2021/06/26 by Zhihua Wang, Zhi‐Ri Tang, Wang, Zhihua +4
Computer Science · Engineering · #Advanced Image Fusion Techniques #Advanced Image Processing Techniques #FOS: Computer and information sciences #Image and Video Quality Assessment #Multimedia (cs.MM)
paper · pdf · doi:10.48550/arxiv.2106.14076
openalex publication_date 2021/06/26 · openalex created_date 2021/07/05 · openalex updated_date 2026/07/28
Nowadays, most existing blind image quality assessment (BIQA) models 1) are developed for synthetically-distorted images and often generalize poorly to authentic ones; 2) heavily rely on human ratings, which are prohibitively labor-expensive to collect. Here, we propose an opinion-free BIQA method that learns from synthetically-distorted images and multiple agents to assess the perceptual quality of authentically-distorted ones captured in the wild without relying on human labels. Specifically, we first assemble a large number of image pairs from synthetically-distorted images and use a set of full-reference image quality assessment (FR-IQA) models to assign pseudo-binary labels of each pair indicating which image has higher quality as the supervisory signal. We then train a convolutional neural network (CNN)-based BIQA model to rank the perceptual quality, optimized for consistency with the binary labels. Since there exists domain shift between the synthetically- and authentically-distorted images, an unsupervised domain adaptation (UDA) module is introduced to alleviate this issue. Extensive experiments demonstrate the effectiveness of our proposed opinion-free BIQA model, yielding state-of-the-art performance in terms of correlation with human opinion scores, as well as gMAD competition. Codes will be made publicly available upon acceptance.