1 code implementation • 22 Nov 2023 • Matías Tailanian, Marina Gardella, Álvaro Pardo, Pablo Musé
We show that diffusion purification methods are well suited for counter-forensics tasks.
1 code implementation • 5 Aug 2023 • Guillermo Carbajal, Patricia Vitoria, José Lezama, Pablo Musé
Then, a second network trained jointly with the first one, unrolls a non-blind deconvolution method using the motion kernel field estimated by the first network.
1 code implementation • 22 Nov 2022 • Matías Tailanian, Álvaro Pardo, Pablo Musé
In this work we propose a non-contrastive method for anomaly detection and segmentation in images, that benefits both from a modern machine learning approach and a more classic statistical detection theory.
1 code implementation • 26 Sep 2022 • Guillermo Carbajal, Patricia Vitoria, Pablo Musé, José Lezama
Successful training of end-to-end deep networks for real motion deblurring requires datasets of sharp/blurred image pairs that are realistic and diverse enough to achieve generalization to real blurred images.
no code implementations • 3 May 2022 • Matías Tailanian, Pablo Musé, Álvaro Pardo
In this work we propose an a contrario framework to detect anomalies in images applying statistical analysis to feature maps obtained via convolutions.
no code implementations • 5 Oct 2021 • Matias Tailanian, Pablo Musé, Álvaro Pardo
In this work we propose an a contrario framework to detect anomalies in images applying statistical analysis to feature maps obtained via convolutions.
1 code implementation • 1 Feb 2021 • Guillermo Carbajal, Patricia Vitoria, Mauricio Delbracio, Pablo Musé, José Lezama
In recent years, the removal of motion blur in photographs has seen impressive progress in the hands of deep learning-based methods, trained to map directly from blurry to sharp images.
1 code implementation • 14 Nov 2019 • Mario González, Andrés Almansa, Mauricio Delbracio, Pablo Musé, Pauline Tan
In this paper we address the problem of solving ill-posed inverse problems in imaging where the prior is a neural generative model.
1 code implementation • 5 Dec 2017 • José Lezama, Qiang Qiu, Pablo Musé, Guillermo Sapiro
Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification.
no code implementations • 10 Jun 2017 • Cecilia Aguerrebere, Andrés Almansa, Julie Delon, Yann Gousseau, Pablo Musé
In this work, we propose the use of a hyperprior to model image patches, in order to stabilize the estimation procedure.
no code implementations • NeurIPS 2013 • Marcelo Fiori, Pablo Sprechmann, Joshua Vogelstein, Pablo Musé, Guillermo Sapiro
We also present results on multimodal graphs and applications to collaborative inference of brain connectivity from alignment-free functional magnetic resonance imaging (fMRI) data.
no code implementations • NeurIPS 2012 • Marcelo Fiori, Pablo Musé, Guillermo Sapiro
Graphical models are a very useful tool to describe and understand natural phenomena, from gene expression to climate change and social interactions.