Memory-Efficient Discrete Cosine Transform Domain Weight Modulation Transformer for Arbitrary-Scale Super-Resolution
Mathematics · 18.09.2023 · 11 (18) · 3954
DOI: 10.3390/math11183954 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 18.09.2023. Verfasst von Min Hyuk Kim und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Industrial Fundamental Technology Development Progra, IITP.
Abstract (Originalsprache)
Recently, several arbitrary-scale models have been proposed for single-image super-resolution. Furthermore, the importance of arbitrary-scale single image super-resolution is emphasized for applications such as satellite image processing, HR display, and video-based surveillance. However, the baseline integer-scale model must be retrained to fit the existing network, and the learning speed is slow. This paper proposes a network to solve these problems, processing super-resolution by restoring the high-frequency information lost in the remaining arbitrary-scale while maintaining the baseline integer scale. The proposed network extends an integer-scaled image to an arbitrary-scale target in the discrete cosine transform spectral domain. We also modulate the high-frequency restoration weights of the depthwise multi-head attention to use memory efficiently. Finally, we demonstrate the performance through experiments with existing state-of-the-art models and their flexibility through integration with existing integer-scale models in terms of peak signal-to-noise ratio (PSNR) and similarity index measure (SSIM) scores. This means that the proposed network restores high-resolution (HR) images appropriately by improving the image sharpness of low-resolution (LR) images.
Förderung
- Industrial Fundamental Technology Development Progra
- IITP
Zitieren
APA
Kim, M. H., & Yoo, S. B. (2023). Memory-Efficient Discrete Cosine Transform Domain Weight Modulation Transformer for Arbitrary-Scale Super-Resolution. Mathematics, 11(18), 3954. https://doi.org/10.3390/math11183954
Vancouver
Kim MH, Yoo SB. Memory-Efficient Discrete Cosine Transform Domain Weight Modulation Transformer for Arbitrary-Scale Super-Resolution. Mathematics. 2023;11(18):3954. doi:10.3390/math11183954
BibTeX
@article{Kim2023,
author = {Kim, Min Hyuk and Yoo, Seok Bong},
title = {Memory-Efficient Discrete Cosine Transform Domain Weight Modulation Transformer for Arbitrary-Scale Super-Resolution},
journal = {Mathematics},
year = {2023},
volume = {11},
number = {18},
pages = {3954},
doi = {10.3390/math11183954}
}
EUVIMED