[1]尹　毅,吕　培,李凯江,等.基于多尺度动态滤波的图像增强模型[J].郑州大学学报(工学版),2026,47(3):100-107.[doi:10.13705/j.issn.1671-6833.2025.03.016]
　YIN Yi,LYU Pei,LI Kaijiang,et al.Image Enhancement Model Based on Multi-scale Dynamic Filtering[J].Journal of Zhengzhou University (Engineering Science),2026,47(3):100-107.[doi:10.13705/j.issn.1671-6833.2025.03.016]
点击复制

基于多尺度动态滤波的图像增强模型()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
47
期数:
2026年3期
页码:
100-107
栏目:
出版日期:
2026-05-27

文章信息/Info

Title:
Image Enhancement Model Based on Multi-scale Dynamic Filtering
文章编号:
1671-6833(2026)03-0100-08
作者:
尹　毅, 吕　培, 李凯江, 郑昊坤, 徐　豪, 陈梦婕
郑州大学 计算机与人工智能学院,河南 郑州 450001
Author(s):
YIN Yi, LYU Pei, LI Kaijiang, ZHENG Haokun, XU Hao, CHEN Mengjie
School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China
关键词:
图像增强;  低通滤波;  高通滤波;  多尺度融合;  频域变换
Keywords:
image enhancement;  low-pass filtering;  high-pass filtering;  multi-scale fusion;  frequency domain transformation
分类号:
TP37:TP391.9
DOI:
10.13705/j.issn.1671-6833.2025.03.016
文献标志码:
A
摘要:
为了解决传统图像增强方法中难以同时兼顾全局平滑与局部纹理细节的问题,提出了一个基于多尺度动态滤波分解的MDFD图像增强模型。首先,利用可学习的低通滤波器和高通滤波器来分别提取图像的低频与高频图像分量;其次,结合这两种频域图像分量,提出了跨低频通道注意力融合模块(LFCA)和跨高频空间注意力融合模块(HFSA),以实现图像全局与局部的协同增强;最后,通过引入多尺度融合策略,综合利用不同尺度下的高频和低频信息进行特征融合。多尺度融合的优点在于能够通过有效整合不同尺度上的细节和全局特征,在多个层面显著提升图像的增强效果。实验结果表明:MDFD模型在FiveK和PPR10K数据集上的验证中表现出色,其中峰值信噪比(PSNR)分别达到25.90和27.35,结构相似性指数(SSIM)分别为0.964和0.945,ΔEab分别为7.38和6.50。这表明MDFD模型在复杂环境和颜色丰富等场景下具有优越的图像增强性能。
Abstract:
To address the issue of collaborative enhancement between global smoothness and local textures in traditional image enhancement techniques, in this study an MDFD image enhancement model based on multi-scale dynamic filtering decomposition was proposed. Initially, learnable low-pass and high-pass filters were utilized to extract the low-frequency and high-frequency image components, respectively. Subsequently, by combining these two frequency-domain image components, the cross low-frequency channel attention fusion module (LFCA) and cross high-frequency spatial attention fusion module (HFSA) were introduced to achieve collaborative enhancement of image global and local features. Finally, a multi-scale fusion strategy was introduced to comprehensively utilize high-frequency and low-frequency information at different scales for feature fusion. The advantage of multi-scale fusion lay in its ability to effectively integrate details and global features at different scales, significantly enhancing the image at multiple levels. Experimental results showed that the MDFD model performed excellently in the validation on the FiveK and PPR10K datasets, with peak signal-to-noise ratio (PSNR) reaching 25.90 and 27.35, structural similarity index (SSIM) being 0.964 and 0.945, and ΔEab being 7.38 and 6.50, respectively. These results indicated that the MDFD model could offer superior image enhancement performance in complex environments and color-rich scenes.

参考文献/References:

[1]刘华军, 张瑞珏, 刘建锋, 等. 基于FPGA的高分辨率视频图像实时增强去雾系统[J]. 郑州大学学报(工学版), 2020, 41(2): 19-24.

