MAP-informed Unrolled Algorithms for Hyper-parameter Estimation - Signaux et Images Access content directly
Conference Papers Year : 2023

MAP-informed Unrolled Algorithms for Hyper-parameter Estimation

Pascal Nguyen
Emmanuel Soubies
Caroline Chaux


Hyper-parameter tuning, and especially regularisation parameter estimation, is a challenging but essential task when solving inverse problems. The solution is obtained here through the minimization of a functional composed of a data fidelity term and a regularization term. Those terms are balanced through a (or several) regularisation parameter(s) whose estimation is made under an unrolled strategy together with the inverse problem solving. The resulting network is trained while incorporating information on the model through Maximum a Posteriori estimation which drastically decreases the amount of data needed for the training and results in better estimation results. The performances are demonstrated in a deconvolution context where the regularisation is performed in the wavelet domain.
Fichier principal
Vignette du fichier
ICIP_2023_final.pdf (1.25 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04153083 , version 1 (10-07-2023)



Pascal Nguyen, Emmanuel Soubies, Caroline Chaux. MAP-informed Unrolled Algorithms for Hyper-parameter Estimation. 2023 IEEE International Conference on Image Processing (ICIP), Oct 2023, Kuala Lumpur, Malaysia. pp.2160-2164, ⟨10.1109/ICIP49359.2023.10222154⟩. ⟨hal-04153083⟩
92 View
60 Download



Gmail Facebook X LinkedIn More