad-mesh topologies and high-resolution textures in under 2 minutes.

Nvidia presents Edify 3D! The method can generate high-quality 3D assets from text descriptions. It uses a diffusion model to create detailed quad-mesh topologies and high-resolution textures in under 2 minutes.

Dreaming Tulpa 🥓👑

39,523 次观看 • 1 年前