Izboljšava kvalitete generiranih slik z uporabo modelov za translacijo med slikami

TANKO, URBAN (author), Skočaj, Danijel (mentor)

Pri generiranju slik se vse več uporabljajo metode GAN. Ena od slabosti je dolgotrajnost njihovega učenja. V diplomski nalogi jo poskusimo odpraviti z uporabo modelov za translacijo med slikami, s katerimi želimo izboljšati kvaliteto generiranih slik. To storimo tako, da zberemo podatkovno množico in na njej naučimo model za generiranje slik StyleGAN. Generirane slike nato poženemo skozi naslednje modele za translacijo med slikami: SR-GAN, Pix2pix, CycleGAN, Pix2pixHD, U-GAT-IT in DeblurGAN. Za vsakega od modelov opišemo generirane slike in jih ocenimo z metriko FID ter človeško oceno, pridobljeno z uporabo ankete. Pridobljene rezultate tudi primerjamo med seboj.

• Language: Slovenian
• Keywords: strojno učenje, umetna inteligenca, nevronske mreže, generativne nasprotniške mreže, translacija med slikami, podatkovna množica, ekstrakcija podatkov
• Work type: Bachelor thesis/paper
• Typology: 2.11 - Undergraduate Thesis
• Organization: FRI - Faculty of Computer and Information Science
• Year: 2020
• PID: 20.500.12556/RUL-114979
• COBISS.SI-ID: 1538565827
• Publication date in RUL: 06.04.2020

Secondary language

• Language: English
• Title: Improving the quality of generated images using image-to-image translation models

Abstract

The application of GAN methods for the purpose of image synthesis has grown considerably. One of their weaknesses is long training time. In this thesis we try to eliminate it by using image-to-image translation models to improve generated image quality. We first gather our dataset and train an image synthesis model StyleGAN. We then feed the generated images into various image-to-image translation models: SR-GAN, Pix2pix, CycleGAN, Pix2pixHD, U-GAT-IT in DeblurGAN. For each of the models we describe the visual properties of generated images. We also calculate the FID scores and human scores, obtained with a survey. At the end we compare the results of the models.

• Keywords: machine learning, artificial intelligence, neural networks, generative adversarial networks, image-to-image translation, dataset, data scraping