Skip to content

Zhanpeng1202/Instant4D

Repository files navigation

Instant4D: 4D Gaussian Splatting in Minutes

Website PDF Paper BibTex

Installation

Clone the repository with the submodules by using:

git clone --recursive [email protected]:Zhanpeng1202/Instant4D.git

Environment

Update requirements.txt with correct CUDA version for PyTorch and cuUML, i.e., replacing cu126 and cu12 with your CUDA version.

conda create -n instant4d python=3.10
conda activate instant4d
pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cu126 # change to your CUDA version 
pip install -r requirement.txt


pip install xformers # read below
# Note: mega-sam requires xformers for Unidepth, but there is a dependancy issue for newer pytroch
# But Gaussian Splatting require CUDA version match.
# therefore one workaround is to use a different virtual environment only for Unidepth metric depth estimaiton

To install mega-sam, run the following command:
Note: change the .type() to scalar_type() in mega-sam\base\src\altcorr_kernel, mega-sam\base\src\correlation_kernels and mega-sam/base/thirdparty/lietorch/lietorch/src/lietorch_gpu.cu if using torch >2.7, refer this issue.

cd SLAM/mega-sam/base
python setup.py install
cd ../../../../

To install Gaussian Splatting accelerating package, run the following command:

cd submodule
pip install fussed-ssim
pip install simple-knn
cd pointops2
python setup.py install
cd ../..

Noted that the gaussian splatting package will be compile during the first running.

Downloading pretrained checkpoints for mega-sam

  1. Download DepthAnything checkpoint to mega-sam/Depth-Anything/checkpoints/depth_anything_vitl14.pth

  2. Download and include RAFT checkpoint at mega-sam/cvd_opt/raft-things.pth

4DGS Remote Viewer

We provide a lightweight websocket remote viewer to visualize 4DGS training process. Users can train 4DGS on a server and hope to view it on local computer.

On the local computer

# download these file in local computer
git clone [email protected]:Zhanpeng1202/gaussian_splatting_websocket_viewer.git

# Connect Server with SSH with vscode
vscode ssh server 

#set up forward port in vscode
Terminal -> Ports -> Forward a Ports -> 6119

On the server

# clone the official gaussain splatting repository
git clone [email protected]:graphdeco-inria/gaussian-splatting.git --recursive

# put networkGUI_Websocket.py in to correct location inside the cloned repository
<location>
|---gaussian_splatting
|   |---gaussain_render
|   |   |---network_gui.py
|   |   |---network_gui_websocket.py

|   |---train.py 
# replace train.py with that provided in this repository

Dataset

mkdir dataset
cd dataset

Download the pre-processed data by DynamicNeRF.

mkdir Nvidia
wget --no-check-certificate https://filebox.ece.vt.edu/~chengao/free-view-video/data.zip
unzip data.zip
rm data.zip

DAVIS or custom sequences

We provide sample videos under examples/, one can start from reproduce them.

Optimization

Change the path and weight in script/reconstruct.sh and change the config accordingly in the script/optmize

source script/reconstruct.sh 
python -m script.prune
python -m script.optmize

Acknowledgement

This work is built on many amazing research works and open-source projects, thanks a lot to all the authors for sharing!

Citation

If you find this project useful in your research, please consider citing:

@article{luo2025instant4d,
  title={Instant4d: 4d gaussian splatting in minutes},
  author={Luo, Zhanpeng and Ran, Haoxi and Lu, Li},
  journal={Advances in neural information processing systems},
  year={2025}
}

About

[NeurIPS 2025] Instant4D: 4D Gaussian Splatting in Minutes

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •