EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Scale Cross-Attention Fusion Network Based on Image Super-Resolution

Yimin Ma, Yi Xu, Yunqing Liu, Fei Yan, Qiong Zhang, Qi Li, Quanyang Liu

Applied Sciences · 21.03.2024 · 14 (6) · 2634

DOI: 10.3390/app14062634 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 21.03.2024. Verfasst von Yimin Ma und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Department Project of Jilin Province, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, deep convolutional neural networks with multi-scale features have been widely used in image super-resolution reconstruction (ISR), and the quality of the generated images has been significantly improved compared with traditional methods. However, in current image super-resolution network algorithms, these methods need to be further explored in terms of the effective fusion of multi-scale features and cross-domain application of attention mechanisms. To address these issues, we propose a novel multi-scale cross-attention fusion network (MCFN), which optimizes the feature extraction and fusion process in structural design and modular innovation. In order to make better use of the attention mechanism, we propose a Pyramid Multi-scale Module (PMM) to extract multi-scale information by cascading. This PMM is introduced in MCFN and is mainly constructed by multiple multi-scale cross-attention modules (MTMs). To fuse the feature information of PMMs efficiently in both channel and spatial dimensions, we propose the cross-attention fusion module (CFM). In addition, an improved integrated attention enhancement module (IAEM) is inserted at the network’s end to enhance the correlation of high-frequency feature information between layers. Experimental results show that the algorithm significantly improves the reconstructed images’ edge information and texture details, and the benchmark dataset’s performance evaluation shows comparable performance to current state-of-the-art techniques.

Förderung

  • Science and Technology Department Project of Jilin Province, China

Zitieren

APA

Ma, Y., Xu, Y., Liu, Y., Yan, F., Zhang, Q., Li, Q., & Liu, Q. (2024). Multi-Scale Cross-Attention Fusion Network Based on Image Super-Resolution. Applied Sciences, 14(6), 2634. https://doi.org/10.3390/app14062634

Vancouver

Ma Y, Xu Y, Liu Y, Yan F, Zhang Q, Li Q, et al. Multi-Scale Cross-Attention Fusion Network Based on Image Super-Resolution. Applied Sciences. 2024;14(6):2634. doi:10.3390/app14062634

BibTeX
@article{Ma2024,
  author = {Ma, Yimin and Xu, Yi and Liu, Yunqing and Yan, Fei and Zhang, Qiong and Li, Qi and Liu, Quanyang},
  title = {Multi-Scale Cross-Attention Fusion Network Based on Image Super-Resolution},
  journal = {Applied Sciences},
  year = {2024},
  volume = {14},
  number = {6},
  pages = {2634},
  doi = {10.3390/app14062634}
}
Kostenlos starten →