This paper proposes a novel CycleGAN architecture for thermal image super-resolution, together with a large dataset consisting of thermal images at different resolutions. The dataset has been acquired using three thermal cameras at different resolutions, which acquire images from the same scenario at the same time. The thermal cameras are mounted in rig trying to minimize the baseline distance to make easier the registration problem. The proposed architecture is based on ResNet6 as a Generator and PatchGAN as Discriminator. The novelty on the proposed unsupervised super-resolution training (CycleGAN) is possible due to the existence of aforementioned thermal images---images of the same scenario with different resolutions. The proposed approach is evaluated in the dataset and compared with classical bicubic interpolation. The dataset and the network are available.
Este dataset cuenta con 1021 imagenes (separadas en 951 para entrenamiento, 50 para testing y 20 para validación). Este dataset cuenta con 3 tipos de resoluciones 160x120, 320x240 y 640x480, categorizados como baja, media y alta. Especificado en [3].
Referencias
[3] Rivadeneira, Rafael E and Sappa, Angel D and Vintimilla, Boris X. (2019). Thermal Image Super-Resolution: a Novel Architecture and Dataset. VISAPP2020 (paper)
|
|
| Download Dataset |
@inproceedings{rivadeneira2019thermal,
title={Thermal Image Super-Resolution: a Novel Architecture and Dataset},
author={Rivadeneira, Rafael E and Sappa, Angel D and Vintimilla, Boris X},
booktitle={International Conference on Computer Vision Theory and Applications},
pages={1--2},
year={2020},
organization={nn}
}