Noise Suppression and Unpacking Accuracy Improvement Based on Generative Adversarial Networks for Interferometric Phase Maps
Main Article Content
Abstract
Multiplicative speckle noise and additive Gaussian noise in the interferometric phase map introduce spurious phase jumps and residual points, disrupting phase continuity and reducing the reliability of the phase unpacking algorithm. To address this issue, this paper proposes a conditional generative adversarial network. The generator uses a multi-scale dilated convolutional U-Net to output a complex phase residual map. The denoised result is obtained by subtracting the residual from the noisy phase. A dual discriminator structure in the spatial and frequency domains, combined with weighted structural similarity loss, phase gradient consistency loss, and least-squares adversarial loss, jointly constrains the network training. Training data is generated through electromagnetic scattering simulation. The proposed method achieves a 97.3% phase unpacking success rate at a signal-to-noise ratio of 0–3 dB. Processing a 2048 × 2048 pixel image takes less than 0.25 seconds. The proposed method effectively suppresses non-stationary noise and improves the accuracy of phase unpacking.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
W. Luo, S. Ye, W. Xiong, Z. Zhang, X. Wang, S. Li, and F. Wang, “A noise reduction method for continuous optical spatial heterodyne interferograms based on deep convolutional neural networks,” Infrared and Laser Engineering, vol. 54, no. 3, pp. 352–365, 2025, doi: https://doi.org/10.3788/IRLA20240392.
L. Tao, G. Huang, S. Yang, T. Wang, H. Sheng, and H. Fan, “An interferometric image denoising method using convolutional neural networks,” Journal of Wuhan University (Information Science Edition), vol. 48, no. 4, pp. 559–567, 2023, doi: https://doi.org/10.13203/j.whugis20200589.
S. Wang, J. Liu, J. Wu, G. Liu, X. Ling, and L. Yu, “A Denoising Method for Sheared Speckle Phase Map Based on Improved Particle Swarm Optimization Algorithm,” Measurement & Control Technology, vol. 42, no. 6, pp. 78–83, 2023, doi: https://doi.org/10.19708/j.ckjs.2023.06.009.
H. K. Yadalam, M. Kizmann, J. R. Rouxel, et al., “Quantum interferometric pathway selectivity in difference-frequency-generation spectroscopy,” The Journal of Physical Chemistry Letters, vol. 14, no. 48, pp. 10803–10809, 2023, doi: https://doi.org/10.1021/acs.jpclett.3c02341.
V. Gordienko, F. M. Ferreira, V. Ribeiro, et al., “Design of an interferometric fiber optic parametric amplifier for the rejection of unwanted four-wave mixing products,” Optics Express, vol. 31, no. 5, pp. 8226–8239, 2023, doi: https://doi.org/10.1364/OE.476884.
R. Jie, H. Zheng, O. Alsalman, et al., “High-sensitivity Fabry-Perot interferometric sensor based on microwave photonics with phase demodulation,” Journal of Lightwave Technology, vol. 42, no. 19, pp. 6958–6966, 2024, doi: https://doi.org/10.1109/JLT.2024.3409536.
T. Natale, P. B. Núñez, L. Dindelli, et al., “Modeling interferometric optical gyroscopes: An experimentally validated approach,” IEEE Sensors Journal, vol. 25, no. 6, pp. 9560–9566, 2025, doi: https://doi.org/10.1109/JSEN.2025.3530638.
A. Florio, G. Avitabile, and G. Coviello, “Multiple source angle of arrival estimation through phase interferometry,” IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 69, no. 3, pp. 674–678, 2022, doi: https://doi.org/10.1109/TCSII.2022.3141247.
S. Rasouli and S. Khoshkhatti, “Single-frame double-grating interferometry with two inherent-phase-shifted interferograms,” Optics Express, vol. 32, no. 13, pp. 22429–22447, 2024, doi: https://doi.org/10.1364/OE.521731.
J. R. Sánchez-Aguilar, A. K. Reyes, L. García-Lechuga, et al., “Polarizing white light interferometry for phase measurements using two simultaneous interferograms,” Applied Optics, vol. 62, no. 27, pp. 7280–7287, 2023, doi: https://doi.org/10.1364/AO.496606.
S. Kim, J. Jeon, Y. Kim, et al., “Design and assessment of phase-shifting algorithms in optical interferometer,” International Journal of Precision Engineering and Manufacturing-Green Technology, vol. 10, no. 2, pp. 611–634, 2023, doi: https://doi.org/10.1007/s40684-022-00495-z.
F. Wang, X. Li, S. Ye, S. Li, and X. Wang, “Error analysis method for spatial heterodyne interferograms using wavelet transform,” Spectroscopy and Spectral Analysis, vol. 45, no. 1, pp. 8–14, 2025, doi: https://doi.org/10.3964/j.issn.1000-0593(2025)01-0008-07.
P. J. de Groot, L. L. Deck, R. Su, et al., “Contributions of holography to the advancement of interferometric measurements of surface topography,” Light: Advanced Manufacturing, vol. 3, no. 2, pp. 258–277, 2022, doi: https://doi.org/10.37188/lam.2022.007.
P. J. Stas, Y. C. Wei, M. Sirotin, et al., “Entanglement-assisted non-local optical interferometry in a quantum network,” Nature, vol. 651, no. 8105, pp. 326–332, 2026.