Our CVPR 2024 paper 'Bayesian Differentiable Physics for Cloth Digitalization'
- GCC 9.5.0 (or MSVC 19.29.30139)
- CUDA 11.3
- Python 3.8.13
- PyTorch 1.12.1
- Kaolin 0.12.0
- Alglib 3.17.0
- Boost 1.75
- Eigen 3.3.9
- Install GCC and CUDA, and confirm their environment variables are set correctly.
- Install Python (Recommond to use Anaconda to create a new environment).
- Install Pytorch and Kaolin with following their official documentations.
- Download Alglib, Boost, and Eigen to a diretory you like.
- Change the Setup.py to make sure the paths are set correctly, i.e. INCLUDE_DIR.append(...).
- Run
python setup.py install
. - Finally, you can confirm our simulator has been successfully installed by executing the following commonds in prompt:
-> python
-> import pytorch
-> import diffsim
The data are available in the .\data...
More data will be uploaded soon.
Authors Deshan Gong, Ningtao Mao and He Wang
Deshan Gong, scdg@leeds.ac.uk
He Wang, he_wang@@ucl.ac.uk, Personal website
Project Webpage: https://drhewang.com/pages/BDP.html
Please cite our paper if you find it useful:
@InProceedings{Gong_Bayesian_2024,
author={Deshan Gong, Ningtao Mao and He Wang},
booktitle={The Conference on Computer Vision and Pattern Recognition (CVPR)},
title={Bayesian Differentiable Physics for Cloth Digitalization},
year={2024}}