Yu Guo, Cameron Smith, Miloš Hašan, Kalyan Sunkavalli and Shuang Zhao.
In ACM Transactions on Graphics (SIGGRAPH Asia 2020). [Project page]
We don't provide the codes for GAN training, please refer to StyleGAN2.
Please download pretrained model and other necessary files here.
Please download real inputs from our paper here.
Or generate your own inputs by using tool/generate_inputs.py
To get the SVBRDF maps by optimization, please try script_optim_ours.py
02/04/2021: This is not the cleanup version. If you have difficulty running the codes or have questions about the codes/data/parameters, please send an email to Yu Guo (tflsguoyu@gmail.com). Sorry for the inconvenience.