%0 Conference Proceedings
%T Multi-Image Super-Resolution for Thermal Images
%A Rafael E. Rivadeneira
%A Angel Sappa
%A Boris X. Vintimilla
%B 17th International Conference on Computer Vision Theory and Applications (VISAPP 2022)
%D 2022
%V 4
%F Rafael E. Rivadeneira2022
%O MSIAU; 601.349
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3690), last updated on Thu, 27 Apr 2023 15:07:39 +0200
%X This paper proposes a novel CNN architecture for the multi-thermal image super-resolution problem. In the proposed scheme, the multi-images are synthetically generated by downsampling and slightly shifting the given image; noise is also added to each of these synthesized images. The proposed architecture uses twoattention blocks paths to extract high-frequency details taking advantage of the large information extracted from multiple images of the same scene. Experimental results are provided, showing the proposed scheme has overcome the state-of-the-art approaches.
%K Thermal Images
%K Multi-view
%K Multi-frame
%K Super-Resolution
%K Deep Learning
%K Attention Block
%U https://www.scitepress.org/PublicationsDetail.aspx?ID=gGSl9NFalmw=&t=1
%U http://refbase.cvc.uab.es/files/RSV2022a.pdf
%P 635-642