Exploring double cross cyclic interpolation in unpaired image-to-image translation Lopez J. es_PE Mauricio A. es_PE Camara G. es_PE 2024-05-30T23:13:38Z 2024-05-30T23:13:38Z 2019
dc.description.abstract The unpaired image-to-image translation consists of transferring a sample a in the domain A to an analog sample b in the domain B without intensive pixel-to-pixel supervision. The current vision focuses on learning a generative function that maps both domains but ignoring the latent information, although its exploration is not explicit supervision. This paper proposes a cross-domain GAN-based model to achieve a bi-directional translation guided by latent space supervision. The proposed architecture provides a double-loop cyclic reconstruction loss in an exchangeable training adopted to reduce mode collapse and enhance local details. Our proposal has outstanding results in visual quality, stability, and pixel-level segmentation metrics over different public datasets.
dc.description.sponsorship Consejo Nacional de Ciencia, Tecnología e Innovación Tecnológica - Concytec
dc.identifier.scopus 2-s2.0-85077031640
dc.language.iso eng
dc.publisher Institute of Electrical and Electronics Engineers Inc.
dc.relation.ispartof Proceedings - 32nd Conference on Graphics, Patterns and Images, SIBGRAPI 2019
dc.rights info:eu-repo/semantics/openAccess
dc.subject Unpaired Image to Image Translation
dc.subject Cross domain interpolation es_PE
dc.subject Latent space exploration es_PE
dc.title Exploring double cross cyclic interpolation in unpaired image-to-image translation
dc.type info:eu-repo/semantics/article