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...
Wedi'i Gadw mewn:
| Prif Awduron: | , , |
|---|---|
| Fformat: | Artigo |
| Iaith: | Inglês |
| Cyhoeddwyd: |
MDPI AG
2026-06-01
|
| Cyfres: | Applied Sciences |
| Pynciau: | |
| Mynediad Ar-lein: | https://www.mdpi.com/2076-3417/16/12/6221 |
| Tagiau: |
Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!
|