Removing noise from images usually results in smoothing of edges and areas with discontinuities. Such nonsmooth areas however play a significant role in the perception of image quality. This paper studies the restoration of these regions during denoising. We exploit the fact that the discontinuities in the pixel chromaticity in these regions are less abrupt than those in the pixel luminance. We derive a Bayesian method that estimates the parts of the latent image data in the nonsmooth areas that a denoiser erroneously removes. We demonstrate that adding back this recovered part of the latent image data improves the denoising performance.