QR koda

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...

Popoln opis

Shranjeno v:
Bibliografske podrobnosti
Principais autores: Ao-Lin Liu, Yi-Han Xu, Wen Zhou
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: Označite
Brez oznak, prvi označite!