提出图像内在尺度概念，量化人眼感知质量最优的分辨率。
Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution
- 定义图像内在尺度为感知质量最高的最大分辨率
- 构建包含785对标注的IISA-DB数据集，基于专家主观评估
- 提出弱标签策略提升模型在低标注数据下的性能
图像质量评估（IQA）旨在通过人类观察者预测感知质量。尽管近期研究指出图像尺度变化对感知质量有关键影响，但该关系尚未系统量化。为此，我们引入图像内在尺度（IIS），定义为图像呈现最高感知质量的最大尺度。同时提出图像内在尺度评估（IISA）任务，基于人类判断进行测量与预测。我们设计了主观标注方法，创建了包含785个图像-IIS配对的IISA-DB数据集，由专家在严格控制的众包研究中完成标注。此外，我们提出WIISA（弱标签图像内在尺度评估）策略，利用图像在降尺度过程中的IIS变化生成弱标签。实验表明，在多个适配IISA的IQA方法训练中，使用WIISA可显著优于仅依赖真实标签的表现。代码、数据集及预训练模型已公开于https://github.com/SonyResearch/IISA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。