Adaptive bivariate wavelet shrinkage for image denoising with spatially varying noise

Image denoising is a very important topic in many real-life applications. In most existing works, the noise level is assumed to be constant over the whole image. Nevertheless, this can be violated in practice. In this paper, we improve the bivariate wavelet shrinkage (BivShrink) to deal with spatially varying noise. Instead of a constant noise level, we estimate the noise levels locally within a small neighborhood so that we can deal with spatially varying noise more effectively. Our new method is very fast for image denoising, and it can deal with spatially varying noise levels, which can happen in real-life images. Experiments demonstrate the success of our new method for reducing both spatially varying noise and uniform noise from noisy images.