尺度因子感知对比学习的无参考型超分辨图像质量评价  

No-reference super-resolution image quality assessment based on upscaling-factor aware contrastive learning

作　　者：樊丹丹 张凯兵[1,2,3] 权星 孟雅蕾 FAN Dandan;ZHANG Kaibing;QUAN Xing;MENG Yalei(School of Electronics and Information,Xi’an Polytechnic University,Xi’an 710048,China;School of Computer Science,Xi’an Polytechnic University,Xi’an 710048,China;Shaanxi Key Laboratory of Clothing Intelligence,Xi’an 710048,China)

机构地区：[1]西安工程大学电子信息学院,陕西西安710048 [2]西安工程大学计算机科学学院,陕西西安710048 [3]陕西省服装设计智能化重点实验室,陕西西安710048

出　　处：《西北大学学报(自然科学版)》2025年第2期309-319,共11页Journal of Northwest University(Natural Science Edition)

基　　金：国家自然科学基金(61971339);陕西省自然科学基础研究计划重点项目(2018JZ6002)。

摘　　要：超分辨图像的质量不仅受重建算法的影响,而且在不同的尺度因子下重建出的图像在质量退化等级方面存在一定差异。然而现有的无参考型超分辨图像质量评价方法主要关注超分辨率图像的视觉特征,忽略了可用的尺度因子信息。提出了一种尺度因子感知对比学习(upscaling-factor aware contrastive learning,UFACL)方法,该网络结构分为尺度因子识别分支和质量分数分支。其中尺度因子识别分支从数据集本身出发,将不同尺度因子的超分辨图像作为彼此的正负样本,在完成分类任务的同时引入对比学习,提高有效特征的表达能力。在质量分数分支设计了一个频域注意模块(frequency domain attention module,FDAM),考虑了全局信息和通道信息,同时,该分支使用倒残差块(inverted residuals blocks,IRB)降低模型的计算量,使得在训练过程中既保证了质量分数预测精度又提升了模型训练效率。实验结果表明,提出的UFACL能够获得与主观感知质量更好的一致性。The quality of super-resolution images is not only affected by the reconstruction algorithm,but also there are some differences in the quality degradation levels of the reconstructed images under different upscaling-factors.However,the existing no-reference super-resolution image quality assessment(NR-SRIQA)methods mainly focus on the visual features of super-resolution images,ignoring the available upscaling-factor information.An upscaling-factor aware contrastive learning(UFACL)method is proposed.The network structure is divided into a upscaling-factor recognition branch and a quality score branch.The upscaling-factor recognition branch starts from the dataset,and takes the super-resolution images of different upscaling-factors as positive and negative samples of each other.Contrastive learning is introduced to complete the classification task,so as to improve the expression ability of effective features.In the quality score branch,a frequency domain attention module(FDAM)is designed,which considers both global information and channel information.At the same time,this branch uses inverted residuals blocks(IRB)to reduce the calculation amount of the model,which ensures the accuracy of quality score prediction and improves the training efficiency of the model in the training process.Experimental results show that the proposed UFACL can achieve better consistency with subjective perceived quality.

关 键 词：超分辨图像质量评价 尺度因子 对比学习 频域注意模块 倒残差块 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]