Exploring double cross cyclic interpolation in unpaired image-to-image translation

• Autores: Lopez J., Mauricio A., Camara G.
• Formato: artículo
• Fecha de Publicación: 2019
• Institución: Consejo Nacional de Ciencia Tecnología e Innovación
• Repositorio: CONCYTEC-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.concytec.gob.pe:20.500.12390/2695
• Enlace del recurso: https://hdl.handle.net/20.500.12390/2695; https://doi.org/10.1109/SIBGRAPI.2019.00025
• Nivel de acceso: acceso abierto
• Materia: Unpaired Image to Image Translation; Cross domain interpolation; Latent space exploration; http://purl.org/pe-repo/ocde/ford#2.02.03

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.