Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorRotger, Gemma
dc.contributor.authorMoreno-Noguer, Francesc
dc.contributor.authorLumbreras, Felipe
dc.contributor.authorAgudo, Antonio
dc.contributor.editorSkala, Václav
dc.date.accessioned2019-10-22T06:05:25Z
dc.date.available2019-10-22T06:05:25Z
dc.date.issued2019
dc.identifier.citationJournal of WSCG. 2019, vol. 27, no. 2, p. 103-112.en
dc.identifier.issn1213-6964 (on-line)
dc.identifier.issn1213-6972 (print)
dc.identifier.issn1213-6980 (CD-ROM)
dc.identifier.urihttp://hdl.handle.net/11025/35594
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencycs
dc.rights© Václav Skala - UNION Agencycs
dc.subject3D rekonstrukce vrásekcs
dc.subjectanalýza obličejecs
dc.subjectoptimalizacecs
dc.titleDetailed 3D Face Reconstruction from a Single RGB Imageen
dc.typečlánekcs
dc.typearticleen
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedThis paper introduces a method to obtain a detailed 3D reconstruction of facial skin from a single RGB image. To this end, we propose the exclusive use of an input image without requiring any information about the observed material nor training data to model the wrinkle properties. They are detected and characterized directly from the image via a simple and effective parametric model, determining several features such as location, orientation, width, and height. With these ingredients, we propose to minimize a photometric error to retrieve the final detailed 3D map, which is initialized by current techniques based on deep learning. In contrast with other approaches, we only require estimating a depth parameter, making our approach fast and intuitive. Extensive experimental evaluation is presented in a wide variety of synthetic and real images, including different skin properties and facial expressions. In all cases, our method outperforms the current approaches regarding 3D reconstruction accuracy, providing striking results for both large and fine wrinkles.en
dc.subject.translated3D wrinkle reconstructionen
dc.subject.translatedface analysisen
dc.subject.translatedoptimizationen
dc.identifier.doihttps://doi.org/10.24132/JWSCG.2019.27.2.3
dc.type.statusPeer-revieweden
Vyskytuje se v kolekcích:Volume 27, Number 2 (2019)

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
Rotger.pdfPlný text13,02 MBAdobe PDFZobrazit/otevřít


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/35594

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.