Learning accurate prior knowledge of natural images is of great importance for single image super-resolution (SR). Existing SR methods either learn the prior from the low/high-resolution patch pairs or estimate the prior models from the input low-resolution (LR) image. Specifically, high-frequency details are learned in the former methods. Though effective, they are heuristic and have limitations in dealing with blurred LR images; while the latter suffers from the limitations of frequency aliasing. In this paper, we propose to combine those two lines of ideas for image super-resolution. More specifically, the parametric sparse prior of the desirable high-resolution (HR) image patches are learned from both the input low-resolution (LR) image and a training image dataset. With the learned sparse priors, the sparse codes and thus the HR image patches can be accurately recovered by solving a sparse coding problem. Experimental results show that the proposed SR method outperforms existing state-of-the-art methods in terms of both subjective and objective image qualities.

Nevertheless, it encounters challenges related to ill-posed problems, resulting in deviations between single model predictions and ground-truths. Ensemble learning, as a powerful machine learning technique, aims to address these deviations by combining the predictions of multiple base models.

Low-complexity single-image super-resolution based on nonnegative neighbor embedding.

Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images.

This supplementary document is organized as follows: Section 1 shows the proof that the formula of FRFT degrades to that of FT when α = π/ 2. Section 2 shows the discrete implementation of 2D FRFT. Section 4 shows the experimental results with single branch. Section 5 shows the architecture design of SFC and example usage of SFC and MFRFC. Section 6 introduces the periodicity of FRFT. Section 7 introduces the energy distribution of FRFT.

To date, Transformer-based frameworks have demonstrated impressive results in single-image super-resolution (SISR).

In addition, we demonstrate the scheme's satisfactory architecture generality by providing QuantSR-C