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.
[CVPR 2024] GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models
| Date | Stars |
|---|---|
| 2026-07-31 | 828 |
| 2026-08-11 | 829 |
| 2026-08-18 | 830 |
| 2026-08-21 | 829 |
| 2026-08-26 | 831 |
| 2026-08-29 | 830 |
| 2026-09-03 | 829 |
| 2026-09-14 | 830 |
| 2026-09-15 | 830 |
| 2026-09-16 | 831 |
| 2026-09-28 | 832 |
| 2026-09-30 | 833 |
| 2026-10-18 | 834 |
| 2026-10-19 | 834 |
| 2026-10-20 | 833 |
| 2026-10-22 | 833 |
| 2026-10-23 | 832 |
| 2026-11-04 | 832 |
Today
— stars today
This week
— stars this week
This month
-1 stars this month
Momentum
0.0
growth rate 0.00%/day
 # GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models (CVPR 2024) ### [Project Page](https://taoranyi.com/gaussiandreamer/) | [arxiv Paper](https://arxiv.org/abs/2310.08529) [GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models](https://taoranyi.com/gaussiandreamer/) [Taoran Yi](https://github.com/taoranyi)<sup>1</sup>, [Jiemin Fang](https://jaminfong.cn/)<sup>2‡</sup>, [Junjie Wang](https://scholar.google.com/citations?view_op=list_works&hl=zh-CN&user=9Nw_mKAAAAAJ)<sup>2</sup>, [Guanjun Wu](https://guanjunwu.github.io/)<sup>3</sup>, [Lingxi Xie](http://lingxixie.com/)<sup>2</sup>, </br>[Xiaopeng Zhang](https://scholar.google.com/citations?user=Ud6aBAcAAAAJ&hl=zh-CN)<sup>2</sup>,[Wenyu Liu](http://eic.hust.edu.cn/professor/liuwenyu/)<sup>1</sup>, [Qi Tian](https://www.qitian1987.com/)<sup>2</sup> , [Xinggang Wang](https://xwcv.github.io/)<sup>1‡✉</sup> <sup>1</sup>School of EIC, HUST  <sup>2</sup>Huawei Inc.   <sup>3</sup>School of CS, HUST   <sup>‡</sup>Project lead. <sup>✉</sup>Corresponding author.  In recent times, the generation of 3D assets from text prompts has shown impressive results. Both 2D and 3D diffusion models can help generate decent 3D objects based on prompts. 3D diffusion models have good 3D consistency, but their quality and generalization are limited as trainable 3D data is expensive and hard to obtain. 2D diffusion models enjoy strong abilities of generalization and fine generation, but 3D consistency is hard to guarantee. This paper attempts to bridge the power from the two types of diffusion models via the recent explicit and efficient 3D Gaussian splatting representation. A fast 3D object generation framework, named as GaussianDreamer, is proposed, where the 3D diffusion model provides priors for initialization and the 2D diffusion model enriches the geometry and appearance. Operations of noisy point growing and color perturbation are introduced to enhance the initialized Gaussians. Our GaussianDreamer can generate a high-quality 3D instance or 3D avatar within 15 minutes on one GPU, much faster than previous methods, while the generated instances can be directly rendered in real time.  ## 🦾 Updates - 1/13/2025: We have released the code of [GaussianDreamerPro](https://taoranyi.com/gaussiandreamerpro/). Have a try! - 6/26/2024: We have released [GaussianDreamerPro](https://taoranyi.com/gaussiandreamerpro/) with highly enhanced quality which can be seamlessly integrated into animation/simulation pipelines🚀. - 5/14/2024: We update the results of our method on [T<sup>3</sup>Bench](https://t3bench.com/), refer to [arxiv paper](https://arxiv.org/abs/2310.08529v3) for details. - 3/8/2024: We also provide a [GaussianDreamer extension for threestudio](https://github.com/cxh0519/threestudio-gaussiandreamer). Thanks for the contribution of [Xinhua Cheng](https://github.com/cxh0519/). - 2/27/2024: Accepted by CVPR 2024. - 12/6/2023: Update [arxiv paper](https://arxiv.org/abs/2310.08529). - 11/27/2023: Update colab and huggingface demo. - 11/27/2023: Release the results initialized using point clouds with ground. And now we support importing the generated 3D assets into the Unity game engine with the help of [UnityGaussianSplatting](https://github.com/aras-p/UnityGaussianSplatting). See the [Project Page](https://taoranyi.com/gaussiandreamer/) for details. - 10/24/2023: Release the results initialized using SMPL. See the [Project Page](https://taoranyi.com/gaussiandreamer/) for details. - 10/21/2023: Fixed some installation issues, thanks to Sikuang Li, [Tawfik Boujeh](), and [ashawkey](https://github.com/ashawkey/diff-gaussian-rasterization). You can view the detailed information in branch diff. - 10/16/2023: The rough code has been released, and there may still be some issues. Please feel free to raise i
Excerpt of 8,251 characters
Read on GitHub
39
Geralt_of_Rivia · Huazhong University of Science and Technology · China
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4f54f039972d38d2, topic:computer-vision, topic:nerf, topic:gaussian-splatting
matched fp:4f54f039972d38d2, topic:text-to-3d, desc:text-to-3d, readme:text-to-3d