Real-world super-resolution with VLM-based degradation prior learning

Real-world super-resolution with VLM-based degradation prior learning

Abstract In Real-world Image Super-resolution (Real-SR) task, complex unknown degradations frequently induce ambiguous local structures, fundamentally constraining reconstruction fidelity. While accurate estimation of degradation processes from low-resolution observations enables SR models to mitiga...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaxu Chen, Duixu Mao, Jun Ke
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Super resolution
Degradation
Contrast learning
Vision-language model
Online Access:https://doi.org/10.1038/s41598-025-14581-0
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://doi.org/10.1038/s41598-025-14581-0

Similar Items