Joint Denoising and Decompression Using CNN Regularization

Wavelet compression schemes (such as JPEG2000) lead to very specific visual artifacts due to the quantization of noisy wavelet coefficients. They have highly spatialy-correlated structure that makes it difficult to be removed with standard denoising algorithms. In this work, we propose a joint denoising and decompression method that combines a data-fitting term which takes into account the quantization process and an implicit prior contained in a stateof-the-art denoising CNN.