Complex-Valued Neural Networks with Adaptive Frequency Attention for Image Denoising

Marjono Marjono, Avin Maulana, Anggi Gustiningsih Hapsani

Abstract


Image denoising encompasses various noise types; in this work, we focus specifically on periodic interference, which introduces coherent frequency-domain artifacts that are challenging to remove using conventional real-valued convolutional neural networks (CNNs). This paper introduces a Complex-Valued Neural Network with Adaptive Frequency Attention (CVNN-AFA) tailored to periodic noise removal, integrating complex-domain feature propagation with explicit radial frequency-band modulation. The proposed architecture employs complex convolutions, complex batch normalization, and ModReLU activations to jointly model amplitude and phase information. An Adaptive Frequency Attention (AFA) module operates in the Fourier domain and partitions the spectrum into low-, mid-, and high-frequency radial bands using distance-based masks, enabling adaptive band-wise reweighting aligned with interference characteristics. Experiments on the BSDS500 dataset augmented with synthetic periodic noise evaluate both low-noise and moderate-to-high noise regimes under matched training budgets and strong real-valued frequency-aware baselines. Results indicate that CVNN-AFA achieves competitive performance overall and provides consistent, moderate improvements in low-amplitude settings, while the real-valued frequency-aware baseline remains more robust under extreme corruption levels. Qualitative and spectral analyses suggest that the proposed approach offers incremental attenuation of periodic components while maintaining comparable detail preservation. These findings are specific to the controlled periodic noise scenarios evaluated in this study.

Keywords


Complex-Valued Neural Networks; Frequency Attention; Image Denoising; Periodic Noise; U-Net.

Full Text:

PDF

References


[1] L. Yan, M. Zhao, S. Liu, S. Shi, and J. Chen, “Cascaded Transformer U-Net for image restoration,” Signal Processing, vol. 206, 2023, doi: 10.1016/j.sigpro.2022.108902.

[2] A. S. Anandhi and M. Jaiganesh, “An enhanced image restoration using deep learning and transformer-based contextual optimization algorithm,” Scientific Reports, vol. 15, p. 10324, 2025, doi: 10.1038/s41598-025-94449-5.

[3] B. Li, Y. Zhang, W. Chen, Y. Ma, and L. Li, “Neural network-based investigation of periodic noise reduction methods for high-resolution infrared line scanning images,” Remote Sensing, vol. 16, no. 5, p. 841, 2024, doi: 10.3390/rs16050841.

[4] Z. H. Shah et al., “Image restoration in frequency space using complex-valued CNNs,” Frontiers in Artificial Intelligence, vol. 7, p. 1353873, 2024, doi: 10.3389/frai.2024.1353873.

[5] K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising,” IEEE Transactions on Image Processing, vol. 26, no. 7, pp. 3142–3155, 2017, doi: 10.1109/TIP.2017.2662206.

[6] C. Ren, X. He, C. Wang, and Z. Zhao, “Adaptive consistency prior based deep network for image denoising (DeamNet),” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2021, pp. 8596–8606, doi: 10.1109/CVPR46437.2021.00849.

[7] S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, and M. Yang, “Restormer: Efficient transformer for high-resolution image restoration,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, IEEE, Jun. 18–24, 2022, pp. 5728–5739, doi: 10.1109/CVPR52688.2022.00564.

[8] Y. Gou, P. Hu, J. Lv, J. T. Zhou, and X. Peng, “Multi-scale adaptive network for single image denoising,” arXiv preprint arXiv:2203.04313, 2022. Available: https://arxiv.org/abs/2203.04313.

[9] A. Maulana, C. Fatichah, and N. Suciati, “Facial inpainting using generative adversarial network with feature reconstruction and landmark loss to preserve spatial consistency in unaligned face images,” International Journal of Intelligent Engineering and Systems, vol. 13, no. 6, pp. 219–228, 2020, doi: 10.22266/ijies2020.1231.20.

[10] J. Varghese, S. Subash, K. Subramaniam, and K. P. Sridhar, “Adaptive Gaussian notch filter for removing periodic noise from digital images,” IET Image Processing, vol. 14, no. 8, pp. 1529–1538, 2020, doi: 10.1049/iet-ipr.2018.5707.

[11] Q. Zeng, H. Qin, X. Yan, and T. Yang, “Fourier domain anomaly detection and spectral fusion for stripe noise removal of TIR imagery,” Remote Sensing, vol. 12, no. 22, p. 3714, 2020, doi: 10.3390/rs12223714.

[12] S. Rawat, K. P. S. Rana, and V. Kumar, “A novel complex-valued convolutional neural network for medical image denoising (CVMIDNet),” Biomedical Signal Processing and Control, vol. 69, p. 102859, 2021, doi: 10.1016/j.bspc.2021.102859.

[13] J. Gurrola-Ramos, O. Dalmau, and T. E. Alarcón, “A residual dense U-Net neural network for image denoising,” IEEE Access, vol. 9, pp. 31742–31754, 2021, doi: 10.1109/ACCESS.2021.3061062.

[14] P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik, “Contour detection and hierarchical image segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 5, pp. 898–916, May 2011, doi: 10.1109/TPAMI.2010.161.

[15] J. T. Barron, “A general and adaptive robust loss function,” arXiv preprint arXiv:1701.03077, 2019. Available: https://arxiv.org/abs/1701.03077.

[16] G. Singh, A. Mittal, and N. Aggarwal, “ResDNN: Deep residual learning for natural image denoising,” IET Image Processing, vol. 14, no. 11, pp. 2425–2434, 2020, doi: 10.1049/iet-ipr.2019.0623.




DOI: https://doi.org/10.18860/cauchy.v11i1.36851

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Marjono Marjono, Avin Maulana, Anggi Gustiningsih Hapsani

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Editorial Office
Mathematics Department,
Universitas Islam Negeri Maulana Malik Ibrahim Malang
Gajayana Street 50 Malang, East Java, Indonesia 65144
Faximile (+62) 341 558933
e-mail: cauchy@uin-malang.ac.id

Creative Commons License
CAUCHY: Jurnal Matematika Murni dan Aplikasi is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.