基于条件先验Swin Transformer的人脸图像超分辨重建

doi:10.16180/j.cnki.issn1007-7820.2025.02.005

Abstract

Abstract:

In view of the problem that the existing image super resolution models based on Swin Transformer do not preprocess the face image, resulting in poor final super resolution results, this study proposes a face image super resolution reconstruction method based on conditional prior Swin Transformer. The method uses face Parsing Map and Swin Transformer model to preprocess the face image, uses conditional prior to optimize the face hyper-segmentation problem, and uses face parsing map to restrict the process so as to obtain more valuable prior information. In the stage of deep feature extraction, the channel space attention mechanism is integrated with Swin Transformer module to balance the speed and precision of feature group adjustment. Experimental results show that the proposed method achieves a PSNR(Peak Signal-to-Noise Ratio)of 32.21 dB on the test set. Compared with the existing model, this method has a certain improvement. It is proved that the improved model is more suitable for human face, and the generated result is clearer and more real, and more details of face image texture can be restored.

Key words: image super-resolution, Swin Transformer, deep learning, conditional priori, face super-resolution, attention mechanism, Transformer, image processing, super reconstruction

CLC Number:

TP391.41

ZHENG Fangliang, WANG Yannian, LIAN Jihong, RUAN Pei. Face Image Super-Resolution Reconstruction Based on Conditional Priori Swin Transformer[J].Electronic Science and Technology, 2025, 38(2): 35-41.

Figures/Tables 10

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Table 1.

Figure 7.

Table 2.

Table 3.

References 19

[1]	Liang J, Cao J, Sun G, et al. Swinir:Image restoration using swin transformer[C]. Montreal: Proceedings of the IEEE/CVF International Conference on Computer Vision,2021:1833-1844.
[2]	Niu B, Wen W, Ren W, et al. Single image super-resolution via a holistic attention network[C]. Glasgow:Computer Vision-ECCV: The Sixteenth European Conference,2020:191-207.
[3]	吕佳, 许鹏程. 多尺度残差特征融合的轻量级真实图像超分辨率重建[J]. 光电子·激光, 2023, 34(2):120-131.
	Lü Jia, Xu Pengcheng. Lightweight real-world image super-resolution reconstruction based on multi-scale residual feature aggregation[J]. Journal of Optoelectronics·Laser, 2023, 34(2):120-131.
[4]	Chen Y, Liu L, Phonevilay V, et al. Image super-resolution reconstruction based on feature map attention mechanism[J]. Applied Intelligence, 2021, 51(7):4367-4380.
[5]	秦兴, 高晓琪, 陈滨. 基于压缩卷积神经网络的图像超分辨率算法[J]. 电子科技, 2020, 33(5):1-8.
	Qin Xing, Gao Xiaoqi, Chen Bin. Image super-resolution algorithm based on squeeze net convolution neural network[J]. Electronic Science and Technology, 2020, 33(5):1-8.
[6]	Chakrabarti A, Rajagopalan A N, Chellappa R. Super-resolution of face images using kernel PCA-based prior[J]. IEEE Transactions on Multimedia, 2007, 9(4):888-892.
[7]	Daihong J, Sai Z, Lei D, et al. Multi-scale generative adversarial network for image super-resolution[J]. Soft Computing, 2022, 26(8):3631-3641.
[8]	Zhao H, Gallo O, Frosio I, et al. Loss functions for image restoration with neural networks[J]. IEEE Transactions on Computational Imaging, 2016, 3(1):47-57.
[9]	Ren T, Xu H, Jiang G, et al. Reinforced swin-convs transformer for simultaneous underwater sensing scene image enhancement and super-resolution[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60(9):1-16.
[10]	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]. Las Vegas: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778.
[11]	王欢, 吴成东, 迟剑宁, 等. 联合多任务学习的人脸超分辨率重建[J]. 中国图象图形学报, 2020, 25(2):229-240.
	Wang Huan, Wu Chengdong, Chi Jianning, et al. Face super-resolution reconstruction based on multitask joint learning[J]. Journal of Image and Graphics, 2020, 25(2):229-240.
[12]	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.
[13]	Zhang Y, Wu Y, Chen L. MSFSR:A multi-stage face super-resolution with accurate facial representation via enhanced facial boundaries[C]. Seattle: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops,2020:504-505.
[14]	高志军, 冯娇娇. 基于生成对抗网络的煤矿工人脸图像超分辨方法[J]. 黑龙江科技大学学报, 2022, 32(6):828-835.
	Gao Zhijun, Feng Jiaojiao. Super-resolution method of miners'face image based on generative adversarial network[J]. Journal of Heilongjiang University of Science and Technology, 2022, 32(6):828-835.
[15]	雷鹏程, 刘丛, 唐坚刚, 等. 分层特征融合注意力网络图像超分辨率重建[J]. 中国图象图形学报, 2020, 25(9):1773-1786.
	Lei Pengcheng, Liu Cong, Tang Jiangang, et al. Hierarchical feature fusion attention network for image super-resolution reconstruction[J]. Journal of Image and Graphics, 2020, 25(9):1773-1786.
[16]	Nazeri K, Thasarathan H, Ebrahimi M. Edge-informed single image super-resolution[C]. Seoul: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops,2019:3275-3284.
[17]	Ma C, Rao Y, Cheng Y, et al. Structure-preserving super resolution with gradient guidance[C]. Seattle: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2020:7769-7778.
[18]	Ji Y, Jiang P, Shi J, et al. Information-growth swin transformer network for image super-resolution[C]. Bordeaux: IEEE International Conference on Image Processing,2022:3993-3997.
[19]	Hui Z, Wang X, Gao X. Fast and accurate single image super-resolution via information distillation network[C]. Salt Lake City: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2018:723-731.

