This repo is the official code of paper:

"Towards Top-Down Stereoscopic Image Quality Assessment via Stereo Attention".

Sumei Li, Huilin Zhang, Haoxiang Chang, Peimin Lin, Wei Xiang.

Tianjin University, Tianjin, China.

• Release the code of SATNet (satnet.py) after the paper is accepted.

• Python 3.8.5
• PyTorch 1.11.0
• torchvision 0.12.0
• CUDA 11.3

In addition, requirement.txt lists all the required packages:

pip install -r requirements.txt

We provide a demo to show how to use SATNet to predict the quality of a stereoscopic image pair.

The code is coming soon.

The code is coming soon.

If you find this repo helpful, please cite our paper:

@misc{zhang2023topdown,
      title={Towards Top-Down Stereoscopic Image Quality Assessment via Stereo Attention}, 
      author={Huilin Zhang and Sumei Li and Yongli Chang},
      year={2023},
      eprint={2308.04156},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

For more SIQA models implemented in PyTorch, please visit our repo SIQA-models-PyTorch-lib.