BDIS: Balanced Training Architecture for Dual Image Scaler Using Origin Referenceable Losses
Deep neural network (DNN)-based research on image scaling has mostly focused on super-resolution (SR) rather than image downscaling. Specifically, most existing DNN-based methods for image downscaling are used as auxiliary modules to improve the quality of super-resolved images. In rare cases, DNN-b...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9780200/ |