Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/24015
Full metadata record
DC FieldValueLanguage
dc.contributor.authorFarrugia, Reuben A.-
dc.contributor.authorGuillemot, Christine-
dc.date.accessioned2017-11-21T08:39:22Z-
dc.date.available2017-11-21T08:39:22Z-
dc.date.issued2016-
dc.identifier.citationFarrugia, R. A., & Guillemot, C. (2016). Model and dictionary guided face inpainting in the wild. Asian Conference on Computer Vision (ACCV), Taipei.en_GB
dc.identifier.urihttps://www.um.edu.mt/library/oar//handle/123456789/24015-
dc.description.abstractThis work presents a method that can be used to inpaint occluded facial regions with unconstrained pose and orientation. This approach first warps the facial region onto a reference model to synthesize a frontal view. A modified Robust Principal Component Analysis (RPCA) approach is then used to suppress warping errors. It then uses a novel local patch-based face inpainting algorithm which hallucinates missing pixels using a dictionary of face images which are pre-aligned to the same reference model. The hallucinated region is then warped back onto the original image to restore missing pixels. Experimental results on synthetic occlusions demonstrate that the proposed face inpainting method has the best performance achieving PSNR gains of up to 0.74 dB over the second-best method. Moreover, experiments on the COFW dataset and a number of real-world images show that the proposed method successfully restores occluded facial regions in the wild even for CCTV quality images.en_GB
dc.language.isoenen_GB
dc.publisherSpringeren_GB
dc.rightsinfo:eu-repo/semantics/restrictedAccessen_GB
dc.subjectHuman face recognition (Computer science)en_GB
dc.subjectImage reconstructionen_GB
dc.subjectVideo recordingen_GB
dc.subjectVideo surveillanceen_GB
dc.titleModel and dictionary guided face inpainting in the wilden_GB
dc.typeconferenceObjecten_GB
dc.rights.holderThe copyright of this work belongs to the author(s)/publisher. The rights of this work are as defined by the appropriate Copyright Legislation or as modified by any successive legislation. Users may access this work and can make use of the information contained in accordance with the Copyright Legislation provided that the author must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the prior permission of the copyright holder.en_GB
dc.bibliographicCitation.conferencenameAsian Conference on Computer Vision (ACCV)en_GB
dc.bibliographicCitation.conferenceplaceTaipei, Taiwan, 20-24/11/2016en_GB
dc.description.reviewedpeer-revieweden_GB
dc.identifier.doi10.1007/978-3-319-54407-6_5-
Appears in Collections:Scholarly Works - FacICTCCE

Files in This Item:
File Description SizeFormat 
RAW10-01.pdf
  Restricted Access
7.04 MBAdobe PDFView/Open Request a copy


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.