LIU H J, ZHANG R J, LIU J F, et al. High resolution video image real-time enhancement system based on FPGA[J]. Journal of Zhengzhou University (Engineering Science), 2020, 41(2): 19-24.
[2]GAUTAM C, TIWARI N. Efficient color image contrast enhancement using range limited Bi-histogram equalization with adaptive gamma correction[C]∥2015 International Conference on Industrial Instrumentation and Control (ICIC). Piscataway:IEEE, 2015: 175-180.
[3]CHEN Y H, ZHU G, WANG X Q, et al. FRR-NET: a fast reparameterized residual network for low-light image enhancement[J]. Signal, Image and Video Processing, 2024, 18(5): 4925-4934.
[4]ZHOU J C, LI B S, ZHANG D H, et al. UGIF-net: an efficient fully guided information flow network for underwater image enhancement[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 4206117.
[5]SHEN L, YUE Z H, FENG F, et al. MSR-net: low-light image enhancement using deep convolutional network[EB/OL]. (2017-11-07)[2024-08-11]. https:∥arxiv.org/abs/1711.02488.
[6]ZENG H, CAI J R, LI L D, et al. Learning image-adaptive 3D lookup tables for high performance photo enhancement in real-time[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(4): 2058-2073.
[7]YANG C Q, JIN M G, JIA X, et al. AdaInt: learning adaptive intervals for 3D lookup tables on real-time image enhancement[C]∥2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE, 2022: 17501-17510.
[8]OUYANG W Q, DONG Y, KANG X Y, et al. RSFNet: a white-box image retouching approach using region-specific color filters[C]∥2023 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway:IEEE, 2023: 12126-12135.
[9]YAHIAOUI M L, KHARFI F, BOUKERDJA L. Resolution enhancement of neutron radiography image using combined SRCNN-POCS method[J]. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2023, 1050: 168123.
[10] GHARBI M, CHEN J W, BARRON J T, et al. Deep bilateral learning for real-time image enhancement[J]. ACM Transactions on Graphics, 2017, 36(4): 1-12.
[11] HALIDOU A, MOHAMADOU Y, ARI A A A, et al. Review of wavelet denoising algorithms[J]. Multimedia Tools and Applications, 2023, 82(27): 41539-41569.
[12] LUO Y C, ZHANG Y, YAN J C, et al. Generalizing face forgery detection with high-frequency features[J]. (202103-23)[2024-08-11]. https:∥arxiv.org/abs/2103.12376.
[13] BAI J W, YUAN L, XIA S T, et al. Improving vision transformers by revisiting high-frequency components[C]∥ Computer Vision-ECCV 2022. Cham: Springer, 2022: 1-18.
[14] XU K, YANG X, YIN B C, et al. Learning to restore low-light images via decomposition-and-enhancement[C]∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE, 2020: 2278-2287.
[15]常青, 杨程伟, 罗彬杰, 等. 基于小波变换的扩散焊超声C图像融合算法[J]. 郑州大学学报(工学版), 2023, 44(4): 54-59, 87.
CHANG Q, YANG C W, LUO B J, et al. Ultrasonic C image fusion algorithm for diffusion welding based on wavelet transform[J]. Journal of Zhengzhou University (Engineering Science), 2023, 44(4): 54-59, 87.
[16] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE, 2016: 770-778.
[17] DUHAMEL P, VETTERLI M. Fast Fourier transforms: a tutorial review and a state of the art[J]. Signal Processing, 1990, 19(4): 259-299.
[18] BYCHKOVSKY V, PARIS S, CHAN E, et al. Learning photographic global tonal adjustment with a database of input/output image pairs[C]∥CVPR 2011. Piscataway:IEEE, 2011: 97-104.
[19] LIANG J, ZENG H, CUI M M, et al. PPR10K: a largescale portrait photo retouching dataset with human-region mask and group-level consistency[C]∥2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE, 2021:00071.
[20]WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[EB/OL]. (2014-01-01)[2024-07-16]. https:∥ieeexplore. ieee.org/document/1284395.
[21] KE Z H, SUN C Y, ZHU L, et al. Harmonizer: learning toPerform white-box image andVideo harmonization[C]∥ Computer Vision-ECCV 2022. Cham: Springer, 2022: 690-706.
[22] HE J W, LIU Y H, QIAO Y, et al. Conditional sequential modulation for efficient global image retouching[C]∥ Computer Vision-ECCV 2020. Cham: Springer, 2020: 679-695.

更新日期/Last Update: 2026-05-27