Deep synthesis regularization of inverse problems

Understand

Recently, a large number of efficient deep learning methods for solving inverse problems have been developed and show outstanding numerical performance.

• For these deep learning methods, however, a solid theoretical foundation in the form of reconstruction guarantees is missing.
• In contrast, for classical reconstruction methods, such as convex variational and frame-based regularization, theoretical convergence and convergence rate results are well established.
• In this paper, we introduce deep synthesis regularization (DESYRE) using neural networks as nonlinear synthesis operator bridging the gap between these two worlds.