论文标题
了解SSIM
Understanding SSIM
论文作者
论文摘要
结构相似性指数（SSIM）的使用广泛。在近二十年的时间里，它在许多不同的研究学科中在图像质量评估中发挥了重要作用。显然，其优点在研究界无可争议。但是，对此指数的审查很少。与普遍的看法相反，SSIM的一些有趣的属性值得这类审查。在本文中，我们分析了SSIM的数学因素，并表明它可以在合成和现实的用例中产生结果，这些案例是出乎意料的，有时不确定且不直觉的。结果，基于SSIM评估图像质量可能会导致结论不正确，并将SSIM用作深度学习的损失功能可以指导神经网络训练的方向错误。
The use of the structural similarity index (SSIM) is widespread. For almost two decades, it has played a major role in image quality assessment in many different research disciplines. Clearly, its merits are indisputable in the research community. However, little deep scrutiny of this index has been performed. Contrary to popular belief, there are some interesting properties of SSIM that merit such scrutiny. In this paper, we analyze the mathematical factors of SSIM and show that it can generate results, in both synthetic and realistic use cases, that are unexpected, sometimes undefined, and nonintuitive. As a consequence, assessing image quality based on SSIM can lead to incorrect conclusions and using SSIM as a loss function for deep learning can guide neural network training in the wrong direction.
