---

[Prerelease] Official implementation of "GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization".

🛠️ Pipeline

---

0. Installation

The installation of GIR is similar to 3D Gaussian Splatting.

# Clone the Repository
git clone https://github.com/guduxiaolang/GIR.git

# Create the environment
conda create -n gir python=3.7
conda activate gir
 
# Install the dependencies
pip install -r requirements.txt
pip install torch==1.12.1+cu116 torchvision==0.13.1+cu116 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu116
pip install -e submodules/diff-gaussian-rasterization
pip install -e submodules/simple-knn
pip install -e submodules/envlight
pip install tqdm plyfile 
    
# Load HDR images correctly 
pip install imageio[full]

---

1. Data preparation

The files are as follows:

Blender Dataset

[DATA_ROOT]
|---test
|   |---<image 0>
|   |---<image 1>
|   |---...
|---train
|   |---<image 0>
|   |---<image 1>
|   |---...
|---transforms_test.json
|---transforms_train.json

COLMAP Dataset

[DATA_ROOT] 
|---images
|   |---<image 0>
|   |---<image 1>
|   |---...
|---sparse
    |---0
        |---cameras.bin
        |---images.bin
        |---points3D.bin

---

2. Training and Evalution

The training and evaluation commands for each dataset are provided in the shell scripts located in the scripts folder.

The basic training and testing commands are shown below.

# training
python train.py -s $data_dir --eval --port $port_num --random_background --hdr_rotation
    
# rendering
python render.py -m $model_dir --skip_train --save_name "render" -w --hdr_rotation
    
# relighting
python render.py -m $model_dir --skip_train --save_name ${hdr_list_name%.*} -w --hdr_rotation --environment_texture $hdr_dir --render_relight

---

3. Acknowledgements

We are quite grateful for 3DGS, NeRO, and Filament

---