Emanuele Schiavi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Emanuele Schiavi has a total of 81 co-authors. Here are the top co-authors by number of shared publications:
- Adrian Martin
Applied Mathematics, Universidad Rey Juan Carlos, Mostoles, Madrid, Spain
12 shared publications - Norberto Malpica
Medical Image Analysis and Biometry Lab, Universidad Rey Juan Carlos, Madrid, Spain
8 shared publications - Jesús Ildefonso Díaz
Universidad Complutense de Madrid, Instituto de Matemática Interdisciplinar, Plaza de las Ciencias, 3, 28040 Madrid, Spain
6 shared publications - Juan Francisco Garamendi
INRIA/INSERM U746/CNRS, UMR6074/University of Rennes I, Rennes 35043, France
5 shared publications - Ana Isabel Muñoz
Departamento de Matemática Aplicada Ciencia e Ingenieria de los Materiales y Tecnologia Electrónica Universidad Rey Juan Carlos Móstoles 28933 Madrid Spain
4 shared publications - Iván Ramírez
CAPO Research Group, Universidad Rey Juan Carlos, Mstoles, Madrid, Spain
4 shared publications
Latest Publications
- Open Access
- 9 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 73 (1) , 347-359
LLNN: A Scalable LUT-Based Logic Neural Network Architecture for FPGAs
When deploying neural networks for inference on specialized hardware devices such as field-programmable gate arrays (FPGAs), designers often face challenges due to limited on-chip memory. Techniques like pruning and quantization reduce network size but often lead to suboptimal designs when transitioning from software frameworks to hardware implementations. A co-design approach using Logic Neural Networks (LNNs) offers an alternative that takes hardware characteristics into account from the outset, replacing conventional neurons with logic gates. However, this approach introduces scalability issues for k-input Boolean functions, with parameter complexity of $\mathcal {O}(2^{2^{k}})$ and high routing overhead, making FPGA implementation both complex and time-consuming. To address these limitations, we propose a novel look-up table (LUT) logic neural network architecture (LLNN), where each neuron is implemented as a LUT encoding a logic function. This architecture leverages the LUT-rich structure of FPGAs, reducing parameter complexity to $\mathcal {O}(2^{k})$ and improving routing efficiency. Our LLNN architectures achieve ultra-low latency—around 2 nanoseconds—on both MNIST and JSC datasets, while maintaining accuracy comparable to state-of-the-art co-designed models. Code available at https://github.com/capo-urjc/llnn
- 9 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 73 (1) , 347-359
Open AccessLLNN: A Scalable LUT-Based Logic Neural Network Architecture for FPGAs
When deploying neural networks for inference on specialized hardware devices such as field-programmable gate arrays (FPGAs), designers often face challenges due to limited on-chip memory. Techniques like pruning and quantization reduce network size but often lead to suboptimal designs when transitioning from software frameworks to hardware implementations. A co-design approach using Logic Neural Networks (LNNs) offers an alternative that takes hardware characteristics into account from the outset, replacing conventional neurons with logic gates. However, this approach introduces scalability issues for k-input Boolean functions, with parameter complexity of $\mathcal {O}(2^{2^{k}})$ and high routing overhead, making FPGA implementation both complex and time-consuming. To address these limitations, we propose a novel look-up table (LUT) logic neural network architecture (LLNN), where each neuron is implemented as a LUT encoding a logic function. This architecture leverages the LUT-rich structure of FPGAs, reducing parameter complexity to $\mathcal {O}(2^{k})$ and improving routing efficiency. Our LLNN architectures achieve ultra-low latency—around 2 nanoseconds—on both MNIST and JSC datasets, while maintaining accuracy comparable to state-of-the-art co-designed models. Code available at https://github.com/capo-urjc/llnn
- Open Access
- 31 July 2025
- Published by Elsevier in Neurocomputing
- Vol. 653
RD-DIP: Rician denoising deep image prior
- 31 July 2025
- Published by Elsevier in Neurocomputing
- Vol. 653
Open AccessRD-DIP: Rician denoising deep image prior
- 17 September 2020
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 18 (3) , 739-750
A non-smooth non-local variational approach to saliency detection in real time
- 17 September 2020
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 18 (3) , 739-750
A non-smooth non-local variational approach to saliency detection in real time
- 11 November 2019
- Published by Taylor & Francis
- p. 309-317
On a Degenerate System in Glaciology Giving Rise to a Free Boundary
The mechanism whereby large ice sheets can surge periodically was recently studied by Fowler and Johnson ([4]) and Fowler ([3]). They proposed a two-dimensional ice sheet simplified model that includes basal ice sliding dependent on the basal water pressure and which consists in the following system: h t − [ ( δ + Q ) S h R + 1 | h x | R − 1 h x ] x = a ( t , x ) Q x − ( δ + Q ) S [ h R + 1 | h x | R + 1 − μ h R | h x | R ξ − 1 2 ] − γ + λ h − 1 ≥ 0 , Q ≥ 0 ( Q x − ( δ + Q ) S [ h R + 1 | h x | R + 1 − μ h R | h x | R ξ − 1 2 ] − γ + λ h − 1 ) Q = 0 ξ x = ( δ + Q ) S h R | h x | R
- 11 November 2019
- Published by Taylor & Francis
- p. 309-317
On a Degenerate System in Glaciology Giving Rise to a Free Boundary
