EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GPSR: Gradient-Prior-Based Network for Image Super-Resolution

Xiancheng Zhu, Detian Huang, Xiaorui Li, Danlin Cai, Daxin Zhu

Applied Sciences · 07.01.2023 · 13 (2) · 833

DOI: 10.3390/app13020833 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 07.01.2023. Verfasst von Xiancheng Zhu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China, Collaborative Innovation Platform Project of Fujian Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent deep learning has shown great potential in super-resolution (SR) tasks. However, most deep learning-based SR networks are optimized via pixel-level loss (i.e., L1, L2, and MSE), which forces the networks to output the average of all possible predictions, leading to blurred details. Especially in SR tasks with large scaling factors (i.e., ×4, ×8), the limitation is further aggravated. To alleviate this limitation, we propose a Gradient-Prior-based Super-Resolution network (GPSR). Specifically, a detail-preserving Gradient Guidance Strategy is proposed to fully exploit the gradient prior to guide the SR process from two aspects. On the one hand, an additional gradient branch is introduced into GPSR to provide the critical structural information. On the other hand, a compact gradient-guided loss is proposed to strengthen the constraints on the spatial structure and to prevent the blind restoration of high-frequency details. Moreover, two residual spatial attention adaptive aggregation modules are proposed and incorporated into the SR branch and the gradient branch, respectively, to fully exploit the crucial intermediate features to enhance the feature representation ability. Comprehensive experimental results demonstrate that the proposed GPSR outperforms state-of-the-art methods regarding both subjective visual quality and objective quantitative metrics in SR tasks with large scaling factors (i.e., ×4 and ×8).

Förderung

  • National Natural Science Foundation of China
  • National Key R&D Program of China
  • Collaborative Innovation Platform Project of Fujian Province
  • Natural Science Foundation of Fujian Provincial Science and Technology Department
  • Natural Science Foundation of Fujian Province
  • Fundamental Research Funds for the Central Universities
  • Foundation of Fujian Education Department
  • Key Project of Quanzhou Science and Technology Plan

Zitieren

APA

Zhu, X., Huang, D., Li, X., Cai, D., & Zhu, D. (2023). GPSR: Gradient-Prior-Based Network for Image Super-Resolution. Applied Sciences, 13(2), 833. https://doi.org/10.3390/app13020833

Vancouver

Zhu X, Huang D, Li X, Cai D, Zhu D. GPSR: Gradient-Prior-Based Network for Image Super-Resolution. Applied Sciences. 2023;13(2):833. doi:10.3390/app13020833

BibTeX
@article{Zhu2023,
  author = {Zhu, Xiancheng and Huang, Detian and Li, Xiaorui and Cai, Danlin and Zhu, Daxin},
  title = {GPSR: Gradient-Prior-Based Network for Image Super-Resolution},
  journal = {Applied Sciences},
  year = {2023},
  volume = {13},
  number = {2},
  pages = {833},
  doi = {10.3390/app13020833}
}
Kostenlos starten →