G
Giovanni Chierchia
Researcher at ESIEE Paris
Publications - 69
Citations - 1323
Giovanni Chierchia is an academic researcher from ESIEE Paris. The author has contributed to research in topics: Convex optimization & Deep learning. The author has an hindex of 14, co-authored 63 publications receiving 961 citations. Previous affiliations of Giovanni Chierchia include Centre national de la recherche scientifique & University of Marne-la-Vallée.
Papers
More filters
Proceedings ArticleDOI
SAR image despeckling through convolutional neural networks
TL;DR: In this article, the authors investigated the use of discriminative model learning through Convolutional Neural Networks (CNNs) for SAR image despeckling, which uses a residual learning strategy, hence it does not recover the filtered image, but the speckle component, which is then subtracted from the noisy one.
Journal ArticleDOI
A Bayesian-MRF Approach for PRNU-Based Image Forgery Detection
TL;DR: Large-scale experiments on simulated and real forgeries show that the proposed technique largely improves upon the current state of the art, and that it can be applied with success to a wide range of practical situations.
Journal ArticleDOI
Epigraphical projection and proximal tools for solving constrained convex optimization problems
TL;DR: In this article, a proximal approach is proposed to deal with a class of convex variational problems involving nonlinear constraints, which can be expressed as the lower-level set of a sum of a convex functions evaluated over different blocks of the linearly transformed signal.
Journal ArticleDOI
A nonlocal structure tensor-based approach for multicomponent image recovery problems
TL;DR: The results demonstrate the interest of introducing a nonlocal ST regularization and show that the proposed approach leads to significant improvements in terms of convergence speed over current state-of-the-art methods, such as the alternating direction method of multipliers.
Proceedings ArticleDOI
On the influence of denoising in PRNU based forgery detection
TL;DR: This work analyzes the influence of denoising on the overall performance of the PRNU-based forgery detection method and shows that the use of a suitable state-of-the art Denoising technique improves performance appreciably w.r.t. the original algorithm.