Tackling Inverse Problems in Imaging Using Targeted Priors

Image denoising is one of the core problems in image processing and some argue that current state-of-the-art general purpose methods may be reaching the maximum possible performance. This talk focuses on two main topics: 1) how can we push such limit; 2) how to leverage the developments in image denoising to tackle other inverse imaging problems. In the former, we propose learning priors that are adapted to specific classes of images, such as documents and face images, or to specific tasks. In the latter, we build upon the recently proposed plug-and-play framework, by plugging a state-of-the-art denoiser into the iterations of an alternating direction method of multipliers algorithm.