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.
Segment-Anything + 3D. Let's lift anything to 3D.
| Date | Stars |
|---|---|
| 2026-07-24 | 1633 |
| 2026-07-25 | 1633 |
| 2026-07-28 | 1632 |
| 2026-07-30 | 1632 |
| 2026-08-06 | 1632 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<!-- # Anything-3D -->
🎉🎉🎉Welcome to the Anything-3D GitHub repository!🎉🎉🎉
- 🔥[Technical Report](https://arxiv.org/abs/2304.10261) is out🔥
- 🔥[Open-source Code](https://github.com/Anything-of-anything/Anything-3D/tree/main/AnyObject3D) is out🔥
Here we present a project where we combine [Segment Anything](https://github.com/facebookresearch/segment-anything) with a series of 3D models to create a very interesting demo. This is currently a small project, but we plan to continue improving it and creating more exciting demos.
**Contributions are highly Welcomed!🤝🙌**
- [🤩 Anything-3D-Objects](#-anything-3d-objects)
- [🔥 Anything-3DNovel-View](#-anything-3dnovel-view)
- [🥳 Anything-NeRF](#-anything-nerf)
- [😎 Any-3DFace](#-any-3dface)
- [:cupid: Acknowledgements](#cupid-acknowledgements)
- [Citation](#citation)
## 🤩 Anything-3D-Objects
In this section, we showcase the results of combining [Segment Anything](https://github.com/facebookresearch/segment-anything) with [3DFuse](https://github.com/KU-CVLAB/3DFuse) to segment and reconstruct 3D objects in the wild. Check out the following table for segmentation results and the corresponding 3D object:
| Segmentation | Result|
| :---: | :---:|
| <img src="AnyObject3D/assets/bull_mask.png" width="550"> |  |
| <img src="AnyObject3D/assets/corgi_mask.png" width="550">|  |
## 🔥 Anything-3DNovel-View
In this section, we demonstrate the combination of [Segment Anything](https://github.com/facebookresearch/segment-anything) with [Zero 1-to-3](https://github.com/cvlab-columbia/zero123) to generate novel views of 3D objects. Check out the following images:
## 🥳 Anything-NeRF
In this section, we showcase the integration of [Segment Anything](https://github.com/facebookresearch/segment-anything) with [NeRF](https://github.com/kwea123/nerf_pl) to generate new perspectives of objects set against intricate backgrounds. When an object is positioned in front of a plain, perspective-less background, NeRF typically struggles to reconstruct the scene. However, by eliminating the background, we can enhance NeRF's performance and facilitate more accurate reconstructions of scenes with objects presented in novel views.
| Segmentation-1 |Segmentation-2 | Result|
| :---: | :---: | :---:|
| <img src="AnyNeRF/assets/crop.png" width="400"> | <img src="AnyNeRF/assets/crop2.png" width="400"> |  |
## 😎 Any-3DFace
In this section, we showcase the results of combining [Segment Anything](https://github.com/facebookresearch/segment-anything) with [HRN](https://younglbw.github.io/HRN-homepage/) for accurate and detailed face reconstruction from in-the-wild images. Check out the following table for segmentation results and the corresponding face reconstruction:
| Segmentation | Result|
| :---: | :---:|
| <img src="AnyFace3D/assets/celebrity_selfie/mask_1.jpg" width="2000"> |  |
| <img src="AnyFace3D/assets/celebrity_selfie/mask_2.jpg" width="2000">|  |
| <img src="AnyFace3D/assets/celebrity_selfie/mask_3.jpg" width="2000">|  |
## :cupid: Acknowledgements
We would like to acknowledge the following projects for their valuable contributions:
- [Segment Anything](https://github.com/facebookresearch/segment-anything)
- [Zero 1-to-3](https://github.com/cvlab-columbia/zero123)
- [HRN](https://younglbw.github.io/HRN-homepage/)
- [3DFuse](https://github.com/KU-CVLAB/3DFuse)
## Citation
If you find this project helpful for your research, please consider citing the following BibTeX entry.
```BibTex
@misc{shen2023anything3d,
title={Anything-3D: Towards Single-view Anything Reconstruction in the Wild},
author={Qiuhong Shen and Xingyi Yang and Xinchao Wang},
yearExcerpt of 5,684 characters
Read on GitHub
Xingyi Yang · Hong Kong Polytechnic University @nus @torrvision @UCSD @seu · Hong Kong
27
9
4
3
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:479bca6551aef6f5, topic:computer-vision