EUVIMEDEUVIMED entdecken
Crossref

Dual-Domain Modulation Network for Lightweight Image Super-Resolution

Wenjie Li, Heng Guo, Yuefeng Hou, Guangwei Gao, Zhanyu Ma

IEEE Transactions on Multimedia · 2026 · 28 · 4679-4689

DOI: 10.1109/tmm.2026.3660149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Multimedia, 2026. Verfasst von Wenjie Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref). Gefördert von: Beijing-Tianjin-Hebei Basic Research Funding Program, National Natural Science Foundation of China, Hebei Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lightweight image super-resolution (SR) aims to reconstruct high-resolution images from low-resolution images under limited computational costs. We find existing frequency-based SR methods cannot balance the reconstruction of overall structures and high-frequency parts. Meanwhile, these methods are inefficient for handling frequency features and unsuitable for lightweight SR. In this paper, we show introducing both wavelet and Fourier information allows our model to consider both high-frequency features and overall SR structure reconstruction while reducing costs. Specifically, we propose a Dual-domain Modulation Network that integrates both wavelet and Fourier information for enhanced frequency modeling. Unlike existing methods that rely on a single frequency representation, our design combines wavelet-domain modulation via a Wavelet-domain Modulation Transformer (WMT) with global Fourier supervision, enabling complementary spectral learning well-suited for lightweight SR. Experimental results show that our method achieves a comparable PSNR of SRFormer (Zhou et al., 2023) and MambaIR (Guo et al., 2024) while with less than 50% and 60% of their FLOPs and achieving inference speeds 15.4× and 5.4× faster, respectively, demonstrating the effectiveness of our method on SR quality and lightweight.

Förderung

  • Beijing-Tianjin-Hebei Basic Research Funding Program
  • National Natural Science Foundation of China
  • Hebei Natural Science Foundation
  • Beijing Natural Science Foundation
  • Beijing Municipal Science & Technology

Zitieren

APA

Li, W., Guo, H., Hou, Y., Gao, G., & Ma, Z. (2026). Dual-Domain Modulation Network for Lightweight Image Super-Resolution. IEEE Transactions on Multimedia, 28, 4679-4689. https://doi.org/10.1109/tmm.2026.3660149

Vancouver

Li W, Guo H, Hou Y, Gao G, Ma Z. Dual-Domain Modulation Network for Lightweight Image Super-Resolution. IEEE Transactions on Multimedia. 2026;28:4679-4689. doi:10.1109/tmm.2026.3660149

BibTeX
@article{Li2026,
  author = {Li, Wenjie and Guo, Heng and Hou, Yuefeng and Gao, Guangwei and Ma, Zhanyu},
  title = {Dual-Domain Modulation Network for Lightweight Image Super-Resolution},
  journal = {IEEE Transactions on Multimedia},
  year = {2026},
  volume = {28},
  pages = {4679--4689},
  doi = {10.1109/tmm.2026.3660149}
}
Kostenlos starten →