On the synthesis of visual illusions using deep generative models
Gómez Villa, Alexandra (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Martín, A. (Universitat Pompeu Fabra)
Vazquez-Corral, Javier (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Bertalmío, Marcelo (Instituto de Óptica)
Malo, J. (Universitat de València)

Date:	2022
Abstract:	Visual illusions expand our understanding of the visual system by imposing constraints in the models in two different ways: i) visual illusions for humans should induce equivalent illusions in the model, and ii) illusions synthesized from the model should be compelling for human viewers too. These constraints are alternative strategies to find good vision models. Following the first research strategy, recent studies have shown that artificial neural network architectures also have human-like illusory percepts when stimulated with classical hand-crafted stimuli designed to fool humans. In this work we focus on the second (less explored) strategy: we propose a framework to synthesize new visual illusions using the optimization abilities of current automatic differentiation techniques. The proposed framework can be used with classical vision models as well as with more recent artificial neural network architectures. This framework, validated by psychophysical experiments, can be used to study the difference between a vision model and the actual human perception and to optimize the vision model to decrease this difference.
Rights:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Language:	Anglès
Document:	Article ; recerca ; Versió publicada
Published in:	Journal of Vision, Vol. 22 Núm. 8 (july 2022) , ISSN 1534-7362

DOI: 10.1167/jov.22.8.2
PMID: 35833884

18 p, 1.6 MB

The record appears in these collections:
Articles > Research articles
Articles > Published articles