EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

XTNSR: Xception-based transformer network for single image super resolution

Jagrati Talreja, Supavadee Aramvith, Takao Onoye

Complex & Intelligent Systems · 2025-02 · 11 (2)

DOI: 10.1007/s40747-024-01760-1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Complex & Intelligent Systems, online erschienen am 25.01.2025. Verfasst von Jagrati Talreja und 2 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Electrical Engineering, Chulalongkorn University, Chulalongkorn University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single image super resolution has significantly advanced by utilizing transformers-based deep learning algorithms. However, challenges still need to be addressed in handling grid-like image patches with higher computational demands and addressing issues like over-smoothing in visual patches. This paper presents a Deep Learning model for single-image super-resolution. In this paper, we present the XTNSR model, a novel multi-path network architecture that combines Local feature window transformers (LWFT) with Xception blocks for single-image super-resolution. The model processes grid-like image patches effectively and reduces computational complexity by integrating a Patch Embedding layer. Whereas the Xception blocks use depth-wise separable convolutions for hierarchical feature extraction, the LWFT blocks capture long-range dependencies and fine-grained qualities. A multi-layer feature fusion block with skip connections, part of this hybrid architecture, guarantees efficient local and global feature fusion. The experimental results show better performance in Peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and visual quality than the state-of-the-art techniques. By optimizing parameters, the suggested architecture also lowers computational complexity. Overall, the architecture presents a promising approach for advancing image super-resolution capabilities.

Förderung

  • Department of Electrical Engineering, Chulalongkorn University
  • Chulalongkorn University

Zitieren

APA

Talreja, J., Aramvith, S., & Onoye, T. (2025). XTNSR: Xception-based transformer network for single image super resolution. Complex & Intelligent Systems, 11(2). https://doi.org/10.1007/s40747-024-01760-1

Vancouver

Talreja J, Aramvith S, Onoye T. XTNSR: Xception-based transformer network for single image super resolution. Complex & Intelligent Systems. 2025;11(2). doi:10.1007/s40747-024-01760-1

BibTeX
@article{Talreja2025,
  author = {Talreja, Jagrati and Aramvith, Supavadee and Onoye, Takao},
  title = {XTNSR: Xception-based transformer network for single image super resolution},
  journal = {Complex & Intelligent Systems},
  year = {2025},
  volume = {11},
  number = {2},
  doi = {10.1007/s40747-024-01760-1}
}
Kostenlos starten →