This is a comprehensive, critical, and pedagogical review of volumetric emission tomography for combustion processes. Many flames that are of interest to scientists and …
Since their inception in the 1930–1960s, the research disciplines of computational imaging and machine learning have followed parallel tracks and, during the last two decades …
Deep learning has been proven to yield reliably generalizable solutions to numerous classification and decision tasks. Here, we demonstrate for the first time to our knowledge …
In the study of compressed sensing (CS), the two main challenges are the design of sampling matrix and the development of reconstruction method. On the one hand, the …
Regularization methods are a key tool in the solution of inverse problems. They are used to introduce prior knowledge and allow a robust approximation of ill-posed (pseudo-) inverses …
S Lefkimmiatis - Proceedings of the IEEE conference on …, 2018 - openaccess.thecvf.com
We design a novel network architecture for learning discriminative image models that are employed to efficiently tackle the problem of grayscale and color image denoising. Based on …
S Lefkimmiatis - Proceedings of the IEEE conference on …, 2017 - openaccess.thecvf.com
We propose a novel deep network architecture for grayscale and color image denoising that is based on a non-local image model. Our motivation for the overall design of the proposed …
Sparse representation models code an image patch as a linear combination of a few atoms chosen out from an over-complete dictionary, and they have shown promising results in …
Convolutional neural networks (CNNs) have gained tremendous success in solving complex inverse problems. The aim of this work is to develop a novel CNN framework to reconstruct …