Search academic texts

Information × Registration Number 2120U007874, Article popup.category Препринт Title NoGAN: Deblurring Images without Adversarial Training (AI translated) popup.author Vei RomanVei Roman popup.publication 01-01-2020 popup.source_user Український католицький університет popup.source https://hdl.handle.net/20.500.14570/4491 popup.publisher Description In this paper, we systematically study generative adversarial networks (GANs) for single image motion deblurring. Firstly, we compare adversarial loss functions, dis- criminators, and other training configurations to find optimal setup. Secondly, we train the blurred image classification model and use it as a pretrained discriminator in the GAN setup. We train GANs in two ways: with frozen and unfrozen discrimi- nator weights. popup.nrat_date 2025-11-05 Close