DeepSUM++: Non-local Deep Neural Network for Super-Resolution of Unregistered Multitemporal Images
This work addresses the problem of enhancing image resolution for remote sensing applications, but it is incremental as it builds on a previous winning method.
The paper tackles super-resolution of unregistered multitememporal remote sensing images by incorporating non-local information into a convolutional neural network, resulting in improved performance over state-of-the-art methods on a challenge dataset.
Deep learning methods for super-resolution of a remote sensing scene from multiple unregistered low-resolution images have recently gained attention thanks to a challenge proposed by the European Space Agency. This paper presents an evolution of the winner of the challenge, showing how incorporating non-local information in a convolutional neural network allows to exploit self-similar patterns that provide enhanced regularization of the super-resolution problem. Experiments on the dataset of the challenge show improved performance over the state-of-the-art, which does not exploit non-local information.