SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings

Autores
Navarro, Jose Pablo; Orlando, José Ignacio; Delrieux, Claudio Augusto; Iarussi, Emmanuel
Año de publicación
2021
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Finding point-wise correspondences between images is a long-standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport changes. In this paper, we present the first attempt to obtain a learned descriptor for dense registration in line drawings. Based on recent deep learning techniques for corresponding photographs, we designed descriptors to locally match image pairs where the object of interest belongs to the same semantic category, yet still differ drastically in shape, form, and projection angle. To this end, we have specifically crafted a data set of synthetic sketches using non-photorealistic rendering over a large collection of part-based registered 3D models. After training, a neural network generates descriptors for every pixel in an input image, which are shown togeneralize correctly in unseen sketches hand-drawn by humans. We evaluate our method against a baseline of correspondences data collected from expert designers, in addition to comparisons with other descriptors that have been proven effective in sketches. Code, data and further resources will be publicly released by the time of publication.
Fil: Navarro, Jose Pablo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina. Universidad Nacional de la Patagonia "San Juan Bosco". Facultad de Ingeniería - Sede Puerto Madryn. Departamento de Informática; Argentina
Fil: Orlando, José Ignacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil; Argentina. Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ciencias Exactas. Grupo de Plasmas Densos Magnetizados. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Grupo de Plasmas Densos Magnetizados; Argentina
Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina
Fil: Iarussi, Emmanuel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires; Argentina
Materia
2D MORPHING
IMAGE AND VIDEO PROCESSING
IMAGE AND VIDEO PROCESSING
IMAGE AND VIDEO PROCESSING
IMAGE DATABASES
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/135664
Acceder
id CONICETDig_4b310a641453ebe3a1485d0444f6db4c
oai_identifier_str oai:ri.conicet.gov.ar:11336/135664
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling SketchZooms: Deep Multi-view Descriptors for Matching Line DrawingsNavarro, Jose PabloOrlando, José IgnacioDelrieux, Claudio AugustoIarussi, Emmanuel2D MORPHINGIMAGE AND VIDEO PROCESSINGIMAGE AND VIDEO PROCESSINGIMAGE AND VIDEO PROCESSINGIMAGE DATABASEShttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Finding point-wise correspondences between images is a long-standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport changes. In this paper, we present the first attempt to obtain a learned descriptor for dense registration in line drawings. Based on recent deep learning techniques for corresponding photographs, we designed descriptors to locally match image pairs where the object of interest belongs to the same semantic category, yet still differ drastically in shape, form, and projection angle. To this end, we have specifically crafted a data set of synthetic sketches using non-photorealistic rendering over a large collection of part-based registered 3D models. After training, a neural network generates descriptors for every pixel in an input image, which are shown togeneralize correctly in unseen sketches hand-drawn by humans. We evaluate our method against a baseline of correspondences data collected from expert designers, in addition to comparisons with other descriptors that have been proven effective in sketches. Code, data and further resources will be publicly released by the time of publication.Fil: Navarro, Jose Pablo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina. Universidad Nacional de la Patagonia "San Juan Bosco". Facultad de Ingeniería - Sede Puerto Madryn. Departamento de Informática; ArgentinaFil: Orlando, José Ignacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil; Argentina. Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ciencias Exactas. Grupo de Plasmas Densos Magnetizados. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Grupo de Plasmas Densos Magnetizados; ArgentinaFil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; ArgentinaFil: Iarussi, Emmanuel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires; ArgentinaWiley Blackwell Publishing, Inc2021-02info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/135664Navarro, Jose Pablo; Orlando, José Ignacio; Delrieux, Claudio Augusto; Iarussi, Emmanuel; SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings; Wiley Blackwell Publishing, Inc; Computer Graphics Forum; 40; 1; 2-2021; 410-4230167-7055CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://onlinelibrary.wiley.com/doi/10.1111/cgf.14197info:eu-repo/semantics/altIdentifier/doi/10.1111/cgf.14197info:eu-repo/semantics/altIdentifier/url/https://arxiv.org/abs/1912.05019info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-nd/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-03T10:05:44Zoai:ri.conicet.gov.ar:11336/135664instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-03 10:05:45.029CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings
title SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings
spellingShingle SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings
Navarro, Jose Pablo
2D MORPHING
IMAGE AND VIDEO PROCESSING
IMAGE AND VIDEO PROCESSING
IMAGE AND VIDEO PROCESSING
IMAGE DATABASES
title_short SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings
title_full SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings
title_fullStr SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings
title_full_unstemmed SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings
title_sort SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings
dc.creator.none.fl_str_mv Navarro, Jose Pablo
Orlando, José Ignacio
Delrieux, Claudio Augusto
Iarussi, Emmanuel
author Navarro, Jose Pablo
author_facet Navarro, Jose Pablo
Orlando, José Ignacio
Delrieux, Claudio Augusto
Iarussi, Emmanuel
author_role author
author2 Orlando, José Ignacio
Delrieux, Claudio Augusto
Iarussi, Emmanuel
author2_role author
author
author
dc.subject.none.fl_str_mv 2D MORPHING
IMAGE AND VIDEO PROCESSING
IMAGE AND VIDEO PROCESSING
IMAGE AND VIDEO PROCESSING
IMAGE DATABASES
topic 2D MORPHING
IMAGE AND VIDEO PROCESSING
IMAGE AND VIDEO PROCESSING
IMAGE AND VIDEO PROCESSING
IMAGE DATABASES
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Finding point-wise correspondences between images is a long-standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport changes. In this paper, we present the first attempt to obtain a learned descriptor for dense registration in line drawings. Based on recent deep learning techniques for corresponding photographs, we designed descriptors to locally match image pairs where the object of interest belongs to the same semantic category, yet still differ drastically in shape, form, and projection angle. To this end, we have specifically crafted a data set of synthetic sketches using non-photorealistic rendering over a large collection of part-based registered 3D models. After training, a neural network generates descriptors for every pixel in an input image, which are shown togeneralize correctly in unseen sketches hand-drawn by humans. We evaluate our method against a baseline of correspondences data collected from expert designers, in addition to comparisons with other descriptors that have been proven effective in sketches. Code, data and further resources will be publicly released by the time of publication.
Fil: Navarro, Jose Pablo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina. Universidad Nacional de la Patagonia "San Juan Bosco". Facultad de Ingeniería - Sede Puerto Madryn. Departamento de Informática; Argentina
Fil: Orlando, José Ignacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil; Argentina. Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ciencias Exactas. Grupo de Plasmas Densos Magnetizados. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Grupo de Plasmas Densos Magnetizados; Argentina
Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina
Fil: Iarussi, Emmanuel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires; Argentina
description Finding point-wise correspondences between images is a long-standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport changes. In this paper, we present the first attempt to obtain a learned descriptor for dense registration in line drawings. Based on recent deep learning techniques for corresponding photographs, we designed descriptors to locally match image pairs where the object of interest belongs to the same semantic category, yet still differ drastically in shape, form, and projection angle. To this end, we have specifically crafted a data set of synthetic sketches using non-photorealistic rendering over a large collection of part-based registered 3D models. After training, a neural network generates descriptors for every pixel in an input image, which are shown togeneralize correctly in unseen sketches hand-drawn by humans. We evaluate our method against a baseline of correspondences data collected from expert designers, in addition to comparisons with other descriptors that have been proven effective in sketches. Code, data and further resources will be publicly released by the time of publication.
publishDate 2021
dc.date.none.fl_str_mv 2021-02
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/135664
Navarro, Jose Pablo; Orlando, José Ignacio; Delrieux, Claudio Augusto; Iarussi, Emmanuel; SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings; Wiley Blackwell Publishing, Inc; Computer Graphics Forum; 40; 1; 2-2021; 410-423
0167-7055
CONICET Digital
CONICET
url http://hdl.handle.net/11336/135664
identifier_str_mv Navarro, Jose Pablo; Orlando, José Ignacio; Delrieux, Claudio Augusto; Iarussi, Emmanuel; SketchZooms: Deep Multi-view Descriptors for Matching Line Drawings; Wiley Blackwell Publishing, Inc; Computer Graphics Forum; 40; 1; 2-2021; 410-423
0167-7055
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://onlinelibrary.wiley.com/doi/10.1111/cgf.14197
info:eu-repo/semantics/altIdentifier/doi/10.1111/cgf.14197
info:eu-repo/semantics/altIdentifier/url/https://arxiv.org/abs/1912.05019
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Wiley Blackwell Publishing, Inc
publisher.none.fl_str_mv Wiley Blackwell Publishing, Inc
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842269926337806336
score 13.13397

Publicaciones similares