基于频域交互与密集融合的人脸超分辨率重建

doi:10.16451/j.cnki.issn1003-6059.202605004

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1852 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对现有人脸超分辨率方法在计算效率与重建质量之间难以取得最佳平衡的问题,文中提出基于频域交互与密集融合的人脸超分辨率重建网络.首先,利用小波变换进行频域下采样,有效保留图像的频谱信息.在此基础上,设计全局-局部Transformer模块,串行处理局部窗口注意力与全局稀疏注意力,在降低计算复杂度的同时较好地捕捉人脸的整体几何结构.然后,提出频域交互Transformer模块,构建跨频段的交互机制,利用高频特征反向修正低频语义,提升图像锐度.最后,通过邻域尺度密集融合机制实现跨尺度特征聚合.实验表明,文中网络在降低参数量的同时,实现感知质量与像素保真度的良好平衡,为资源受限场景中的人脸超分辨率重建提供新的解决方案.相应源代码获取地址https://github.com/Hddcc/FIDFN.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	刘姝
	张宇峰
	奎晓燕

关键词 ：深度学习, 人脸超分辨率, Transformer, 频域交互, 密集融合

Abstract：It is difficult for existing face super-resolution methods to achieve an optimal tradeoff between computational efficiency and reconstruction quality. To address this issue, a face super-resolution network based on frequency-domain interaction and dense fusion is proposed. First, wavelet transform is adopted for frequency-domain downsampling. The spectral information of images is effectively preserved. On this basis, a global-local Transformer module is designed to serially process local window attention and global sparse attention. The overall geometric structure of the face is better captured and the computational complexity is reduced. Second, a frequency-domain interaction Transformer module is proposed to construct a cross-frequency band interaction mechanism. High-frequency features are utilized to refine low-frequency semantics, thereby improving image sharpness. Finally, cross-scale feature aggregation is realized through an adjacent cross-scale fusion mechanism. Experiments indicate that the proposed network achieves a good balance between perceptual quality and pixel fidelity while reducing the number of parameters. A new solution is provided for face super-resolution in resource-constrained scenarios. The code is available at https://github.com/Hddcc/FIDFN.

Key words： Deep Learning Face Super-Resolution Transformer Frequency-Domain Interaction Dense Fusion

收稿日期: 2026-01-22

ZTFLH:

TP391

基金资助:国家自然科学基金项目(No.U22A2034)、湖南省教育厅科学研究重点项目(No.24A0018)、湘江实验室重点项目(No.23XJ02005)资助

通讯作者: 奎晓燕,博士,教授,主要研究方向为图像处理、数据可视化与可视分析.E-mail:xykui@csu.edu.cn.

作者简介: 刘姝,博士,副教授,主要研究方向为计算机视觉、多模态智能认知.E-mail:sliu35@csu.edu.cn.
张宇峰,硕士研究生,主要研究方向为计算机视觉、图像超分辨率.E-mail:yufengzhang@csu.edu.cn.

引用本文:

刘姝, 张宇峰, 奎晓燕. 基于频域交互与密集融合的人脸超分辨率重建[J]. 模式识别与人工智能, 2026, 39(5): 436-447. LIU Shu, ZHANG Yufeng, KUI Xiaoyan. Face Super-Resolution Reconstruction Based on Frequency-Domain Interaction and Dense Fusion. Pattern Recognition and Artificial Intelligence, 2026, 39(5): 436-447.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202605004 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2026/V39/I5/436

