PT Journal AU Rafael E. Rivadeneira Angel Sappa Boris X. Vintimilla Riad I. Hammoud TI A Novel Domain Transfer-Based Approach for Unsupervised Thermal Image Super-Resolution SO Sensors JI SENS PY 2022 BP 2254 VL 22 IS 6 DI 10.3390/s22062254 DE Thermal image super-resolution; unsupervised super-resolution; thermal images; attention module; semiregistered thermal images AB 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. ER