Chengfeng Zhao¹, Junbo Qi², Zhiyang Dou³, Minchen Li⁴, Ziwei Liu⁵, Wenping Wang⁶, Yuan Liu^1,5,†

¹The Hong Kong University of Science and Technology    ²Waseda University    ³The University of Hong Kong   
⁴Carnegie Mellon University    ⁵Nanyang Technological University    ⁶Texas A&M University
^†Corresponding author

We tested our environment on Ubuntu 20.04 LTS with CUDA 12.1, gcc 9.4.0, and g++ 9.4.0.

conda create python=3.10 --name unic
conda activate unic

pip install torch==2.5.0 torchvision==0.20.0 torchaudio==2.5.0 --index-url https://download.pytorch.org/whl/cu121
pip install -r requirements.txt

conda install -c fvcore -c iopath -c conda-forge fvcore iopath
pip install "git+https://github.com/facebookresearch/pytorch3d.git@stable"

git clone https://github.com/unlimblue/KNN_CUDA.git
cd KNN_CUDA
make && make install
cd ..

Thanks to the following work that we refer to and benefit from:

• Codebook Matching: the categorical encoder architecture and the Unity project framework;
• NeRF-Pytorch: the neural field implementation;
• SMPL-to-FBX: the FBX Python SDK usage;
• HOOD: the visualization code

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.