SP-IGAN: An Improved GAN Framework for Effective Utilization of Semantic Priors in Real-World Image Super-Resolution

SP-IGAN: An Improved GAN Framework for Effective Utilization of Semantic Priors in Real-World Image Super-Resolution

Single-image super-resolution (SISR) based on GANs has achieved significant progress. However, these methods still face challenges when reconstructing locally consistent textures due to a lack of semantic understanding of image categories. This highlights the necessity of focusing on contextual info...

Full description

Saved in:
Bibliographic Details
Main Authors: Meng Wang, Zhengnan Li, Haipeng Liu, Zhaoyu Chen, Kewei Cai
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Entropy
Subjects:
single image super-resolution
semantic priors
long-range dependency
wavelet loss
Online Access:https://www.mdpi.com/1099-4300/27/4/414
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items