Search academic texts

Information × Registration Number 2119U006542, Article popup.category Препринт Title Color and style transfer using Generative Adversarial Networks (AI translated) popup.author Kusyy AndriyKusyy Andriy popup.publication 01-01-2019 popup.source_user Український католицький університет popup.source https://hdl.handle.net/20.500.14570/1331 popup.publisher Description In this work, we present an end-to-end solution for an image to image color and style transfer using Conditional Generative Adversarial Networks. Nowadays photo editing industry is growing rapidly, and one of the crucial issues is recoloring and restyling of individual objects or areas on images. With a fast advancement of deep segmentation models, getting a precise segmentation mask for an area on a picture is no longer a problem although unsupervised restyling and recoloring of the object with complex patterns is still a challenge. The proposed model is a state-of-the-art regarding visual appearance and provides high structural similarity. popup.nrat_date 2025-11-05 Close