Official code for the paper "LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes".

😴 LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes 😴

LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes

*Jaeyoung Chung, *Suyoung Lee, Hyeongjin Nam, Jaerin Lee, Kyoung Mu Lee

*Denotes equal contribution.

⚡ Usage

We offer several ways to interact with LucidDreamer:

1. A demo is available on ironjr/LucidDreamer HuggingFace Space (including custom SD ckpt) and ironjr/LucidDreamer-mini HuggingFace Space (minimal features / try at here in case of the former is down) (We appreciate all the HF / Gradio team for their support).

2. Another demo is available on a Colab, implemented by @camenduru (We greatly thank @camenduru for the contribution).
3. You can use the gradio demo locally by running CUDA_VISIBLE_DEVICES=0 python app.py (full feature including huggingface model download, requires ~15GB) or CUDA_VISIBLE_DEVICES=0 python app_mini.py (minimum viable demo, uses only SD1.5).
4. You can also run this with command line interface as described below.

Prerequisite

• CUDA>=11.4 (higher version is OK).
• Python==3.9 (cannot use 3.10 due to open3d compatibility)

Install

Ubuntu

conda create -n lucid python=3.9
conda activate lucid
pip install peft diffusers scipy numpy imageio[ffmpeg] opencv-python Pillow open3d torchvision gradio
# ZoeDepth
pip install torch==2.0.1 timm==0.6.7
# Gaussian splatting
pip install plyfile==0.8.1

cd submodules/depth-diff-gaussian-rasterization-min
# sudo apt-get install libglm-dev # may be required for the compilation.
python setup.py install
cd ../simple-knn
python setup.py install
cd ../..

Windows (Experimental, Tested on Windows 11 with VS2022)

Note: Windows installation is experimental and may contain errors during installation. Please report the error to issues if occurs.

• CUDA of the same version as the cudatoolkit used when installing pytorch must be installed in your system. Here we assume that CUDA version is 11.8.
• C++ (>=14) should be installed in your system. If not download it using the Visual Studio build tools.

conda create -n lucid python=3.9
conda activate lucid
conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.8 -c pytorch -c nvidia
pip install peft diffusers scipy numpy imageio[ffmpeg] opencv-python Pillow open3d gradio
# ZoeDepth
pip install timm==0.6.7
# Gaussian splatting
pip install plyfile==0.8.1

cd submodules\depth-diff-gaussian-rasterization-min\third_party
git clone https://github.com/g-truc/glm.git
cd ..\
python setup.py install
cd ..\simple-knn
python setup.py install
cd ..\..

Run with your own samples

# Default Example
python run.py

To run with your own inputs and prompts, attach following arguments after run.py.

• -img : path of input image.
• -t : text prompt. Can be either path to txt file or the text itself.
• -nt : negative text prompt. Can be either path to txt file or the text itself.
• -cg : camera extrinsic path for generating scenes. Can be one of "Rotate_360", "LookAround", or "LookDown".
• -cr : camera extrinsic path for rendering videos. Can be one of "Back_and_forth", "LLFF", or "Headbanging".
• --seed : manual seed for Stable Diffusion inpainting.
• --diff_steps : number of denoising steps for Stable Diffusion inpainting. Default is 50.
• -s : path to save results.

Visualize .ply files

There are multiple available viewers / editors for Gaussian splatting .ply files.

1. @playcanvas's Super-Splat project (Live demo). This is the viewer we have used for our debugging along with MeshLab.

2. @antimatter15's WebGL viewer for Gaussian splatting (Live demo).

3. @splinetool's web-based viewer for Gaussian splatting. This is the version we have used in our project page's demo.

🚩 Updates

• ✅ December 8, 2023: HuggingFace Space demo is out. We deeply thank all the HF team for their support!
• ✅ December 7, 2023: Colab implementation is now available thanks to @camenduru!
• ✅ December 6, 2023: Code release!
• ✅ November 22, 2023: We have released our paper, LucidDreamer on arXiv.

🌏 Citation

Please cite us if you find our project useful!

@article{chung2023luciddreamer,
    title={LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes},
    author={Chung, Jaeyoung and Lee, Suyoung and Nam, Hyeongjin and Lee, Jaerin and Lee, Kyoung Mu},
    journal={arXiv preprint arXiv:2311.13384},
    year={2023}
}

🤗 Acknowledgement

We deeply appreciate ZoeDepth, Stability AI, and Runway for their models.

📧 Contact

If you have any questions, please email robot0321@snu.ac.kr, esw0116@snu.ac.kr, jarin.lee@gmail.com.

⭐ Star History