Розширення можливостей Paint Transformer з генеруванням мазків пензля за допомогою GAN
| dc.contributor.advisor | Швай, Надія | |
| dc.contributor.author | Поляков, Михайло | |
| dc.date.accessioned | 2024-04-10T10:35:35Z | |
| dc.date.available | 2024-04-10T10:35:35Z | |
| dc.date.issued | 2022 | |
| dc.description.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. | uk_UA |
| dc.identifier.uri | https://ekmair.ukma.edu.ua/handle/123456789/28820 | |
| dc.language.iso | en | uk_UA |
| dc.relation.organisation | НаУКМА | uk_UA |
| dc.status | first published | uk_UA |
| dc.subject | MyPaint Brushstroke Action Spa | uk_UA |
| dc.subject | GAN-generated strokes | uk_UA |
| dc.subject | Modifying the Stroke Predictor | uk_UA |
| dc.subject | магістерська робота | uk_UA |
| dc.title | Розширення можливостей Paint Transformer з генеруванням мазків пензля за допомогою GAN | uk_UA |
| dc.type | Other | uk_UA |