Single Image Super Resolution - When Model Adaptation Matters
This work addresses the need for more accurate super-resolution in images with repetitive structures or high resolutions, though it is incremental by building on existing deep learning approaches.
The paper tackles the problem of single image super-resolution by proposing a deep convolutional neural network with model adaptation strategies to leverage internal image priors, achieving PSNR improvements of 0.1 to 0.3 dB over state-of-the-art results on standard datasets.
In the recent years impressive advances were made for single image super-resolution. Deep learning is behind a big part of this success. Deep(er) architecture design and external priors modeling are the key ingredients. The internal contents of the low resolution input image is neglected with deep modeling despite the earlier works showing the power of using such internal priors. In this paper we propose a novel deep convolutional neural network carefully designed for robustness and efficiency at both learning and testing. Moreover, we propose a couple of model adaptation strategies to the internal contents of the low resolution input image and analyze their strong points and weaknesses. By trading runtime and using internal priors we achieve 0.1 up to 0.3dB PSNR improvements over best reported results on standard datasets. Our adaptation especially favors images with repetitive structures or under large resolutions. Moreover, it can be combined with other simple techniques, such as back-projection or enhanced prediction, for further improvements.