PT Unknown
AU Rafael E. Rivadeneira
   Angel Sappa
   Boris X. Vintimilla
TI Multi-Image Super-Resolution for Thermal Images
BT 17th International Conference on Computer Vision Theory and Applications (VISAPP 2022)
PY 2022
BP 635
EP 642
VL 4
DE Thermal Images; Multi-view; Multi-frame; Super-Resolution; Deep Learning; Attention Block
AB 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.
ER