Structural Toughness Under Noise: An Efficient No-Reference Image Distortion Assessment for Blur and Noise

In image denoising and reconstruction problems, it is useful to monotonically quantify the distortions in images representing the same scene. For this purpose, we propose a training-free no-reference image distortion assessment method for both blur and noise. The method is based on the observation that the structural similarity between an input image and its shifted-and-noised copy is related to the levels of blur and noise distorting the input image. Computing a noised copy would require a random number generation, but assuming virtual noise independent from the input image, we derived the method that does not require computing actual noised copy. In our experiments of assessing the singly/multiply distorted images representing the same scene, the proposed method generally showed better monotonicity than competing state-of-the-art methods. The proposed method runs about 80 times faster than those competing methods and it can assess local regions of the input image, which makes it useful in spatially adaptive denoising applications.