Image Denoising and Inpainting with Deep Neural Networks

We present a novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA). We pro-pose an alternative training scheme that successfully adapts DA, originally de-signed for unsupervised feature learning, to the tasks of image denoising and blind inpainting. Our method’s performance in the image denoising task is comparable to that of KSVD which is a widely used sparse coding technique. More impor-tantly, in blind image inpainting task, the proposed method provides solutions to some complex problems that have not been tackled before. Specifically, we can automatically remove complex patterns like superimposed text from an image, rather…