Розширення можливостей Paint Transformer з генеруванням мазків пензля за допомогою GAN
Loading...
Date
2022
Authors
Поляков, Михайло
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Neural painting produces a sequence of strokes for a given image and artistically recreates it using neural networks. In this thesis, we explore a novel Transformer-based framework named Paint Transformer to predict the parameters of a stroke set with a feed-forward neural network. Paint Transformer achieves better painting results than previous methods with more inexpensive training and inference costs. The thesis proposes a novel extension to Paint Transformer that adds more complex GAN-generated strokes to achieve a more artistically abstract painting style than the original method.
Description
Keywords
MyPaint Brushstroke Action Spa, GAN-generated strokes, Modifying the Stroke Predictor, магістерська робота