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 2025 Highlight] VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step
| Date | Stars |
|---|---|
| 2026-07-24 | 353 |
| 2026-07-25 | 353 |
| 2026-07-28 | 353 |
| 2026-07-30 | 353 |
| 2026-08-06 | 353 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center">
<h1 align="center">VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step</h1>
<p align="center">
<a href="https://hanyang-21.github.io/">Hanyang Wang</a><sup>*</sup>,
<a href="https://liuff19.github.io/">Fangfu Liu</a><sup>*</sup>,
<a href="https://github.com/hanyang-21/VideoScene">Jiawei Chi</a>,
<a href="https://duanyueqi.github.io/">Yueqi Duan</a>
<br>
<sup>*</sup>Equal Contribution.
<br>
Tsinghua University
</p>
<h3 align="center">CVPR 2025 Hightlight 🔥</h3>
<h5 align="center">
[](https://arxiv.org/abs/2504.01956)
[](https://hanyang-21.github.io/VideoScene)
<a><img src='https://img.shields.io/badge/License-MIT-blue'></a>
<a href='https://mp.weixin.qq.com/s/u6OUo5mHKPG6I3yYJPMC8Q'><img src='https://img.shields.io/badge/%E5%BE%AE%E4%BF%A1-%E4%B8%AD%E6%96%87%E4%BB%8B%E7%BB%8D-green'></a>
</h5>
<!-- <h3 align="center"><a href="https://arxiv.org/abs/">Paper</a> | <a href="">Project Page</a> | <a href="">Pretrained Models</a> </h3> -->
<!-- <div align="center">
<a href="https://news.ycombinator.com/item?id=41222655">
<img
alt="Featured on Hacker News"
src="https://hackerbadge.vercel.app/api?id=41222655&type=dark"
/>
</a>
</div> -->
</p>
<div align="center">
VideoScene is a one-step video diffusion model that bridges the gap from video to 3D.
</div>
</br>
https://github.com/user-attachments/assets/dca733b1-b78f-49ac-ae47-5d1b1e8a689b
Building on [ReconX](https://github.com/liuff19/ReconX), VideoScene has achieved a turbo-version advancement.
## Installation
To get started, clone this project, create a conda virtual environment using Python 3.10+, and install the requirements:
1. Clone VideoScene.
```bash
git clone https://github.com/hanyang-21/VideoScene
cd VideoScene
```
2. Create the environment, here we show an example using conda.
```bash
conda create -y -n videoscene python=3.10
conda activate videoscene
pip install torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 --index-url https://download.pytorch.org/whl/cu118
pip install -r requirements.txt
```
3. Optional, compile the cuda kernels for RoPE (as in CroCo v2).
```bash
# NoPoSplat relies on RoPE positional embeddings for which you can compile some cuda kernels for faster runtime.
cd src/model/encoder/backbone/croco/curope/
python setup.py build_ext --inplace
cd ../../../../../..
```
## Acquiring Datasets
### RealEstate10K and ACID
Our VideoScene uses the same training datasets as pixelSplat. Below we quote pixelSplat's [detailed instructions](https://github.com/dcharatan/pixelsplat?tab=readme-ov-file#acquiring-datasets) on getting datasets.
> pixelSplat was trained using versions of the RealEstate10k and ACID datasets that were split into ~100 MB chunks for use on server cluster file systems. Small subsets of the Real Estate 10k and ACID datasets in this format can be found [here](https://drive.google.com/drive/folders/1joiezNCyQK2BvWMnfwHJpm2V77c7iYGe?usp=sharing). To use them, simply unzip them into a newly created `datasets` folder in the project root directory.
> If you would like to convert downloaded versions of the Real Estate 10k and ACID datasets to our format, you can use the [scripts here](https://github.com/dcharatan/real_estate_10k_tools). Reach out to us (pixelSplat) if you want the full versions of our processed datasets, which are about 500 GB and 160 GB for Real Estate 10k and ACID respectively.
## Downloading checkpoints
* download our [pretrained weights](https://wisemodel.cn/models/hanyang/VideoScene/file) (`VideoScene/checkpoints/model.safetensors` and `VideoScene/checkpoints/prompt_embeds.pt`), and save them to `checkpoints`.
* for customized image inputs, get the NoPoSplat [pretrained models](https://huggingface.co/botaoye/NoPoSplat/resolve/main/mixRe10kDl3dExcerpt of 6,135 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2eefe95729dc3708, topic:3d-reconstruction
matched fp:2eefe95729dc3708, topic:video-generation