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...
Shranjeno v:
| Principais autores: | , , |
|---|---|
| Format: | Artigo |
| Jezik: | Inglês |
| Izdano: |
MDPI AG
2026-06-01
|
| Serija: | Applied Sciences |
| Teme: | |
| Online dostop: | https://www.mdpi.com/2076-3417/16/12/6221 |
| Oznake: |
Brez oznak, prvi označite!
|
