no code implementations • 30 Apr 2024 • Diangarti Tariang, Riccardo Corvi, Davide Cozzolino, Giovanni Poggi, Koki Nagano, Luisa Verdoliva
In this work we present an overview of approaches for the detection and attribution of synthetic images and highlight their strengths and weaknesses.
no code implementations • 30 Nov 2023 • Davide Cozzolino, Giovanni Poggi, Riccardo Corvi, Matthias Nießner, Luisa Verdoliva
The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images.
1 code implementation • 14 Sep 2023 • Giada Zingarini, Davide Cozzolino, Riccardo Corvi, Giovanni Poggi, Luisa Verdoliva
Here, we investigate this issue and propose M3Dsynth, a large dataset of manipulated Computed Tomography (CT) lung images.
no code implementations • 27 Jul 2023 • Matteo Ciotola, Mario Ragosta, Giovanni Poggi, Giuseppe Scarpa
This work presents a new unsupervised framework for training deep learning models for super-resolution of Sentinel-2 images by fusion of its 10-m and 20-m bands.
1 code implementation • 26 Jul 2023 • Matteo Ciotola, Giovanni Poggi, Giuseppe Scarpa
In latest years, deep learning has gained a leading role in the pansharpening of multiresolution images.
Ranked #1 on Pansharpening on GeoEye-1 PairMax
no code implementations • 13 Apr 2023 • Riccardo Corvi, Davide Cozzolino, Giovanni Poggi, Koki Nagano, Luisa Verdoliva
Detecting fake images is becoming a major goal of computer vision.
1 code implementation • 1 Nov 2022 • Riccardo Corvi, Davide Cozzolino, Giada Zingarini, Giovanni Poggi, Koki Nagano, Luisa Verdoliva
Over the past decade, there has been tremendous progress in creating synthetic media, mainly thanks to the development of powerful methods based on generative adversarial networks (GAN).
no code implementations • 28 Sep 2022 • Alessandro Pianese, Davide Cozzolino, Giovanni Poggi, Luisa Verdoliva
Thanks to recent advances in deep learning, sophisticated generation tools exist, nowadays, that produce extremely realistic synthetic speech.
no code implementations • 23 Dec 2021 • Davide Cozzolino, Diego Gragnaniello, Giovanni Poggi, Luisa Verdoliva
The ever higher quality and wide diffusion of fake images have spawn a quest for reliable forensic tools.
2 code implementations • 16 Nov 2021 • Matteo Ciotola, Sergio Vitale, Antonio Mazza, Giovanni Poggi, Giuseppe Scarpa
A further problem is the scarcity of training data, which causes a limited generalization ability and a poor performance on off-training test images.
1 code implementation • 6 Apr 2021 • Diego Gragnaniello, Davide Cozzolino, Francesco Marra, Giovanni Poggi, Luisa Verdoliva
The advent of deep learning has brought a significant improvement in the quality of generated media.
no code implementations • 10 Dec 2020 • Giulia Fracastoro, Enrico Magli, Giovanni Poggi, Giuseppe Scarpa, Diego Valsesia, Luisa Verdoliva
Synthetic aperture radar (SAR) images are affected by a spatially-correlated and signal-dependent noise called speckle, which is very severe and may hinder image exploitation.
no code implementations • 31 Oct 2020 • Michela Gravina, Diego Gragnaniello, Luisa Verdoliva, Giovanni Poggi, Iuri Corsini, Carlo Dani, Fabio Meneghin, Gianluca Lista, Salvatore Aversa, Francesco Raimondi, Fiorella Migliaro, Carlo Sansone
Lung ultrasound imaging is reaching growing interest from the scientific community.
no code implementations • 17 Jan 2020 • Davide Cozzolino, Francesco Marra, Diego Gragnaniello, Giovanni Poggi, Luisa Verdoliva
PRNU-based image processing is a key asset in digital multimedia forensics.
1 code implementation • 15 Sep 2019 • Francesco Marra, Diego Gragnaniello, Luisa Verdoliva, Giovanni Poggi
Due to limited computational and memory resources, current deep learning models accept only rather small images in input, calling for preliminary image resizing.
1 code implementation • 20 Feb 2019 • Diego Gragnaniello, Francesco Marra, Giovanni Poggi, Luisa Verdoliva
Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training.
no code implementations • 31 Dec 2018 • Francesco Marra, Diego Gragnaniello, Luisa Verdoliva, Giovanni Poggi
In the last few years, generative adversarial networks (GAN) have shown tremendous potential for a number of applications in computer vision and related fields.
1 code implementation • 28 Nov 2018 • Sergio Vitale, Davide Cozzolino, Giuseppe Scarpa, Luisa Verdoliva, Giovanni Poggi
We propose a new method for SAR image despeckling which leverages information drawn from co-registered optical imagery.
no code implementations • 25 Aug 2018 • Diego Gragnaniello, Francesco Marra, Giovanni Poggi, Luisa Verdoliva
With the ubiquitous diffusion of social networks, images are becoming a dominant and powerful communication channel.
no code implementations • 29 Aug 2017 • Dario D'Avino, Davide Cozzolino, Giovanni Poggi, Luisa Verdoliva
Video forgery detection is becoming an important issue in recent years, because modern editing software provide powerful and easy-to-use tools to manipulate videos.
no code implementations • 14 Mar 2017 • Davide Cozzolino, Giovanni Poggi, Luisa Verdoliva
Local descriptors based on the image noise residual have proven extremely effective for a number of forensic applications, like forgery detection and localization.
no code implementations • 14 Mar 2017 • Luca D'Amiano, Davide Cozzolino, Giovanni Poggi, Luisa Verdoliva
We propose a new algorithm for the reliable detection and localization of video copy-move forgeries.
no code implementations • 11 Sep 2015 • Luisa Verdoliva, Davide Cozzolino, Giovanni Poggi
We propose a new algorithm for fast approximate nearest neighbor search based on the properties of ordered vectors.
no code implementations • 1 Aug 2015 • Marco Castelluccio, Giovanni Poggi, Carlo Sansone, Luisa Verdoliva
We explore the use of convolutional neural networks for the semantic classification of remote sensing scenes.