Fast Noise Variance Estimation

摘要

The paper presents a fast and simple method for estimating the variance of additive zero mean Gaussian noise in an image. The method can also be used to give a local estimate of the noise variance in the situation in which the noise variance varies across the image. It requires only the use of a 3 × 3 mask followed by a summation over the image or a local neighborhood. A total of 14 integer operations per pixel is necessary. The method performs well for a large range of noise variance values. In highly textured images or regions, though, the noise estimator perceives thin lines as noise.