Piecewise linear regression-based single image super-resolution via Hadamard transform

Image super-resolution (SR) has extensive applications in surveillance systems, satellite imaging, medical imaging, and ultra-high definition display devices. However, state-of-the-art methods for SR still incur considerable running times. In this paper, we thus propose a method based on the Hadamard pattern and tree search structure to significantly reduce the running time. In this approach, low-resolution (LR) and high-resolution (HR) training patch pairs are classified into different classes based on the Hadamard patterns generated from the LR training patches. The mapping relationship between the LR space and the HR space for each class is then learned and used for SR. Experimental results show that the proposed method can achieve an accuracy comparable to those of state-of-the-art methods with a much faster running speed. The dataset, pretrained models and source code can be accessed at the URL in the footnote2.