G
Giovanni Poggi
Researcher at University of Naples Federico II
Publications - 13
Citations - 180
Giovanni Poggi is an academic researcher from University of Naples Federico II. The author has contributed to research in topics: Image processing & Synthetic aperture radar. The author has an hindex of 3, co-authored 13 publications receiving 27 citations. Previous affiliations of Giovanni Poggi include German Aerospace Center & Aeronáutica.
Papers
More filters
Proceedings ArticleDOI
Are GAN Generated Images Easy to Detect? A Critical Analysis of the State-Of-The-Art
TL;DR: This work analyzes the state-of-the-art methods for the detection of synthetic images, highlighting the key ingredients of the most successful approaches, and comparing their performance over existing generative architectures.
Journal ArticleDOI
Deep Learning Methods For Synthetic Aperture Radar Image Despeckling: An Overview Of Trends And Perspectives
Giulia Fracastoro,Enrico Magli,Giovanni Poggi,Giuseppe Scarpa,Diego Valsesia,Luisa Verdoliva +5 more
TL;DR: In this paper, a survey of deep learning methods applied to SAR despeckling is presented, with the objective of identifying the most promising lines and identifying the factors that have limited the success of deep models.
Journal ArticleDOI
Combining PRNU and noiseprint for robust and efficient device source identification
TL;DR: In this article, the authors leverage the image noiseprint, a recently proposed camera-model fingerprint that has proved effective for several forensic tasks, to boost the performance of PRNU-based analyses in challenging conditions involving low quality and quantity of data.
Journal ArticleDOI
Deep Learning Methods For Synthetic Aperture Radar Image Despeckling: An Overview Of Trends And Perspectives
Giulia Fracastoro,Enrico Magli,Giovanni Poggi,Giuseppe Scarpa,Diego Valsesia,Luisa Verdoliva +5 more
TL;DR: In this article, the authors provide a critical analysis of existing methods with the objective to recognize the most promising lines, identify the factors that have limited the success of deep learning for SAR despeckling, and propose ways forward in an attempt to fully exploit the potential of DNN for SAR.
Posted Content
Combining PRNU and noiseprint for robust and efficient device source identification
TL;DR: This work proposes to leverage the image noiseprint, a recently proposed camera-model fingerprint that has proved effective for several forensic tasks, to boost the performance of PRNU-based analyses in challenging conditions involving low quality and quantity of data.