Liu Ce, Szeliski Richard, Bing Kang Sing, Zitnick C Lawrence, Freeman William T
Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, MA 02139, USA.
IEEE Trans Pattern Anal Mach Intell. 2008 Feb;30(2):299-314. doi: 10.1109/TPAMI.2007.1176.
Image denoising algorithms often assume an additive white Gaussian noise (AWGN) process that is independent of the actual RGB values. Such approaches are not fully automatic and cannot effectively remove color noise produced by todays CCD digital camera. In this paper, we propose a unified framework for two tasks: automatic estimation and removal of color noise from a single image using piecewise smooth image models. We introduce the noise level function (NLF), which is a continuous function describing the noise level as a function of image brightness. We then estimate an upper bound of the real noise level function by fitting a lower envelope to the standard deviations of per-segment image variances. For denoising, the chrominance of color noise is significantly removed by projecting pixel values onto a line fit to the RGB values in each segment. Then, a Gaussian conditional random field (GCRF) is constructed to obtain the underlying clean image from the noisy input. Extensive experiments are conducted to test the proposed algorithm, which is shown to outperform state-of-the-art denoising algorithms.
图像去噪算法通常假定存在一个与实际RGB值无关的加性高斯白噪声（AWGN）过程。此类方法并非完全自动化，无法有效去除当今CCD数码相机产生的彩色噪声。在本文中，我们针对两项任务提出了一个统一框架：使用分段平滑图像模型从单幅图像中自动估计并去除彩色噪声。我们引入了噪声水平函数（NLF），它是一个连续函数，将噪声水平描述为图像亮度的函数。然后，我们通过对每段图像方差的标准差拟合一个下包络来估计真实噪声水平函数的上界。对于去噪，通过将像素值投影到拟合每段RGB值的直线上，可显著去除彩色噪声的色度。然后，构建一个高斯条件随机场（GCRF），以便从有噪声的输入中获取潜在的清晰图像。我们进行了大量实验来测试所提出的算法，结果表明该算法优于现有最先进的去噪算法。
