Simulation results (color denoising)

Color images are filtered in a luminance-chrominance space, exploiting the structural information obtained from the luminance channel to drive the shape-adaptation for the chrominance channels. In practice, we impose that the three transforms supports which are used for the filtering of the Y , U, and V channels at a particular location have the same adaptive shape, which is defined by the anisotropic LPA-ICI for the luminance channel.


Details of the original F-16 image, noisy observation (σ=30, PSNR=18.59dB), estimate by ProbShrink-MultiBand (Pizurica et al.) (PSNR=30.50dB), and Anisotropic LPA-ICI + SA-DCT estimate (PSNR=31.59dB).