42 citations · 70 across the 10 of their papers we have counts for
14 papers
A Perceptually Inspired Variational Framework for Color Enhancement
Rodrigo Palma-Amestoy, Edoardo Provenzi, Marcelo Bertalmío +1
Basic phenomenology of human color vision has been widely taken as an inspiration to devise explicit color correction algorithms. The behavior of these models in terms of significa…
Contrast Sensitivity Functions in Autoencoders
Qiang Li, Alex Gomez-Villa, Marcelo Bertalmio +1
Three decades ago, Atick et al. suggested that human frequency sensitivity may emerge from the enhancement required for a more efficient analysis of retinal images. Here we reasses…
Visual Illusions Also Deceive Convolutional Neural Networks: Analysis and Implications
A. Gomez-Villa, A. Martín, J. Vazquez-Corral +2
Visual illusions allow researchers to devise and test new models of visual perception. Here we show that artificial neural networks trained for basic visual tasks in natural images…
Synthesizing Visual Illusions Using Generative Adversarial Networks
Alexander Gomez-Villa, Adrian Martín, Javier Vazquez-Corral +2
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. In this work we intro…
Cortical-inspired Wilson-Cowan-type equations for orientation-dependent contrast perception modelling
Marcelo Bertalmío, Luca Calatroni, Valentina Franceschi +2
We consider the evolution model proposed in [9, 6] to describe illusory contrast perception phenomena induced by surrounding orientations. Firstly, we highlight its analogies and d…
Visual Information flow in Wilson-Cowan networks
Alexander Gomez-Villa, Marcelo Bertalmío, Jesús Malo
In this work we study the communication efficiency of a psychophysically-tuned cascade of Wilson-Cowan and Divisive Normalization layers that simulate the retina-V1 pathway. This i…