Lightweight CNN–Transformer Hybrid Network for Efficient Face Super-Resolution
Face super-resolution (FSR) aims to reconstruct high-quality high-resolution face images from low-resolution inputs. Although CNN–Transformer hybrid models have shown promising performance by jointly modeling local textures and global dependencies, their large parameter sizes and high computational...
保存先:
| 主要な著者: | , , |
|---|---|
| フォーマット: | Artigo |
| 言語: | Inglês |
| 出版事項: |
MDPI AG
2026-06-01
|
| シリーズ: | Applied Sciences |
| 主題: | |
| オンライン･アクセス: | https://www.mdpi.com/2076-3417/16/12/6221 |
| タグ: |
タグなし, このレコードへの初めてのタグを付けませんか!
|