The mechanism whereby large ice sheets can surge periodically was recently studied by Fowler and Johnson ([4]) and Fowler ([3]). They proposed a two-dimensional ice sheet simplified model that includes basal ice sliding dependent on the basal water pressure and which consists in the following system: h t − [ ( δ + Q ) S h R + 1 | h x | R − 1 h x ] x = a ( t , x ) Q x − ( δ + Q ) S [ h R + 1 | h x | R + 1 − μ h R | h x | R ξ − 1 2 ] − γ + λ h − 1 ≥ 0 , Q ≥ 0 ( Q x − ( δ + Q ) S [ h R + 1 | h x | R + 1 − μ h R | h x | R ξ − 1 2 ] − γ + λ h − 1 ) Q = 0 ξ x = ( δ + Q ) S h R | h x | R
- Open Access
Non-convex non-local flows for saliency detection
We propose and numerically solve a new variational model for automatic saliency detection in digital images. Using a non-local framework we consider a family of edge preserving functions combined with a new quadratic saliency detection term. Such term defines a constrained bilateral obstacle problem for image classification driven by p-Laplacian operators, including the so-called hyper-Laplacian case (0 < p < 1). The related non-convex non-local reactive flows are then considered and applied for glioblastoma segmentation in magnetic resonance fluid-attenuated inversion recovery (MRI-Flair) images. A fast convolutional kernel based approximated solution is computed. The numerical experiments show how the non-convexity related to the hyperLaplacian operators provides monotonically better results in terms of the standard metrics.
Open AccessNon-convex non-local flows for saliency detection
We propose and numerically solve a new variational model for automatic saliency detection in digital images. Using a non-local framework we consider a family of edge preserving functions combined with a new quadratic saliency detection term. Such term defines a constrained bilateral obstacle problem for image classification driven by p-Laplacian operators, including the so-called hyper-Laplacian case (0 < p < 1). The related non-convex non-local reactive flows are then considered and applied for glioblastoma segmentation in magnetic resonance fluid-attenuated inversion recovery (MRI-Flair) images. A fast convolutional kernel based approximated solution is computed. The numerical experiments show how the non-convexity related to the hyperLaplacian operators provides monotonically better results in terms of the standard metrics.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 631-634
Optimization of a variational model using deep learning: An application to brain tumor segmentation
We propose a new variational model for saliency detection in images and its application to brain tumor segmentation. By incorporating a saliency term to a classical Total Variation based restoration functional, the new model is able to discriminate what is relevant (salient) from the background. The resulting non-convex and non-smooth problem has a special Difference of Convex structure and it is numerically solved using a proximal point algorithm that involves using a primal-dual method to solve an internal non-smooth sub-problem. We introduce a Deep Learning framework for using available knowledge from a specific application to optimize the parameters of the energy functional. The proposed framework is successfully tested on a database of Magnetic Resonance Images of the brain of patients suffering from a glio-blastoma reaching a Dice Similarity Coefficient of 85,7%.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 631-634
Optimization of a variational model using deep learning: An application to brain tumor segmentation
We propose a new variational model for saliency detection in images and its application to brain tumor segmentation. By incorporating a saliency term to a classical Total Variation based restoration functional, the new model is able to discriminate what is relevant (salient) from the background. The resulting non-convex and non-smooth problem has a special Difference of Convex structure and it is numerically solved using a proximal point algorithm that involves using a primal-dual method to solve an internal non-smooth sub-problem. We introduce a Deep Learning framework for using available knowledge from a specific application to optimize the parameters of the energy functional. The proposed framework is successfully tested on a database of Magnetic Resonance Images of the brain of patients suffering from a glio-blastoma reaching a Dice Similarity Coefficient of 85,7%.
- 1 January 2017
- Published by INSTICC
- p. 100-107
A Non-Local Diffusion Saliency Model for Magnetic Resonance Imaging
- 1 January 2017
- Published by INSTICC
- p. 100-107
A Non-Local Diffusion Saliency Model for Magnetic Resonance Imaging
- Open Access
- 1 January 2017
- Published by INSTICC
- p. 468-475
A Multiclass Anisotropic Mumford-Shah Functional for Segmentation of D-dimensional Vectorial Images
- 1 January 2017
- Published by INSTICC
- p. 468-475
Open AccessA Multiclass Anisotropic Mumford-Shah Functional for Segmentation of D-dimensional Vectorial Images
- 1 December 2016
- Published by Elsevier in Nonlinear Analysis: Real World Applications
- Vol. 32, 74-90
Well-posedness of a nonlinear integro-differential problem and its rearranged formulation
- 1 December 2016
- Published by Elsevier in Nonlinear Analysis: Real World Applications
- Vol. 32, 74-90
Well-posedness of a nonlinear integro-differential problem and its rearranged formulation