MPI-I-2011-4-002

Many computer vision and computational photography applications essentially solve an image enhancement problem. The image has been deteriorated by a specific noise process, such as aberrations from camera optics and compression artifacts, that we would like to remove. We describe a framework for learning-based image enhancement. At the core of our algorithm lies a generic regularization framework that comprises a prior on natural images, as well as an application-specific conditional model based on Gaussian processes. In contrast to prior learning-based approaches, our algorithm can instantly learn task-specific degradation models from sample images which enables users to easily adapt the algorithm to a specific problem and data set of interest. This is facilitated by our efficient approximation scheme of large-scale Gaussian processes. We demonstrate the efficiency and effectiveness of our approach by applying it to example enhancement applications including single-image super-resolution, as well as artifact removal in JPEG- and JPEG 2000-encoded images.