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.
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)
| Date | Stars |
|---|---|
| 2026-07-24 | 857 |
| 2026-07-25 | 857 |
| 2026-07-28 | 857 |
| 2026-07-30 | 857 |
| 2026-08-07 | 860 |
| 2026-08-15 | 862 |
| 2026-08-19 | 861 |
| 2026-08-28 | 860 |
| 2026-08-31 | 859 |
| 2026-09-03 | 860 |
| 2026-09-06 | 861 |
| 2026-09-08 | 862 |
| 2026-09-10 | 863 |
| 2026-09-11 | 864 |
| 2026-09-20 | 864 |
Today
— stars today
This week
— stars this week
This month
+3 stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <p align="center"> <img src="img/logo.png" width="200px"> </p> [](https://arxiv.org/abs/2411.14384) [](https://zhuanlan.zhihu.com/p/1962623398749372601) [](https://caiyuanhao1998.github.io/project/DiffusionGS/) [](https://huggingface.co/datasets/CaiYuanhao/DiffusionGS) [](https://x.com/janusch_patas/status/1859867424859856997?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Etweet) <h3>Baking Gaussian Splatting into Diffusion Denoiser for Fast and <br> Scalable Single-stage Image-to-3D Generation and Reconstruction</h3> </div> <p align="center"> <img src="img/abo.gif" width="24%" alt="abo"> <img src="img/gso.gif" width="24%" alt="gso"> <img src="img/real_img.gif" width="24%" alt="real_img"> <img src="img/wild.gif" width="24%" alt="wild"> </p> <p align="center"> <img src="img/sd_2.gif" width="24%" alt="sd_2"> <img src="img/sd_1.gif" width="24%" alt="sd_1"> <img src="img/flux_1.gif" width="24%" alt="flux_1"> <img src="img/green_man.gif" width="24%" alt="green_man"> </p> <p align="center"> <img src="img/plaza.gif" width="50%" alt="plaza"> <img src="img/town.gif" width="48%" alt="town"> </p> <p align="center"> <img src="img/cliff.gif" width="49.5%" alt="cliff"> <img src="img/art_gallery.gif" width="48.5%" alt="art_gallery"> </p> ### Introduction This is an implementation of our work "Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction ". The code and checkpoints here is a **re-implementation** and **re-training** and **differs** from the original version developed at Adobe. Our DiffusionGS is single-stage and does not rely on 2D multi-view diffusion model. DiffusionGS can be applied to single-view 3D object generation with mesh exportation and scene reconstruction without using depth estimator in ~6 seconds. If you find our repo useful, please give it a star ⭐ and consider citing our paper. Thank you :)  ### News - **2025.11.20 :** Added mesh exportation code. Feel free to have a try. 💫 - **2025.10.23 :** Add mesh exportion example. Code of this part will also will be released. 🤗 - **2025.10.17 :** Add visual comparisons between Hunyuan-v2.5 and our open-source model. Our method is over **7.5x** Hunyuan-v2.5 model. 🚀 - **2025.10.10 :** Code and models have been released. Feel free to check and use them. 💫 - **2024.11.22 :** Our [project page](https://caiyuanhao1998.github.io/project/DiffusionGS/) has been built up. Feel free to check the video and interactive generation results on the project page. - **2024.11.21 :** We upload the prompt image and our generation results to our [hugging face dataset](https://huggingface.co/datasets/CaiYuanhao/DiffusionGS). Feel free to download and make a comparison with your method. 🤗 - **2024.11.20 :** Our paper is on [arxiv](https://arxiv.org/abs/2411.14384) now. 🚀 ### Comparison with State-of-the-Art Methods <details close> <summary><b>Quantitative Comparison in the Paper</b></summary>  </details> <details close> <summary><b>Qualitative Comparison in the paper</b></summary>  </details> <details open> <summary><b>Qualitative Comparison between Hunyuan-v2.5 and Our Open-source Version Model</b></summary> `Note:` The first row is the prompt image. The second row is Hunyuan-v2.5. The third row is our open-source model. Our model only takes 24s for inference, while Hunyuan-v2.5 takes about 180s. Our model is **7.5x** faster. As for the training cost, our open-source model only takes 16-32 GPUs to train and can be applied on scene-level generation, while Hunyu
Excerpt of 11,351 characters
Read on GitHub
Yuanhao Cai · Johns Hopkins University <- Tsinghua · United States
59
3
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:acfa38734c61ecf2, topic:text-to-3d, desc:3d generation, readme:3d generation
matched fp:acfa38734c61ecf2, topic:diffusion-models, readme:diffusion model