Guanjun Wu^1*, Taoran Yi^2*, Jiemin Fang³, Lingxi Xie³,
Xiaopeng Zhang³, Wei Wei¹,Wenyu Liu², Qi Tian³ , Xinggang Wang^2✉

¹School of CS, HUST   ²School of EIC, HUST   ³Huawei Inc.  

Our method converges very quickly. And achieves real-time rendering speed.

Colab demo: (Thanks camenduru.)

Please follow the 3D-GS to install the relative packages.

git clone https://github.com/hustvl/4DGaussians
cd 4DGaussians
git submodule update --init --recursive
conda create -n Gaussians4D python=3.7 
conda activate Gaussians4D

pip install -r requirements.txt
pip install -e submodules/depth-diff-gaussian-rasterization
pip install -e submodules/simple-knn

In our environment, we use pytorch=1.13.1+cu116.

For synthetic scenes:
The dataset provided in D-NeRF is used. You can download the dataset from dropbox.

For real dynamic scenes:
The dataset provided in HyperNeRF is used. You can download scenes from Hypernerf Dataset and organize them as Nerfies. Meanwhile, Plenoptic Dataset could be downloaded from their offical websites, to save the memory, you should extract the frames of each video, them organize your dataset as follows.

├── data
│   | dnerf 
│     ├── mutant
│     ├── standup 
│     ├── ...
│   | hypernerf
│     ├── interp
│     ├── misc
│     ├── virg
│   | dynerf
│     ├── cook_spinach
│       ├── cam00
│           ├── images
│               ├── 0000.png
│               ├── 0001.png
│               ├── 0002.png
│               ├── ...
│       ├── cam01
│           ├── images
│               ├── 0000.png
│               ├── 0001.png
│               ├── ...
│     ├── cut_roasted_beef
|     ├── ...

For training synthetic scenes such as lego, run

python train.py -s data/dnerf/bouncingballs --port 6017 --expname "dnerf/bouncingballs" --configs arguments/dnerf/bouncingballs.py 

You can custom your training config through the config files.

Run the following script to render the images.

python render.py --model_path "output/dnerf/bouncingballs/"  --skip_train --configs arguments/dnerf/bouncingballs.py  &

Run the following script to evaluate the model.

python metrics.py --model_path "output/dnerf/bouncingballs/" 

There are some helpful scripts in scripts/, please feel free to use them.

Some source code of ours is borrowed from 3DGS, k-planes,HexPlane, TiNeuVox. We sincerely appreciate the excellent works of these authors.

We would like to express our sincere gratitude to @zhouzhenghong-gt for his revisions to our code and discussions on the content of our paper.

If you find this repository/work helpful in your research, welcome to cite the paper and give a ⭐.

@article{wu20234dgaussians,
  title={4D Gaussian Splatting for Real-Time Dynamic Scene Rendering},
  author={Wu, Guanjun and Yi, Taoran and Fang, Jiemin and Xie, Lingxi and Zhang, Xiaopeng and Wei Wei and Liu, Wenyu and Tian, Qi and Wang Xinggang},
  journal={arXiv preprint arXiv:2310.08528},
  year={2023}
}