Generative Adversarial Network for Mural Inpainting Based on Multi-level Feature Fusion and Hypergraph Convolution
Aiming at the problems of low feature utilization and insufficient attention to context information in existing deep learning image restoration methods, a generative adversarial mural restoration model based on multi-level feature fusion and hypergraph convolution was proposed. Firstly, a pyramid fe...
Сохранить в:
| Главные авторы: | , , |
|---|---|
| Формат: | Artigo |
| Язык: | Inglês |
| Опубликовано: |
Editorial Department of Journal of Sichuan University (Engineering Science Edition)
2024-05-01
|
| Серии: | 工程科学与技术 |
| Предметы: | |
| Online-ссылка: | http://jsuese.scu.edu.cn/thesisDetails#10.12454/j.jsuese.202200874 |
| Метки: |
Нет меток, Требуется 1-ая метка записи!
|