Unrolled three-operator splitting for parameter-map learning in Low Dose X-ray CT reconstruction
Abstract
We propose a method for fast and automatic estimation of spatially dependent regularization maps for total variation-based (TV) tomography reconstruction. The estimation is based on two distinct sub-networks, with the first sub-network estimating the regularization parameter-map from the input data while the second one unrolling T iterations of the Primal-Dual Three-Operator Splitting (PD3O) algorithm. The latter approximately solves the corresponding TV-minimization problem incorporating the previously estimated regularization parameter-map. The overall network is then trained end-to-end in a supervised learning fashion using pairs of clean-corrupted data but crucially without the need of having access to labels for the optimal regularization parameter-maps.
Authors
Kofler, A; Altekrüger, F; Ba, FA; Kolbitsch, C; Papoutsellis, E; Schote, D; Sirotenko, C; Zimmermann, FF; Papafitsoros, KCollections
- Mathematics [1458]