Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
🌍 WorldGen - Generate Any 3D Scene in Seconds
| Date | Stars |
|---|---|
| 2026-07-24 | 2031 |
| 2026-07-25 | 2033 |
| 2026-07-28 | 2033 |
| 2026-07-30 | 2033 |
| 2026-08-06 | 2033 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# WorldGen: Generate Any 3D Scene in Seconds <div align="center"> <img src="./assets/logo.png" alt="logo" width="300" style="margin-bottom: 210px;"/> </div> <div align="center"> [](https://worldgen.github.io/) [](https://huggingface.co/LeoXie/WorldGen)  [](https://github.com/ZiYang-xie/WorldGen/stargazers/) </div> > Author 👨💻: [Ziyang Xie](https://ziyangxie.site/) > Contact Email 📧: [[email protected]](mailto:[email protected]) > Feel free to contact me for any questions or collaborations! ## 🌟 Introduction 🌏 **WorldGen** can generate 3D scenes in seconds from text prompts and images. It is a powerful tool for creating 3D environments and scenes for games, simulations, robotics, and virtual reality applications. - **Instant 3D Generation** ⚡️ : Create full 3D scenes from input data in seconds - **360° Free Exploration** 🧭 : WorldGen supports free 360° consistent exploration of the generated 3D scene with loop closure. - **Diverse Scenes Support** 🌈 : WorldGen supports both indoor and outdoor scenes, both realistic and unrealistic scenes in any style. - **Flexible Rendering** 📸 : WorldGen supports rendering at any resolution with any camera setting and trajectory in real-time. Two lines of code to generate a 3D scene in seconds ```python # Use our API to generate a 3D scene worldgen = WorldGen() worldgen.generate_world("<TEXT PROMPT to describe the scene>") ``` ## Text-to-Scene Generation <div align="center"> <img src="https://github.com/ZiYang-xie/WorldGen/blob/demos/assets/text2scene/indoor1.gif" alt="demo" width="400"/> <img src="https://github.com/ZiYang-xie/WorldGen/blob/demos/assets/text2scene/outdoor1.gif" alt="demo" width="400"/> <br> <img src="https://github.com/ZiYang-xie/WorldGen/blob/demos/assets/text2scene/indoor2.gif" alt="demo" width="400"/> <img src="https://github.com/ZiYang-xie/WorldGen/blob/demos/assets/text2scene/outdoor2.gif" alt="demo" width="400"/> </div> ## Image-to-Scene Generation <div align="center"> <img src="https://github.com/ZiYang-xie/WorldGen/blob/demos/assets/img2scene/painting.png" alt="demo" width=300 height=200 /> <img src="https://github.com/ZiYang-xie/WorldGen/blob/demos/assets/img2scene/painting.gif" alt="demo" width=350 height=200/> <br> <img src="https://github.com/ZiYang-xie/WorldGen/blob/demos/assets/img2scene/street.png" alt="demo" width="300" height=200 /> <img src="https://github.com/ZiYang-xie/WorldGen/blob/demos/assets/img2scene/street.gif" alt="demo" width=350 height=200/> </div> --- ## News and TODOs - [x] `04.12.2026` 🔧 **[Improved Sharp]** Rework ml-sharp pipeline: use cubemap depth to align Sharp's per-face gaussians for better global consistency. Reduced from 8+ views to 6 cubemap faces. - [x] `04.11.2026` 🔄 **[Updated Depth]** Replace UniK3D with [DA-2](https://github.com/EnVision-Research/DA-2) for better 360° depth estimation. - [x] `03.17.2026` 🔧 **[Improved Quality]** Improve the GS quality by fixing the project scale issue. Make ml-sharp dependency optional. - [x] `01.10.2026` 🔥 **[New feature]** Add support for ml-sharp (modified to work on 360 images) for better GS generation (Currently in experimental mode) - [x] `05.10.2025` 🤖 Add support for low-vram generation (Only use ~10GB VRAM for generation). - [x] `04.26.2025` 📄 **New** Relase a project page for WorldGen - [x] `04.22.2025` 🏡 Add support for mesh scene generation (Should give better results than splat) - [x] `04.21.2025` 🎉 Opensource the WorldGen codebase - [x] `04.19.2025` 🖼️ Add support for image-to-scene generation - [x] `04.17.2025` 📝 Add support for text-to-scene generation - [ ] Release technical report and video - [ ] Support better
Excerpt of 10,052 characters
Read on GitHub
53
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:e29252f5e636c2e6, topic:3d-reconstruction, readme:depth estimation
matched fp:e29252f5e636c2e6, topic:text-to-3d, readme:3d generation