Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution

TL;DR

This paper introduces the concept of Image Intrinsic Scale (IIS) to quantify how image perceived quality varies with scale, develops a dataset and methodology for assessing IIS, and improves IQA models using weak-labeling strategies.

Contribution

It defines the IIS concept, creates the IISA-DB dataset with expert annotations, and proposes WIISA for enhancing IQA models through weak-labeling based on scale variations.

Findings

WIISA improves IQA model performance.

The IISA-DB dataset contains 785 annotated image-IIS pairs.

Applying WIISA during training yields consistent accuracy gains.

Abstract

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.