Alternative design of DeepPDNet in the context of image restoration
This work addresses image restoration for computer vision applications, but it is incremental as it adapts an existing optimization method into a deep learning framework.
The authors tackled image restoration by designing a deep network based on unfolded Chambolle-Pock primal-dual iterations, with parameters including step-sizes and sparsity operators, and demonstrated good performance on the BSD68 database.
This work designs an image restoration deep network relying on unfolded Chambolle-Pock primal-dual iterations. Each layer of our network is built from Chambolle-Pock iterations when specified for minimizing a sum of a $\ell_2$-norm data-term and an analysis sparse prior. The parameters of our network are the step-sizes of the Chambolle-Pock scheme and the linear operator involved in sparsity-based penalization, including implicitly the regularization parameter. A backpropagation procedure is fully described. Preliminary experiments illustrate the good behavior of such a deep primal-dual network in the context of image restoration on BSD68 database.