The FiBSR Method for Face Super-Resolution Reconstruction in Power Systems

Authors

  • Hao Lu Northeast Petroleum University, Qinhuangdao 066004, China
  • Shuyi Liu Northeast Petroleum University, Qinhuangdao 066004, China

DOI:

https://doi.org/10.54097/77efnc71

Keywords:

Face Super-Resolution, Spatially Variant Degradation, Power Systems

Abstract

This paper proposes a blind face super-resolution reconstruction method called FiBSR, aiming to solve the complex spatial-temporal degradation problems in real scenarios. The core innovations of this method include: A physical modeling system based on anisotropic Gaussian kernels is constructed, and the degradation prior of spatial changes is explicitly regressed through the degradation kernel parameter estimation network (SV_KEN).a multi-scale discriminator, and a progressive two-stage training strategy, FiBSR provides a robust and systematic solution that outperforms existing mainstream methods in both subjective and objective evaluations, laying a solid foundation for practical applications in complex degradation scenarios.

Downloads

Download data is not yet available.

References

[1] Gu Y, Wang X, Xie L, et al. Vqfr: Blind face restoration with vector-quantized dictionary and parallel decoder [C]//European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022: 126-143.

[2] Dong C, Loy C C, He K, et al. Image super-resolution using deep convolutional networks [J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 38(2): 295-307.

[3] Xin J, Wang N, Jiang X, et al. Facial attribute capsules for noise face super resolution [C]//Proceedings of the AAAI conference on artificial intelligence. 2020, 34(07): 12476-12483.

[4] Ma C, Jiang Z, Rao Y, et al. Deep face super-resolution with iterative collaboration between attentive recovery and landmark estimation [C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 5569-5578.

[5] Chen C, Gong D, Wang H, et al. Learning spatial attention for face super-resolution [J]. IEEE Transactions on Image Processing, 2020, 30: 1219-1231.

[6] Li W, Guo H, Liu X, et al. Efficient face super-resolution via wavelet-based feature enhancement network [C]//Proceedings of the 32nd ACM international conference on multimedia. 2024: 4515-4523.

Downloads

Published

2026-03-26

Issue

Section

Articles

How to Cite

Lu, H., & Liu, S. (2026). The FiBSR Method for Face Super-Resolution Reconstruction in Power Systems. International Journal of Advanced Engineering and Technology Research, 1(2), 71-73. https://doi.org/10.54097/77efnc71