dc.contributor.author | Kofler, A | |
dc.contributor.author | Altekrüger, F | |
dc.contributor.author | Ba, FA | |
dc.contributor.author | Kolbitsch, C | |
dc.contributor.author | Papoutsellis, E | |
dc.contributor.author | Schote, D | |
dc.contributor.author | Sirotenko, C | |
dc.contributor.author | Zimmermann, FF | |
dc.contributor.author | Papafitsoros, K | |
dc.date.accessioned | 2024-02-16T12:23:55Z | |
dc.date.available | 2024-02-16T12:23:55Z | |
dc.date.issued | 2023-04-17 | |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/94667 | |
dc.description.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. | en_US |
dc.publisher | arXiv | en_US |
dc.subject | math.OC | en_US |
dc.subject | math.OC | en_US |
dc.subject | eess.IV | en_US |
dc.title | Unrolled three-operator splitting for parameter-map learning in Low Dose X-ray CT reconstruction | en_US |
dc.rights.holder | © 2023, The Author(s). | |
pubs.author-url | http://arxiv.org/abs/2304.08350v1 | en_US |
pubs.notes | Not known | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |