Search Results for author: Pier Luigi Dragotti

Found 27 papers, 8 papers with code

Enhanced Event-Based Video Reconstruction with Motion Compensation

no code implementations18 Mar 2024 Siying Liu, Pier Luigi Dragotti

To address this, we propose warping the input intensity frames and sparse codes to enhance reconstruction quality.

Event-Based Video Reconstruction Motion Compensation +1

First-spike coding promotes accurate and efficient spiking neural networks for discrete events with rich temporal structures

1 code implementation Frontiers in Neuroscience 2023 Siying Liu, Vincent C. H. Leung, Pier Luigi Dragotti

In the backpropagation, we develop an error assignment method that propagates error from FS times to spikes through a Gaussian window, and then supervised learning for spikes is implemented through a surrogate gradient approach.

Decision Making

CommIN: Semantic Image Communications as an Inverse Problem with INN-Guided Diffusion Models

no code implementations2 Oct 2023 Jiakang Chen, Di You, Deniz Gündüz, Pier Luigi Dragotti

In this work, we propose CommIN, which views the recovery of high-quality source images from degraded reconstructions as an inverse problem.

INDigo: An INN-Guided Probabilistic Diffusion Algorithm for Inverse Problems

no code implementations5 Jun 2023 Di You, Andreas Floros, Pier Luigi Dragotti

With the help of INN, our algorithm effectively estimates the details lost in the degradation process and is no longer limited by the requirement of knowing the closed-form expression of the degradation model.

Sensing Diversity and Sparsity Models for Event Generation and Video Reconstruction from Events

1 code implementation IEEE Transactions on Pattern Analysis and Machine Intelligence 2023 Siying Liu, Pier Luigi Dragotti

In this paper, we propose a light, simple model-based deep network for E2V reconstruction, explore the diversity for adjacent pixels in V2E generation, and finally build a video-to-events-to-video (V2E2V) architecture to validate how alternative event generation strategies improve video reconstruction.

Event-based vision Video Reconstruction

Learning-Based Reconstruction of FRI Signals

1 code implementation16 Dec 2022 Vincent C. H. Leung, Jun-Jie Huang, Yonina C. Eldar, Pier Luigi Dragotti

While the deep unfolded network achieves similar performance as the classical FRI techniques and outperforms the encoder-decoder network in the low noise regimes, the latter allows to reconstruct the FRI signal even when the sampling kernel is unknown.

Denoising

Generative Joint Source-Channel Coding for Semantic Image Transmission

no code implementations24 Nov 2022 Ecenaz Erdemir, Tze-Yang Tung, Pier Luigi Dragotti, Deniz Gunduz

In GenerativeJSCC, we carry out end-to-end training of an encoder and a StyleGAN-based decoder, and show that GenerativeJSCC significantly outperforms DeepJSCC both in terms of distortion and perceptual quality.

Denoising Generative Adversarial Network

A Fast Automatic Method for Deconvoluting Macro X-ray Fluorescence Data Collected from Easel Paintings

no code implementations31 Oct 2022 Su Yan, Jun-Jie Huang, Herman Verinaz-Jadan, Nathan Daly, Catherine Higgitt, Pier Luigi Dragotti

Macro X-ray Fluorescence (MA-XRF) scanning is increasingly widely used by researchers in heritage science to analyse easel paintings as one of a suite of non-invasive imaging techniques.

FAD

DURRNet: Deep Unfolded Single Image Reflection Removal Network

no code implementations12 Mar 2022 Jun-Jie Huang, Tianrui Liu, Zhixiong Yang, Shaojing Fu, Wentao Zhao, Pier Luigi Dragotti

With the deep unrolling technique, we build the DURRNet with ProxNets to model natural image priors and ProxInvNets which are constructed with invertible networks to impose the exclusion prior.

blind source separation Reflection Removal +1

Active Privacy-Utility Trade-off Against Inference in Time-Series Data Sharing

no code implementations11 Feb 2022 Ecenaz Erdemir, Pier Luigi Dragotti, Deniz Gunduz

For privacy measure, we consider both the probability of correctly detecting the true value of the secret and the mutual information (MI) between the secret and the released data.

Action Detection Activity Detection +2

Mixed X-Ray Image Separation for Artworks with Concealed Designs

no code implementations23 Jan 2022 Wei Pu, Jun-Jie Huang, Barak Sober, Nathan Daly, Catherine Higgitt, Ingrid Daubechies, Pier Luigi Dragotti, Miguel Rodigues

In this paper, we focus on X-ray images of paintings with concealed sub-surface designs (e. g., deriving from reuse of the painting support or revision of a composition by the artist), which include contributions from both the surface painting and the concealed features.

Rolling Shutter Correction

AI-based Reconstruction for Fast MRI -- A Systematic Review and Meta-analysis

no code implementations23 Dec 2021 Yutong Chen, Carola-Bibiane Schönlieb, Pietro Liò, Tim Leiner, Pier Luigi Dragotti, Ge Wang, Daniel Rueckert, David Firmin, Guang Yang

Compressed sensing (CS) has been playing a key role in accelerating the magnetic resonance imaging (MRI) acquisition process.

Light-Field Microscopy for optical imaging of neuronal activity: when model-based methods meet data-driven approaches

no code implementations24 Oct 2021 Pingfan Song, Herman Verinaz Jadan, Carmel L. Howe, Amanda J. Foust, Pier Luigi Dragotti

This paper is devoted to a comprehensive survey to state-of-the-art of computational methods for LFM, with a focus on model-based and data-driven approaches.

WINNet: Wavelet-inspired Invertible Network for Image Denoising

1 code implementation14 Sep 2021 Jun-Jie Huang, Pier Luigi Dragotti

The proposed WINNet consists of K-scale of lifting inspired invertible neural networks (LINNs) and sparsity-driven denoising networks together with a noise estimation network.

Deblurring Image Deblurring +2

LINN: Lifting Inspired Invertible Neural Network for Image Denoising

1 code implementation7 May 2021 Jun-Jie Huang, Pier Luigi Dragotti

In this paper, we propose an invertible neural network for image denoising (DnINN) inspired by the transform-based denoising framework.

Image Denoising

Active Privacy-utility Trade-off Against a Hypothesis Testing Adversary

no code implementations16 Feb 2021 Ecenaz Erdemir, Pier Luigi Dragotti, Deniz Gunduz

We consider a user releasing her data containing some personal information in return of a service.

Reinforcement Learning (RL)

Learning Deep Analysis Dictionaries for Image Super-Resolution

no code implementations31 Jan 2020 Jun-Jie Huang, Pier Luigi Dragotti

Inspired by the recent success of deep neural networks and the recent efforts to develop multi-layer dictionary models, we propose a Deep Analysis dictionary Model (DeepAM) which is optimized to address a specific regression task known as single image super-resolution.

Clustering Image Super-Resolution +1

Learning Deep Analysis Dictionaries -- Part II: Convolutional Dictionaries

no code implementations31 Jan 2020 Jun-Jie Huang, Pier Luigi Dragotti

By exploiting the properties of a convolutional dictionary, we present an efficient convolutional analysis dictionary learning approach.

Clustering Dictionary Learning +1

Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion

no code implementations9 Oct 2019 Xin Deng, Pier Luigi Dragotti

In this paper, we propose a novel deep convolutional neural network to solve the general multi-modal image restoration (MIR) and multi-modal image fusion (MIF) problems.

Image Denoising Image Reconstruction +3

Privacy-Aware Location Sharing with Deep Reinforcement Learning

no code implementations17 Jul 2019 Ecenaz Erdemir, Pier Luigi Dragotti, Deniz Gunduz

Existing approaches are mainly focused on privacy of sharing a single location or myopic location trace privacy; neither of them taking into account the temporal correlations between the past and current locations.

Information Theory Cryptography and Security Information Theory

Reconstructing Classes of Non-bandlimited Signals from Time Encoded Information

1 code implementation8 May 2019 Roxana Alexandru, Pier Luigi Dragotti

We investigate time encoding as an alternative method to classical sampling, and address the problem of reconstructing non-bandlimited signals from time-based samples.

Signal Processing

Multimodal Image Super-resolution via Joint Sparse Representations induced by Coupled Dictionaries

1 code implementation25 Sep 2017 Pingfan Song, Xin Deng, João F. C. Mota, Nikos Deligiannis, Pier Luigi Dragotti, Miguel R. D. Rodrigues

This paper proposes a new approach to construct a high-resolution (HR) version of a low-resolution (LR) image given another HR image modality as reference, based on joint sparse representations induced by coupled dictionaries.

Dictionary Learning Image Super-Resolution

Deep De-Aliasing for Fast Compressive Sensing MRI

no code implementations19 May 2017 Simiao Yu, Hao Dong, Guang Yang, Greg Slabaugh, Pier Luigi Dragotti, Xujiong Ye, Fangde Liu, Simon Arridge, Jennifer Keegan, David Firmin, Yike Guo

Fast Magnetic Resonance Imaging (MRI) is highly in demand for many clinical applications in order to reduce the scanning cost and improve the patient experience.

Compressive Sensing De-aliasing +1

Cannot find the paper you are looking for? You can Submit a new open access paper.