Cargando…

On the synthesis of visual illusions using deep generative models

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 c...

Descripción completa

Detalles Bibliográficos
Autores principales: Gomez-Villa, Alex, Martín, Adrián, Vazquez-Corral, Javier, Bertalmío, Marcelo, Malo, Jesús
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Association for Research in Vision and Ophthalmology 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9290318/
https://www.ncbi.nlm.nih.gov/pubmed/35833884
http://dx.doi.org/10.1167/jov.22.8.2
_version_ 1784748871425982464
author Gomez-Villa, Alex
Martín, Adrián
Vazquez-Corral, Javier
Bertalmío, Marcelo
Malo, Jesús
author_facet Gomez-Villa, Alex
Martín, Adrián
Vazquez-Corral, Javier
Bertalmío, Marcelo
Malo, Jesús
author_sort Gomez-Villa, Alex
collection PubMed
description 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.
format Online
Article
Text
id pubmed-9290318
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher The Association for Research in Vision and Ophthalmology
record_format MEDLINE/PubMed
spelling pubmed-92903182022-07-19 On the synthesis of visual illusions using deep generative models Gomez-Villa, Alex Martín, Adrián Vazquez-Corral, Javier Bertalmío, Marcelo Malo, Jesús J Vis Article 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. The Association for Research in Vision and Ophthalmology 2022-07-14 /pmc/articles/PMC9290318/ /pubmed/35833884 http://dx.doi.org/10.1167/jov.22.8.2 Text en Copyright 2022 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
spellingShingle Article
Gomez-Villa, Alex
Martín, Adrián
Vazquez-Corral, Javier
Bertalmío, Marcelo
Malo, Jesús
On the synthesis of visual illusions using deep generative models
title On the synthesis of visual illusions using deep generative models
title_full On the synthesis of visual illusions using deep generative models
title_fullStr On the synthesis of visual illusions using deep generative models
title_full_unstemmed On the synthesis of visual illusions using deep generative models
title_short On the synthesis of visual illusions using deep generative models
title_sort on the synthesis of visual illusions using deep generative models
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9290318/
https://www.ncbi.nlm.nih.gov/pubmed/35833884
http://dx.doi.org/10.1167/jov.22.8.2
work_keys_str_mv AT gomezvillaalex onthesynthesisofvisualillusionsusingdeepgenerativemodels
AT martinadrian onthesynthesisofvisualillusionsusingdeepgenerativemodels
AT vazquezcorraljavier onthesynthesisofvisualillusionsusingdeepgenerativemodels
AT bertalmiomarcelo onthesynthesisofvisualillusionsusingdeepgenerativemodels
AT malojesus onthesynthesisofvisualillusionsusingdeepgenerativemodels