Class-adapted and Scene-Adapted Regularization for Imaging Inverse ProblemsMS37

I will discuss our recent work on patch-based models that are adapted to specific image classes, or even specific scenes. We illustrate their use beyond image denoising, in more general inverse problems, such as inpainting, deblurring, and hyperspectral super-resolution, using the recently introduced plug-and-play-ADMM approach. We discuss conditions for convergence of the resulting algorithm. This is joint work with José Bioucas-Dias and Afonso Teodoro

This presentation is part of Minisymposium “MS37 - Sparse-based techniques in variational image processing (2 parts)
organized by: Serena Morigi (Dept. Mathematics, University of Bologna) , Ivan Selesnick (New York University) , Alessandro Lanza (Dept. Mathematics, University of Bologna) .

Mário Figueiredo (Instituto de Telecomunicações and IST, University of Lisboa)
image reconstruction