方法	质量评价
方法	PSNR/dB	SSIM
现有经典超分算法	27.80	0.742 1
基准SwinIR算法	32.02	0.898 7
本文算法	32.21	0.901 4

方法	质量评价
方法	PSNR/dB	SSIM
Bicubic	22.49	0.623 9
FSRCNN	24.95	0.656 7
ESPCN	24.90	0.674 4
SRGAN	27.03	0.721 6
ESRGAN	27.80	0.742 1
本文算法	32.21	0.901 4

方法	RSTB	人脸解析图网络	通道空间注意力	PSNR /dB
基准SwinIR算法	√	-	-	32.02
改进1	√	√	-	32.17
改进2	√	-	√	32.09
本文算法	√	√	√	32.21

Face Image Super-Resolution Reconstruction Based on Conditional Priori Swin Transformer

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 19

Related Articles 15

Metrics

Comments

Recommended 0

[1]	WANG Ziyi, CHEN Shiping. Self-Supervised Network Intrusion Detection Model Based on Graph Contrastive Learning [J]. Electronic Science and Technology, 2025, 38(3): 22-31.
[2]	ZHAO Yunfei, XUE Cunjin. A Remote Sensing Image Water Extraction Method by Combining Atrous Convolution and Pooling Models [J]. Electronic Science and Technology, 2025, 38(3): 40-46.
[3]	CHEN Yuyang, LI Feng. Integration of CNN and Transformer for Retinal OCT Image Fluid Segmentation Method [J]. Electronic Science and Technology, 2025, 38(3): 47-59.
[4]	SUN Jiaqian, ZHU Jinrong, ZHANG Xiaobao, ZHANG Yunkai, GONG Weijuan. Research on Iris Segmentation Algorithm Based on Ensemble Learning [J]. Electronic Science and Technology, 2025, 38(3): 88-94.
[5]	ZHOU Bin, KAN Jiarong, CHEN Heming, CHEN Weiwei, LI Yan, XU Sudong. A Transformerless Half-Bridge Lithium Battery Equalizer Based on Phase-Shift Strategy [J]. Electronic Science and Technology, 2025, 38(2): 1-9.
[6]	XIONG Zhangliang, CHEN Suting, XUAN Zhibin, ZHAO Tingchen, LIU Jiajun, FU Mannan. Design of High Speed Encoding and Decoding Circuit for Isolation Driver Chip [J]. Electronic Science and Technology, 2025, 38(2): 84-92.
[7]	LAI Ying, JU Zhiyong, YE Yuxin. A Vehicle Detection Algorithm Based on Improved YOLOv4 [J]. Electronic Science and Technology, 2025, 38(1): 81-87.
[8]	KUAI Xinchen, LI Ye. Hybrid Image Super-Resolution Reconstruction with Multiple and Multi-Scale Attention [J]. Electronic Science and Technology, 2024, 37(9): 34-42.
[9]	HE Zhiqiang, SUN Zhanquan. Swin-Transformer-Based Carotid Ultrasound Image Plaque Segmentation [J]. Electronic Science and Technology, 2024, 37(9): 48-56.
[10]	TONG Zhaojing, JING Lifei, LAN Mengyue. A Bayesian Network Optimization Method for Transformer Fault Diagnosis [J]. Electronic Science and Technology, 2024, 37(8): 34-39.
[11]	CAO Chunping, XU Zhihua. A Self-Supervised CT Image Classification Method Incorporating Intra-Slice Semantic and Inter-Slice Structural Features [J]. Electronic Science and Technology, 2024, 37(7): 43-52.
[12]	HE Xing, HUANG Yongming, ZHU Yong. Pavement Pothole Detection Method Based on Improved YOLOv5 [J]. Electronic Science and Technology, 2024, 37(7): 53-59.
[13]	LIANG Qiyu, WANG Yonggang, QIU Shengshun. Overvoltage Suppression of Single Switch Resonant Pulse Power Supply [J]. Electronic Science and Technology, 2024, 37(6): 17-28.
[14]	WANG Shengxiong, LIU Ruian, YAN Da. Image Style Transfer Algorithm Based on Improved Generative Adversarial Network [J]. Electronic Science and Technology, 2024, 37(6): 36-43.
[15]	YE Yuxin, JU Zhiyong, LAI Ying. Traffic Sign Detection Algorithm Incorporating Receptive Field Enhancement Module and Attention Mechanism [J]. Electronic Science and Technology, 2024, 37(6): 8-16.