Mean-Curvature-Regularized Deep Image Prior with Soft Attention for Image Denoising and Deblurring

Sparsity-driven regularization has undergone significant development in single-image restoration, particularly with the transition from handcrafted priors to trainable deep architectures. In this work, a geometric prior-enhanced deep image prior (DIP) framework, termed DIP-MC, is proposed that integ...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Muhammad Israr, Shahbaz Ahmad, Muhammad Nabeel Asghar, Saad Arif
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	MDPI AG 2025-12-01
Serie:	Mathematics
Soggetti:	image reconstruction image restoration image deblurring deep learning deep image prior total variation regularization
Accesso online:	https://www.mdpi.com/2227-7390/13/24/3906
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!