VGCN-PyTorch

Thanks for your attention. In this repo, we provide the codes for the paper [Blind Omnidirectional Image Quality Assessment with Viewport Oriented Graph Convolutional Networks].

Prerequisites

• scipy==1.2.1
• opencv_python==4.1.0.25
• numpy==1.16.4
• torchvision==0.3.0
• torch==1.1.0
• Pillow==6.2.0

Install

To install all the dependencies in prerequisites

Prepare Data

• Obtain cviqd_local_epoch.pth, cviqd_global_epoch.pth, and cviqd_model.pth
• Download database

FoV Selection

matlab fov_selection/demo.m

Training

python main.py --root1 cviqd_local_epoch.pth --root2 cviqd_global_epoch.pth --save test

Testing

python main.py --resume cviqd_model.pth --skip_training

Citation

You may cite it in your paper. Thanks a lot.

@article{xu2020blind,
  title={Blind omnidirectional image quality assessment with viewport oriented graph convolutional networks},
  author={Xu, Jiahua and Zhou, Wei and Chen, Zhibo},
  journal={IEEE Transactions on Circuits and Systems for Video Technology},
  year={2020},
  publisher={IEEE}
}