Highly Corrupted Image Inpainting Through Hypoelliptic Diffusion

Detalhes bibliográficos
Autor(a) principal: Ugo V. Boscain
Data de Publicação: 2018
Outros Autores: Roman Chertovskih, Jean-Paul Gauthier, Dario Prandi, Alexey Remizov
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: https://hdl.handle.net/10216/111681
Resumo: We present a new biomimetic image inpainting algorithm, the Averaging and Hypoelliptic Evolution (AHE) algorithm, inspired by the one presented in Boscain et al. (SIAM J. Imaging Sci. 7(2):669-695, 2014) and based upon a semi-discrete variation of the Citti-Petitot-Sarti model of the primary visual cortex V1. The AHE algorithm is based on a suitable combination of sub-Riemannian hypoelliptic diffusion and ad hoc local averaging techniques. In particular, we focus on highly corrupted images (i.e., where more than the 80% of the image is missing), for which we obtain high-quality reconstructions.
id RCAP_f1761614125053aacfd61d5935a5d8e5
oai_identifier_str oai:repositorio-aberto.up.pt:10216/111681
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Highly Corrupted Image Inpainting Through Hypoelliptic DiffusionWe present a new biomimetic image inpainting algorithm, the Averaging and Hypoelliptic Evolution (AHE) algorithm, inspired by the one presented in Boscain et al. (SIAM J. Imaging Sci. 7(2):669-695, 2014) and based upon a semi-discrete variation of the Citti-Petitot-Sarti model of the primary visual cortex V1. The AHE algorithm is based on a suitable combination of sub-Riemannian hypoelliptic diffusion and ad hoc local averaging techniques. In particular, we focus on highly corrupted images (i.e., where more than the 80% of the image is missing), for which we obtain high-quality reconstructions.20182018-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/10216/111681eng0924-990710.1007/s10851-018-0810-4Ugo V. BoscainRoman ChertovskihJean-Paul GauthierDario PrandiAlexey Remizovinfo: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:RCAAP2023-11-29T13:58:54Zoai:repositorio-aberto.up.pt:10216/111681Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T23:51:30.436878Repositório 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 Highly Corrupted Image Inpainting Through Hypoelliptic Diffusion
title Highly Corrupted Image Inpainting Through Hypoelliptic Diffusion
spellingShingle Highly Corrupted Image Inpainting Through Hypoelliptic Diffusion
Ugo V. Boscain
title_short Highly Corrupted Image Inpainting Through Hypoelliptic Diffusion
title_full Highly Corrupted Image Inpainting Through Hypoelliptic Diffusion
title_fullStr Highly Corrupted Image Inpainting Through Hypoelliptic Diffusion
title_full_unstemmed Highly Corrupted Image Inpainting Through Hypoelliptic Diffusion
title_sort Highly Corrupted Image Inpainting Through Hypoelliptic Diffusion
author Ugo V. Boscain
author_facet Ugo V. Boscain
Roman Chertovskih
Jean-Paul Gauthier
Dario Prandi
Alexey Remizov
author_role author
author2 Roman Chertovskih
Jean-Paul Gauthier
Dario Prandi
Alexey Remizov
author2_role author
author
author
author
dc.contributor.author.fl_str_mv Ugo V. Boscain
Roman Chertovskih
Jean-Paul Gauthier
Dario Prandi
Alexey Remizov
description We present a new biomimetic image inpainting algorithm, the Averaging and Hypoelliptic Evolution (AHE) algorithm, inspired by the one presented in Boscain et al. (SIAM J. Imaging Sci. 7(2):669-695, 2014) and based upon a semi-discrete variation of the Citti-Petitot-Sarti model of the primary visual cortex V1. The AHE algorithm is based on a suitable combination of sub-Riemannian hypoelliptic diffusion and ad hoc local averaging techniques. In particular, we focus on highly corrupted images (i.e., where more than the 80% of the image is missing), for which we obtain high-quality reconstructions.
publishDate 2018
dc.date.none.fl_str_mv 2018
2018-01-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/10216/111681
url https://hdl.handle.net/10216/111681
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 0924-9907
10.1007/s10851-018-0810-4
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_ 1799135834682687488

Registros relacionados