Single Image Super-Resolution: From Discrete to Continuous Scale Without Retraining

Single Image Super-Resolution: From Discrete to Continuous Scale Without Retraining

Convolutional neural network (CNN)-based single image super-resolution (SR) methods have achieved superior performance on some discrete-scaling factors, including 2, 3, and 4. However, the scaling factors for SR should be continuous and not discrete in practical applications. Previous CNN-based SR m...

Full description

Bibliographic Details
Main Authors: Yuzhen Niu, Hanmei Weng, Jiaqi Lin, Genggeng Liu
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Convolutional neural network
image interpolation
super-resolution
Online Access:https://ieeexplore.ieee.org/document/8993794/

Internet

https://ieeexplore.ieee.org/document/8993794/

Similar Items