A Novel Domain Transfer-Based Approach for Unsupervised Thermal Image Super-Resolution
This paper presents a transfer domain strategy to tackle the limitations of low-resolution thermal sensors and generate higher-resolution images of reasonable quality. The proposed technique employs a CycleGAN architecture and uses a ResNet as an encoder in the generator along with an attention modu...
Main Authors: | Rivadeneira, Rafael E. (Author), Sappa, Angel D. (Author), Vintimilla, Boris X. (Author), Hammoud, Riad (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute,
2022-03-24T19:01:58Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Domain Transfer Learning for Hyperspectral Image Super-Resolution
by: Xiaoyan Li, et al.
Published: (2019-03-01) -
Unsupervised Single-Image Super-Resolution with Multi-Gram Loss
by: Yong Shi, et al.
Published: (2019-07-01) -
Deep Unsupervised Fusion Learning for Hyperspectral Image Super Resolution
by: Zhe Liu, et al.
Published: (2021-03-01) -
Wide-Band Color Imagery Restoration for RGB-NIR Single Sensor Images
by: Xavier Soria, et al.
Published: (2018-06-01) -
An Unsupervised Remote Sensing Single-Image Super-Resolution Method Based on Generative Adversarial Network
by: Ning Zhang, et al.
Published: (2020-01-01)