Luca Calatroni

collaborators

3 papers

math.OC2025

Box-constrained L0 Bregman-relaxations

Mhamed Essafri, Luca Calatroni, Emmanuel Soubies

Regularization using the L0 pseudo-norm is a common approach to promote sparsity, with widespread applications in machine learning and signal processing. However, solving such prob…

eess.IV2025

Patch-based learning of adaptive Total Variation parameter maps for blind image denoising

Claudio Fantasia, Luca Calatroni, Xavier Descombes +1

We consider a patch-based learning approach defined in terms of neural networks to estimate spatially adaptive regularisation parameter maps for image denoising with weighted Total…

cs.LG2025

Learning Spatially Adaptive $ℓ_{1}$ -Norms Weights for Convolutional Synthesis Regularization

Andreas Kofler, Luca Calatroni, Christoph Kolbitsch +1

We propose an unrolled algorithm approach for learning spatially adaptive parameter maps in the framework of convolutional synthesis-based $ℓ_{1}$ regularization. More precisely,…

Box-constrained L0 Bregman-relaxations

Patch-based learning of adaptive Total Variation parameter maps for blind image denoising

Learning Spatially Adaptive ℓ1​-Norms Weights for Convolutional Synthesis Regularization

Learning Spatially Adaptive $ℓ_{1}$ -Norms Weights for Convolutional Synthesis Regularization