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...
Saved in:
| Main Authors: | Xiaxu Chen, Duixu Mao, Jun Ke |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-14581-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Boosting Degradation Representation Learning for Blind Image Super-Resolution
by: YUAN Jiang, MA Ji, ZHOU Dengwen
Published: (2025-05-01) -
Unsupervised Spectral Super-Resolution Guided by Spectral Sampling Priors
by: Xintao Zhong, et al.
Published: (2025-01-01) -
MARSWIN: A Cross-Shot Swin Transformer Network for Super-Resolution on Mars MoRIC Image
by: Junjie Li, et al.
Published: (2025-01-01) -
Hourglass attention for image super-resolution
by: Ling Xu, et al.
Published: (2025-08-01) -
Peningkatan Performa Pengenalan Wajah pada Gambar Low-Resolution Menggunakan Metode Super-Resolution
by: Muhammad Imaduddin Abdur Rohim, et al.
Published: (2024-02-01)