.png){kind=icon}
.png){kind=icon}
Return
Post-Processing Ensemble Framework for Balancing Fidelity and Perception in Super-Resolution
.png){kind=icon}
PRE
AI
D
J
DOI：10.1016/j.patrec.2026.05.001.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A novel, lightweight post-processing ensemble framework for Super-Resolution. • Balances the trade-off between image fidelity (PSNR/SSIM) and perceptual quality. • Effectively mitigates color, structure, and facial artifacts from perception-oriented models. • Requires no model retraining, making it a versatile plug-and-play solution.
Keywords:
Super-Resolution
Post-Processing
Ensemble Framework
Image Fidelity
Perceptual Quality
Journal
IF:
3.3
Papers:
7.8K
Citations:
1.6W
Organization
Cited Papers