Semantic image completion through an adversarial strategy

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Vitoria, Patricia
• dc.contributor.author Sintes Marcos, Joan
• dc.contributor.author Ballester, Coloma
• dc.date.accessioned 2021-07-06T08:16:13Z
• dc.date.available 2021-07-06T08:16:13Z
• dc.date.issued 2019
• dc.description Comunicació presentada a: VISIGRAPP 2019: Computer Vision, Imaging and Computer Graphics Theory and Applications. 14th International Joint Conference, celebrat del 25 al 27 de febrer de 2019 a Praga, República Txeca.
• dc.description.abstract Image completion or image inpainting is the task of filling in missing regions of an image. When those areas are large and the missing information is unique such that the information and redundancy available in the image is not useful to guide the completion, the task becomes even more challenging. This paper proposes an automatic semantic inpainting method able to reconstruct corrupted information of an image by semantically interpreting the image itself. It is based on an adversarial strategy followed by an energy-based completion algorithm. First, the data latent space is learned by training a modified Wasserstein generative adversarial network. Second, the learned semantic information is combined with a novel optimization loss able to recover missing regions conditioned by the available information. Moreover, we present an application in the context of face inpainting, where our method is used to generate a new face by integrating desired facial attributes or expressions from a reference face. This is achieved by slightly modifying the objective energy. Quantitative and qualitative top-tier results show the power and realism of the presented method.en
• dc.description.sponsorship The authors acknowledge partial support by MICINN/FEDER UE project, reference PGC2018-098625-B-I00 and by H2020-MSCA-RISE-2017 project, reference 777826 NoMADS. We also thank NVIDIA for the Quadro P6000 GPU donation.
• dc.format.mimetype application/pdf
• dc.identifier.citation Vitoria P, Sintes J, Ballester C. Semantic image completion through an adversarial strategy. In: Cláudio AP, Bouatouch K, Chessa M, Paljic A, Kerren A, Hurter C, Tremeau A, Farinella GM, editors. Computer Vision, Imaging and Computer Graphics Theory and Applications. 14th International Joint Conference, VISIGRAPP 2019; 2019 Feb 25-27; Prague, Czech Republic. Cham: Springer; 2019. p. 520-42. DOI: 10.1007/978-3-030-41590-7_22
• dc.identifier.doi http://dx.doi.org/10.1007/978-3-030-41590-7_22
• dc.identifier.uri http://hdl.handle.net/10230/48090
• dc.language.iso eng
• dc.publisher Springer
• dc.relation.ispartof Cláudio AP, Bouatouch K, Chessa M, Paljic A, Kerren A, Hurter C, Tremeau A, Farinella GM, editors. Computer Vision, Imaging and Computer Graphics Theory and Applications. 14th International Joint Conference, VISIGRAPP 2019; 2019 Feb 25-27; Prague, Czech Republic. Cham: Springer; 2019. p. 520-42
• dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/PGC2018-098625-B-I00
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/777826
• dc.rights © Springer The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-030-41590-7_22
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Generative modelsen
• dc.subject.keyword Wasserstein GANen
• dc.subject.keyword Image inpaintingen
• dc.subject.keyword Semantic understandingen
• dc.title Semantic image completion through an adversarial strategyen
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion