61 citations · 67 across the 8 of their papers we have counts for
4 papers · 1 filter
Beyond Convolution: A Taxonomy of Structured Operators for Learning-Based Image Processing
Simone Cammarasana
The convolution operator is the fundamental building block of modern convolutional neural networks (CNNs), owing to its simplicity, translational equivariance, and efficient implem…
Optimal Weighted Convolution for Classification and Denosing
Simone Cammarasana, Giuseppe Patanè
We introduce a novel weighted convolution operator that enhances traditional convolutional neural networks (CNNs) by integrating a spatial density function into the convolution ope…
Optimal Density Functions for Weighted Convolution in Learning Models
Simone Cammarasana, Giuseppe Patanè
The paper introduces the weighted convolution, a novel approach to the convolution for signals defined on regular grids (e.g., 2D images) through the application of an optimal dens…
Learning-based Framework for US Signals Super-resolution
Simone Cammarasana, Paolo Nicolardi, Giuseppe Patanè
We propose a novel deep-learning framework for super-resolution ultrasound images and videos in terms of spatial resolution and line reconstruction. We up-sample the acquired low-r…