Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution
This work addresses the problem of image quality assessment for computer vision researchers and practitioners, providing a new approach to quantify the relationship between image scale and perceived quality.
The authors tackled the problem of quantifying the relationship between image scale and perceived quality, and achieved a significant improvement in performance by introducing the Image Intrinsic Scale Assessment task and a weak-labeling strategy, with results demonstrated on the IISA-DB dataset of 785 image-IIS pairs. The proposed WIISA strategy consistently improved the performance of several IQA methods adapted for IISA.
Image Quality Assessment (IQA) measures and predicts perceived image quality by human observers. Although recent studies have highlighted the critical influence that variations in the scale of an image have on its perceived quality, this relationship has not been systematically quantified. To bridge this gap, we introduce the Image Intrinsic Scale (IIS), defined as the largest scale where an image exhibits its highest perceived quality. We also present the Image Intrinsic Scale Assessment (IISA) task, which involves subjectively measuring and predicting the IIS based on human judgments. We develop a subjective annotation methodology and create the IISA-DB dataset, comprising 785 image-IIS pairs annotated by experts in a rigorously controlled crowdsourcing study. Furthermore, we propose WIISA (Weak-labeling for Image Intrinsic Scale Assessment), a strategy that leverages how the IIS of an image varies with downscaling to generate weak labels. Experiments show that applying WIISA during the training of several IQA methods adapted for IISA consistently improves the performance compared to using only ground-truth labels. The code, dataset, and pre-trained models are available at https://github.com/SonyResearch/IISA.