Deep learning for fast super-resolution reconstruction from multiple images
Michał Kawulok, Paweł Benecki, Krzysztof Hrynczenko, Daniel Kostrzewa, Szymon Piechaczek, Jakub Nalepa, Bogdan Smołka · 2019
Recent advancements in single-image super-resolution reconstruction (SRR) are attributed primarily to convolutional neural networks (CNNs), which effectively learn the relation between low and high resolution and allow for obtaining high-quality reconstruction within seconds. SRR from multiple images benefits from information fusion, which improves the reconstruction outcome compared with example-based methods. On the other hand, multiple-image SRR is computationally more demanding, mainly due to required subpixel registration of the input images. Here, we explore how to exploit CNNs in multiple-image SRR and we demonstrate that competitive reconstruction outcome can be obtained within seconds.