The enormous space and diversity of natural images is usually represented by a few small-scale human-rated image quality assessment (IQA) datasets. This casts great challenges to deep neural network (DNN) based blind IQA (BIQA), which requires large-scale training data that is representative of the natural image distribution. It is extremely difficult to create human-rated IQA datasets composed of millions of images due to constraints of subjective testing. While a number of efforts have focused on design innovations to enhance the performance of DNN based BIQA, attempts to address the scarcity of labeled IQA data remain surprisingly missing. To address this data challenge, we construct so far the largest IQA database, namely Waterloo Exploration-II, which contains 3,570 pristine reference and around 3.45 million singly and multiply distorted images. Since subjective testing for such a large dataset is nearly impossible, we develop a novel mechanism that synthetically assigns perceptual quality labels to the distorted images. We construct a DNN-based BIQA model called EONSS, train it on Waterloo Exploration-II, and test it on nine subject-rated IQA datasets, without any retraining or fine-tuning. The results show that with a straightforward DNN architecture, EONSS is able to outperform the very state-of-the-art in BIQA, both in terms of quality prediction performance and execution speed. This study strongly supports the view that the quantity and quality of meaningfully annotated training data, rather than a sophisticated network architecture or training strategy, is the dominating factor that determines the performance of DNN-based BIQA models. (Note: Since this is an ongoing project, the final versions of Waterloo Exploration-II database, quality annotations, and EONSS, will be made publicly available in the future when it culminates.)
翻译:自然图像的巨大空间和多样性通常表现在少数小规模的人端标准图像质量评估(IQA)数据集上。这给深神经网络(DNN)基于盲盲IQA(BIQA)的深神经网络(DNN)盲盲IQA(BIQA)带来了巨大挑战,这需要大规模培训数据来代表自然图像的分布。由于主观测试的限制,很难创建由数百万图像组成的人类级IQA数据集。虽然一些努力侧重于设计创新,以提高基于BIQA的 DNNS 质量评估(IQA)的性能,试图解决标签IQA数据的稀缺问题,令人惊讶地缺少数据。为了应对这一数据挑战,我们迄今为止建造了最大的IQA数据库,即WaterloeExlation-II, 包含370 pristine 参考, 以及大约345万个随机和数的扭曲图像。由于对如此庞大的数据集进行主观测试几乎是不可能的,我们开发了一种新型机制,在扭曲的图像中合成地给DNEQA的品质标签标签。我们建了一个名为DQA的模型,在Weloeloeloal-real-real-de-de-al-de-deal-deal-deal-deal-deal-deal-destrual-deal-deal-deal a a a a la export the brodustrual dal a exal a exportmental exportmental exportmental dismal laismational lautmental 。