Construção de modelos neurais para criação de arte generativa visual
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://hdl.handle.net/10216/114370 |
Resumo: | The emergence of the generative adversarial networks (GANs) in 2014 allowed the development of neural models that effectively solve computer vision problems such as generation of photorealistic images, image-image translation and super-resolution. Several computer artists have been creatively exploring these generative models and presenting very different results, mainly in the visual field. However, the potential of applying these models in generative art is hampered by problems such as incapacity of element-based generation, low resolution and predictability of results. In the present work are presented two adversarial models, AGAN and bezierGAN that partially counter these problems. The AGAN is an adversarial model with two discriminators, which allows the generation of images with different distributions of the training images, reducing the degree of predictability of the results. The results obtained show that the images generated by the model are abstractions of the training images, and the intensity of these abstractions is controllable. The bezierGAN model is an adversarial generative model for the generation of vectorized images based on bézier curves, which capture the distributions of training bitmap images. The results show that the model can only capture simpler image distributions, failing in complex images. However the great potential of the model is the creation of a latent space for images based on elements, allowing the creation of videos and minimalistic images with organic distributions in any resolution. |
id |
RCAP_588d55df81926fca8d2237bb6a0d9fe4 |
---|---|
oai_identifier_str |
oai:repositorio-aberto.up.pt:10216/114370 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Construção de modelos neurais para criação de arte generativa visualOutras ciências da engenharia e tecnologiasOther engineering and technologiesThe emergence of the generative adversarial networks (GANs) in 2014 allowed the development of neural models that effectively solve computer vision problems such as generation of photorealistic images, image-image translation and super-resolution. Several computer artists have been creatively exploring these generative models and presenting very different results, mainly in the visual field. However, the potential of applying these models in generative art is hampered by problems such as incapacity of element-based generation, low resolution and predictability of results. In the present work are presented two adversarial models, AGAN and bezierGAN that partially counter these problems. The AGAN is an adversarial model with two discriminators, which allows the generation of images with different distributions of the training images, reducing the degree of predictability of the results. The results obtained show that the images generated by the model are abstractions of the training images, and the intensity of these abstractions is controllable. The bezierGAN model is an adversarial generative model for the generation of vectorized images based on bézier curves, which capture the distributions of training bitmap images. The results show that the model can only capture simpler image distributions, failing in complex images. However the great potential of the model is the creation of a latent space for images based on elements, allowing the creation of videos and minimalistic images with organic distributions in any resolution.2018-07-182018-07-18T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/10216/114370TID:202113566porDaniel Leal Moreira Machadoinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-29T14:18:35Zoai:repositorio-aberto.up.pt:10216/114370Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T23:58:36.760635Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Construção de modelos neurais para criação de arte generativa visual |
title |
Construção de modelos neurais para criação de arte generativa visual |
spellingShingle |
Construção de modelos neurais para criação de arte generativa visual Daniel Leal Moreira Machado Outras ciências da engenharia e tecnologias Other engineering and technologies |
title_short |
Construção de modelos neurais para criação de arte generativa visual |
title_full |
Construção de modelos neurais para criação de arte generativa visual |
title_fullStr |
Construção de modelos neurais para criação de arte generativa visual |
title_full_unstemmed |
Construção de modelos neurais para criação de arte generativa visual |
title_sort |
Construção de modelos neurais para criação de arte generativa visual |
author |
Daniel Leal Moreira Machado |
author_facet |
Daniel Leal Moreira Machado |
author_role |
author |
dc.contributor.author.fl_str_mv |
Daniel Leal Moreira Machado |
dc.subject.por.fl_str_mv |
Outras ciências da engenharia e tecnologias Other engineering and technologies |
topic |
Outras ciências da engenharia e tecnologias Other engineering and technologies |
description |
The emergence of the generative adversarial networks (GANs) in 2014 allowed the development of neural models that effectively solve computer vision problems such as generation of photorealistic images, image-image translation and super-resolution. Several computer artists have been creatively exploring these generative models and presenting very different results, mainly in the visual field. However, the potential of applying these models in generative art is hampered by problems such as incapacity of element-based generation, low resolution and predictability of results. In the present work are presented two adversarial models, AGAN and bezierGAN that partially counter these problems. The AGAN is an adversarial model with two discriminators, which allows the generation of images with different distributions of the training images, reducing the degree of predictability of the results. The results obtained show that the images generated by the model are abstractions of the training images, and the intensity of these abstractions is controllable. The bezierGAN model is an adversarial generative model for the generation of vectorized images based on bézier curves, which capture the distributions of training bitmap images. The results show that the model can only capture simpler image distributions, failing in complex images. However the great potential of the model is the creation of a latent space for images based on elements, allowing the creation of videos and minimalistic images with organic distributions in any resolution. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-07-18 2018-07-18T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://hdl.handle.net/10216/114370 TID:202113566 |
url |
https://hdl.handle.net/10216/114370 |
identifier_str_mv |
TID:202113566 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799135908588421120 |