Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Gruber, Ivan | |
dc.contributor.author | Hrúz, Marek | |
dc.contributor.author | Železný, Miloš | |
dc.contributor.author | Karpov, Alexey | |
dc.date.accessioned | 2022-03-28T10:00:29Z | - |
dc.date.available | 2022-03-28T10:00:29Z | - |
dc.date.issued | 2021 | |
dc.identifier.citation | GRUBER, I. HRÚZ, M. ŽELEZNÝ, M. KARPOV, A. X-Bridge: Image-to-Image Translation with Reconstruction Capabilities. In 23rd International Conference, SPECOM 2021, St. Petersburg, Russia, September 27–30, 2021, Proceedings. Cham: Springer, 2021. s. 238-249. ISBN: 978-3-030-87801-6 , ISSN: 0302-9743 | cs |
dc.identifier.isbn | 978-3-030-87801-6 | |
dc.identifier.issn | 0302-9743 | |
dc.identifier.uri | 2-s2.0-85116369882 | |
dc.identifier.uri | http://hdl.handle.net/11025/47269 | |
dc.format | 12 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | Springer | en |
dc.relation.ispartofseries | 23rd International Conference, SPECOM 2021, St. Petersburg, Russia, September 27–30, 2021, Proceedings | en |
dc.rights | Plný text je přístupný v rámci univerzity přihlášeným uživatelům. | cs |
dc.rights | © Springer | en |
dc.subject | Translace obrázků | cs |
dc.subject | Generativní adversarialní sítě | cs |
dc.subject | Heterogenní rozpoznávání lidské tváře | cs |
dc.title | X-Bridge: Image-to-Image Translation with Reconstruction Capabilities | en |
dc.title.alternative | X-Bridge: Translace obrázků s rekonstrukčními kapacitami | cs |
dc.type | konferenční příspěvek | cs |
dc.type | ConferenceObject | en |
dc.rights.access | restrictedAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | This work presents a novel method for image-to-image translation named X-Bridge. The method is based on a conditional adversarial network. X-Bridge is a supervised method build upon the Pix2pix approach, however, it extends the original system with an additional reconstruction path and a shared-latent space assumption between the original and the reconstruction path. With these modifications, we argue that the qualitative results provided by X-Bridge overcome other state-of-the-art methods in terms of similarity between translated and corresponding images, robustness, generalization capacity, and translated features preservation. This assumption is confirmed with provided quantitative results. We demonstrate the power of this approach on the challenging facial image-to-sketch translation task. Code is available at: https://github.com/YvanG/Cross-modal-Bridge. | en |
dc.subject.translated | Image-to-image translation | en |
dc.subject.translated | Generative adversarial networks | en |
dc.subject.translated | Heterogeneous face recognition | en |
dc.identifier.doi | 10.1007/978-3-030-87802-3_22 | |
dc.type.status | Peer-reviewed | en |
dc.identifier.obd | 43933803 | |
dc.project.ID | TN01000024/Národní centrum kompetence - Kybernetika a umělá inteligence - prodloužení | cs |
dc.project.ID | 90042/Velká výzkumná infrastruktura povinnost (J) - CESNET II | cs |
Appears in Collections: | Konferenční příspěvky / Conference Papers (KKY) Konferenční příspěvky / Conference papers (NTIS) OBD |
Files in This Item:
File | Size | Format | |
---|---|---|---|
Gruber2021_Chapter_X-BridgeImage-to-ImageTranslat.pdf | 2,6 MB | Adobe PDF | View/Open Request a copy |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/47269
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.