TY - GEN
T1 - A GRAPH NEURAL NETWORK FOR MULTIPLE-IMAGE SUPER-RESOLUTION
AU - Tarasiewicz, Tomasz
AU - Nalepa, Jakub
AU - Kawulok, Michal
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Super-resolution consists in reconstructing a high-resolution image from single or multiple low-resolution observations. Deep learning has been reported extremely successful for single-image super-resolution, but its applications to the multiple-image scenarios are limited due to the challenges that arise from feeding a network with a stack of images with sub-pixel translations. In this paper, we introduce Magnet—a new graph neural network that benefits from representing the input low-resolution images as a graph. This enables us to exploit the sub-pixel shifts among the input images while preserving the original low-resolution pixel values for feature extraction and information fusion. Despite a relatively simple architecture, Magnet outperforms the state-of-the-art methods for multiple-image super-resolution, and due to the flexible graph representation, it allows for using a variable number of low-resolution images for reconstruction.
AB - Super-resolution consists in reconstructing a high-resolution image from single or multiple low-resolution observations. Deep learning has been reported extremely successful for single-image super-resolution, but its applications to the multiple-image scenarios are limited due to the challenges that arise from feeding a network with a stack of images with sub-pixel translations. In this paper, we introduce Magnet—a new graph neural network that benefits from representing the input low-resolution images as a graph. This enables us to exploit the sub-pixel shifts among the input images while preserving the original low-resolution pixel values for feature extraction and information fusion. Despite a relatively simple architecture, Magnet outperforms the state-of-the-art methods for multiple-image super-resolution, and due to the flexible graph representation, it allows for using a variable number of low-resolution images for reconstruction.
KW - Deep learning
KW - Graph neural networks
KW - Super-resolution reconstruction
UR - https://www.scopus.com/pages/publications/85125600365
U2 - 10.1109/ICIP42928.2021.9506070
DO - 10.1109/ICIP42928.2021.9506070
M3 - Conference contribution
AN - SCOPUS:85125600365
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1824
EP - 1828
BT - 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
PB - IEEE Computer Society
T2 - 28th IEEE International Conference on Image Processing, ICIP 2021
Y2 - 19 September 2021 through 22 September 2021
ER -