[1] 国家数据局.数字中国发展报告(2024年)[EB/OL].[2025-12-19]. http://www.ndrc.gov.cn.
(National Data Bureau.Digital China Development Report[EB/OL].[2025-12-19]. http://www.ndrc.gov.cn
[2] DONG C, CHEN C L, HE K M, et al. Image Super-Resolution Using Deep Convolutional Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307.
[3] DONG C, CHEN C L, TANG X O.Accelerating the Super-Resolution Convolutional Neural Network // Proc of the 14th European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 391-407.
[4] SHI W Z, CABALLERO J, HUSZÁR F, et al. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 1874-1883.
[5] SIMONYAN K, ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition[C/OL].[2025-12-19]. https://arxiv.org/pdf/1409.1556.
[6] LIM B, SON S, KIM H, et al. Enhanced Deep Residual Networks for Single Image Super-Resolution // Proc of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, USA: IEEE, 2017: 1132-1140.
[7] KIM J, LEE J K, LEE K M.Deeply-Recursive Convolutional Network for Image Super-Resolution // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 1637-1645.
[8] TAI Y, YANG J, LIU X M.Image Super-Resolution via Deep Recursive Residual Network // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 2790-2798.
[9] LAI W S, HUANG J B, AHUJA N, et al. Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 5835-5843.
[10] TONG T, LI G, LIU X J, et al. Image Super-Resolution Using Dense Skip Connections // Proc of the IEEE International Confe-rence on Computer Vision. Washington, USA: IEEE, 2017: 4809-4817.
[11] ZHANG Y L, TIAN Y P, KONG Y, et al. Residual Dense Network for Image Super-Resolution // Proc of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 2472-2481.
[12] ZHANG Y L, LI K P, LI K, et al. Image Super-Resolution Using Very Deep Residual Channel Attention Networks // Proc of the 15th European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 294-310.
[13] LI J C, FANG F M, MEI K F, et al. Multi-scale Residual Network for Image Super-Resolution // Proc of the 15th European Confe-rence on Computer Vision. Berlin, Germany: Springer, 2018: 527-542.
[14] VASWANI A, SHAZEER N, PARMAR N, et al. Attention Is All You Need[C/OL].[2025-12-19]. https://arxiv.org/pdf/1706.03762.
[15] LIANG J Y, CAO J Z, SUN G L, et al. SwinIR: Image Restoration Using Swin Transformer // Proc of the IEEE/CVF Interna-tional Conference on Computer Vision Workshops. Washington, USA: IEEE, 2021: 1833-1844.
[16] CHEN X Y, WANG X T, ZHOU J T, et al. Activating More Pixels in Image Super-Resolution Transformer // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2023: 22367-22377.
[17] GUO H, LI J M, DAI T, et al. MambaIR: A Simple Baseline for Image Restoration with State-Space Model // Proc of the 18th European Conference on Computer Vision. Berlin, Germany: Sprin-ger, 2024: 222-241.
[18] LIU Y, TIAN Y J, ZHAO Y Z, et al. VMamba: Visual State Space Model // Proc of the 38th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2024: 103031-103063.
[19] MA C, JIANG Z Y, RAO Y M, et al. Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation // Proc of the IEEE/CVF Conference on Compu-ter Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 5568-5577.
[20] WANG C Y, JIANG J J, ZHONG Z W, et al. Spatial-Frequency Mutual Learning for Face Super-Resolution // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2023: 22356-22366.
[21] LI W J, GUO H, LIU X N, et al. Efficient Face Super-Resolution via Wavelet-Based Feature Enhancement Network // Proc of the 32nd ACM International Conference on Multimedia. New York, USA: ACM, 2024: 4515-4523.
[22] SHI C T, LI M J, AN Z Y.Face Super-Resolution via Iterative Collaboration between Multi-attention Mechanism and Landmark Estimation. Complex & Intelligent Systems, 2025, 11(1). DOI: 10.1007/s40747-024-01673-z.
[23] WANG J K, GONG J, ZHANG L, et al. OSDface: One-Step Di-ffusion Model for Face Restoration // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2025: 12626-12636.
[24] VARANKA T, TOIVONEN T, TRIPATHY S, et al. PFStorer: Personalized Face Restoration and Super-Resolution // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2024: 2372-2381.
[25] LIU S Y, DUAN Z P, OUYANG J, et al. FaceMe: Robust Blind Face Restoration with Personal Identification. Proceedings of the AAAI Conference on Artificial Intelligence, 2025, 39(5): 5567-5575.
[26] LIU Z W, LUO P, WANG X G, et al. Deep Learning Face Attri-butes in the Wild // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2015: 3730-3738.
[27] LE V, BRANDT J, LIN Z, et al. Interactive Facial Feature Loca-lization // Proc of the 12th European Conference on Computer Vision. Berlin, Germany: Springer, 2012: 679-692.
[28] HU J W, MATHUR L, LIANG P P, et al. OpenFace 3.0: A Lightweight Multitask System for Comprehensive Facial Behavior Analysis[C/OL].[2025-12-19]. https://arxiv.org/pdf/2506.02891.