This is the pytorch implementation of the paper Locally Adaptive Structure and Texture Similarity for Image Quality Assessment — an extension of DISTS, which separates structure and texture across space and scale, and assigns the adaptive weights to quality measurements according to local image content.
@inproceedings{ding2021adists,
title={Locally Adaptive Structure and Texture Similarity for Image Quality Assessment},
author={Ding, Keyan and Liu, Yi and Zou, Xueyi and Wang, Shiqi and Ma, Kede},
booktitle={Proceedings of the 29th ACM International Conference on Multimedia},
pages={2483--2491},
year={2021}
}