6 papers
Flower: A Flow-Matching Solver for Inverse Problems
Mehrsa Pourya, Bassam El Rawas, Michael Unser
We introduce Flower, a solver for linear inverse problems. It leverages a pre-trained flow model to produce reconstructions that are consistent with the observed measurements. Flow…
DEALing with Image Reconstruction: Deep Attentive Least Squares
Mehrsa Pourya, Erich Kobler, Michael Unser +1
State-of-the-art image reconstruction often relies on complex, highly parameterized deep architectures. We propose an alternative: a data-driven reconstruction method inspired by t…
Comparison of 2D Regular Lattices for the CPWL Approximation of Functions
Mehrsa Pourya, Maïka Nogarotto, Michael Unser
We investigate the approximation error of functions with continuous and piecewise-linear (CPWL) representations. We focus on the CPWL search spaces generated by translates of box s…
Iteratively Refined Image Reconstruction with Learned Attentive Regularizers
Mehrsa Pourya, Sebastian Neumayer, Michael Unser
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 m…
Random ReLU Neural Networks as Non-Gaussian Processes
Rahul Parhi, Pakshal Bohra, Ayoub El Biari +2
We consider a large class of shallow neural networks with randomly initialized parameters and rectified linear unit activation functions. We prove that these random neural networks…
Delaunay-Triangulation-Based Learning with Hessian Total-Variation Regularization
Mehrsa Pourya, Alexis Goujon, Michael Unser
Regression is one of the core problems tackled in supervised learning. Rectified linear unit (ReLU) neural networks generate continuous and piecewise-linear (CPWL) mappings and are…