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.
@article{arxiv.2304.08350,
title = {Unrolled three-operator splitting for parameter-map learning in Low Dose X-ray CT reconstruction},
author = {Andreas Kofler and Fabian Altekrüger and Fatima Antarou Ba and Christoph Kolbitsch and Evangelos Papoutsellis and David Schote and Clemens Sirotenko and Felix Frederik Zimmermann and Kostas Papafitsoros},
journal= {arXiv preprint arXiv:2304.08350},
year = {2023}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2301.05888