Search Results for author: Jesús Malo

Found 11 papers, 2 papers with code

Orthonormal Convolutions for the Rotation Based Iterative Gaussianization

no code implementations8 Jun 2022 Valero Laparra, Alexander Hepburn, J. Emmanuel Johnson, Jesús Malo

Here we present the \emph{Convolutional RBIG}: an extension that alleviates this issue by imposing that the rotation in RBIG is a convolution.

Texture Synthesis

Neural Networks with Divisive normalization for image segmentation with application in cityscapes dataset

no code implementations25 Mar 2022 Pablo Hernández-Cámara, Valero Laparra, Jesús Malo

In addition to the results on the Cityscapes and Foggy Cityscapes datasets, we explain these advantages through visualization of the responses: the equalization induced by the divisive normalization leads to more invariant features to local changes in contrast and illumination.

Image Segmentation Semantic Segmentation

On the relation between statistical learning and perceptual distances

no code implementations ICLR 2022 Alexander Hepburn, Valero Laparra, Raul Santos-Rodriguez, Johannes Ballé, Jesús Malo

Since machine learning relies on the statistics of training data as well, the above connection has interesting implications when using perceptual distances (which mimic the behavior of the human visual system) as a loss function.

BIG-bench Machine Learning Perceptual Distance

Information Theory in Density Destructors

2 code implementations2 Dec 2020 J. Emmanuel Johnson, Valero Laparra, Gustau Camps-Valls, Raul Santos-Rodríguez, Jesús Malo

Density destructors are differentiable and invertible transforms that map multivariate PDFs of arbitrary structure (low entropy) into non-structured PDFs (maximum entropy).

Synthesizing Visual Illusions Using Generative Adversarial Networks

no code implementations21 Nov 2019 Alexander Gomez-Villa, Adrian Martín, Javier Vazquez-Corral, Jesús Malo, Marcelo Bertalmío

Visual illusions are a very useful tool for vision scientists, because they allow them to better probe the limits, thresholds and errors of the visual system.

PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance

no code implementations28 Oct 2019 Alexander Hepburn, Valero Laparra, Jesús Malo, Ryan McConville, Raul Santos-Rodriguez

Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations.

Perceptual Distance

Nonlinearities and Adaptation of Color Vision from Sequential Principal Curves Analysis

no code implementations31 Jan 2016 Valero Laparra, Sandra Jiménez, Gustavo Camps-Valls, Jesús Malo

Here we address the simultaneous statistical explanation of (i) the nonlinear behavior of achromatic and chromatic mechanisms in a fixed adaptation state, and (ii) the change of such behavior.

Iterative Gaussianization: from ICA to Random Rotations

7 code implementations IEEE Transactions on Neural Networks 2011 Valero Laparra, Gustavo Camps-Valls, Jesús Malo

The practical performance of RBIG is successfully illustrated in a number of multidimensional problems such as image synthesis, classification, denoising, and multi-information estimation.

Denoising Image Generation

Image Denoising with Kernels based on Natural Image Relations

no code implementations31 Jan 2016 Valero Laparra, Juan Gutiérrez, Gustavo Camps-Valls, Jesús Malo

In this paper, we propose an alternative non-explicit way to take into account the relations among natural image wavelet coefficients for denoising: we use support vector regression (SVR) in the wavelet domain to enforce these relations in the estimated signal.

Image Denoising

On the Suitable Domain for SVM Training in Image Coding

no code implementations18 Oct 2013 Gustavo Camps-Valls, Juan Gutiérrez, Gabriel Gómez-Pérez, Jesús Malo

We analytically demonstrate that no linear domain fulfills this condition because of the statistical and perceptual inter-coefficient relations that exist in these domains.

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