A Novel Domain Transfer-Based Approach for Unsupervised Thermal Image Super-Resolution
Author(s)
Rivadeneira, Rafael E.; Sappa, Angel D.; Vintimilla, Boris X.; Hammoud, Riad
Downloadsensors-22-02254.pdf (1.078Mb)
Publisher with Creative Commons License
Publisher with Creative Commons License
Creative Commons Attribution
Terms of use
Metadata
Show full item recordAbstract
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 module and a novel loss function. The network is trained on a multi-resolution thermal image dataset acquired with three different thermal sensors. Results report better performance benchmarking results on the 2nd CVPR-PBVS-2021 thermal image super-resolution challenge than state-of-the-art methods. The code of this work is available online.
Date issued
2022-03-14Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence LaboratoryPublisher
Multidisciplinary Digital Publishing Institute
Citation
Sensors 22 (6): 2254 (2022)
Version: Final published version