Publications de Mehrsa Pourya | EPFL Graph Search

A Continuous-Domain Solution for Computed Tomography with Hessian Total-Variation Regularization

Michaël Unser, Mehrsa Pourya, Youssef Haouchat

We formulate computed-tomography reconstruction as a continuous-domain optimization problem with Hessian total variation (HTV) as the regularizer. HTV is a sparsity-promoting regularizer that favors continuous and piecewise-linear functions with few affine ...

IEEE Computer Society2024

A Box-Spline Framework for Inverse Problems With Continuous-Domain Sparsity Constraints

Michaël Unser, Mehrsa Pourya

The formulation of inverse problems in the continuum eliminates discretization errors and allows for the exact incorporation of priors. In this paper, we formulate a continuous-domain inverse problem over a search space of continuous and piecewise-linear f ...

Ieee-Inst Electrical Electronics Engineers Inc2024

Iteratively Refined Image Reconstruction with Learned Attentive Regularizers

Michaël Unser, Mehrsa Pourya

We propose a regularization scheme for image reconstruction that leverages the power of deep learning while hinging on classic sparsity-promoting models. Many deep-learning-based models are hard to interpret and cumbersome to analyze theoretically. In cont ...

2024

Delaunay-Triangulation-Based Learning With Hessian Total-Variation Regularization

Michaël Unser, Alexis Marie Frederic Goujon, Mehrsa Pourya

2023

Boosting Weakly Convex Ridge Regularizers with Spatial Adaptivity

Michaël Unser, Alexis Marie Frederic Goujon, Sebastian Jonas Neumayer, Mehrsa Pourya

2023