A New Image Quality Metric for Image Auto-denoising
A New Image Quality Metric for Image Auto-denoising
复制标题
DOI：
10.1109/iccv.2013.359
复制
发表时间：
2013-12
期刊：
影响因子：
--
通讯作者：
Xiangfei Kong;Kuan Li;Qingxiong Yang;Wenyin Liu;Ming-Hsuan Yang
中科院分区：
文献类型：
--
作者：
Xiangfei Kong;Kuan Li;Qingxiong Yang;Wenyin Liu;Ming-Hsuan Yang
本文提出了一种新的非参考图像质量度量，可用于最新的图像/视频去噪算法的自动去噪。所提出的度量非常简单，可以在四行MatLab代码中实现。该度量所采用的基本假设是噪声应该独立于原始图像。然而，由于现有去噪方法的精度相对较低，因此直接测量这种相关性是不切实际的。该度量的目标是最大化输入噪声图像与均匀区域周围估计图像噪声之间的结构相似性，以及高结构区域附近输入噪声图像与去噪图像之间的结构相似性，并作为两个对应的结构相似图的线性相关系数来计算。大量的实验结果表明，该度量不仅在数量和质量上都优于目前最先进的非参考质量度量，而且在用于视频去噪时还能更好地保持时间一致性。
This paper proposes a new non-reference image quality metric that can be adopted by the state-of-the-art image/ video denoising algorithms for auto-denoising. The proposed metric is extremely simple and can be implemented in four lines of Matlab code. The basic assumption employed by the proposed metric is that the noise should be independent of the original image. A direct measurement of this dependence is, however, impractical due to the relatively low accuracy of existing denoising method. The proposed metric thus aims at maximizing the structure similarity between the input noisy image and the estimated image noise around homogeneous regions and the structure similarity between the input noisy image and the denoised image around highly-structured regions, and is computed as the linear correlation coefficient of the two corresponding structure similarity maps. Numerous experimental results demonstrate that the proposed metric not only outperforms the current state-of-the-art non-reference quality metric quantitatively and qualitatively, but also better maintains temporal coherence when used for video denoising.