Recently, with the development of deep learning, a number of Just Noticeable Difference (JND) datasets have been built for JND modeling. However, all the existing JND datasets only label the JND points based on the level of compression distortion. Hence, JND models learned from such datasets can only be used for image/video compression. As known, JND is a major characteristic of the human visual system (HVS), which reflects the maximum visual distortion that the HVS can tolerate. Hence, a generalized JND modeling should take more kinds of distortion types into account. To benefit JND modeling, this work establishes a generalized JND dataset with a coarse-to-fine JND selection, which contains 106 source images and 1,642 JND maps, covering 25 distortion types. To this end, we proposed a coarse JND candidate selection scheme to select the distorted images from the existing Image Quality Assessment (IQA) datasets as JND candidates instead of generating JND maps ourselves. Then, a fine JND selection is carried out on the JND candidates with a crowdsourced subjective assessment.

翻译：近年来，随着深度学习的发展，已有多个用于刚可察觉差异（JND）建模的JND数据集被构建。然而，现有JND数据集均仅基于压缩失真程度标注JND点。因此，基于此类数据集学习的JND模型仅能用于图像/视频压缩。众所周知，JND是人类视觉系统（HVS）的核心特性，反映HVS所能容忍的最大视觉失真。因此，广义的JND建模应纳入更多失真类型。为促进JND建模，本研究建立了一个采用由粗到精JND选择策略的广义JND数据集，包含106张源图像与1,642张JND图，覆盖25种失真类型。为此，我们提出粗粒度JND候选选择方案，从现有图像质量评估（IQA）数据集中选取失真图像作为JND候选（而非自行生成JND图），继而通过众包主观评估对JND候选进行细粒度JND筛选。