Hybrid-Domain Synergistic Transformer for Hyperspectral Image Denoising
Source abstract
Abstract
Hyperspectral image (HSI) denoising is challenged by complex spatial-spectral noise coupling. Existing deep learning methods, primarily designed for RGB images, fail to address HSI-specific noise distributions and spectral correlations. This paper proposes a Hybrid-Domain Synergistic Transformer (HDST) integrating frequency-domain enhancement and multiscale modeling. Key contributions include (1) a Fourier-based preprocessing module decoupling spectral noise; (2) a dynamic cross-domain attention mechanism adaptively fusing spatial-frequency features; and (3) a hierarchical architecture combining global noise modeling and detail recovery. Experiments on realistic and synthetic datasets show HDST outperforms state-of-the-art methods in PSNR, with fewer parameters. Visual results confirm effective noise suppression without spectral distortion. The framework provides a robust solution for HSI denoising, demonstrating potential for high-dimensional visual data processing.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image and Signal Denoising Methods · Advanced Image Fusion Techniques · Remote-Sensing Image Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Optoelectronic Science and Engineering, Soochow University, Suzhou 215000, China
References (49)
Show source-provided references
1. HFAN: High-Frequency Attention Network for hyperspectral image denoising10.1007/s13042-023-01942-2 ↗
2. Lin, Y., Cai, Z., Li, J., and Zhang, J. (2022, January 26–28). Lightweight Remote Sensing Image Denoising via Knowledge Distillation. Proceedings of the 2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP), Shanghai, China.10.1109/MMSP55362.2022.9949236 ↗
3. Tang, J., Zhang, F., Ma, F., Gao, F., Yin, Q., and Zhou, Y. (2021, January 11–16). How SAR Image Denoise Affects the Performance of DCNN-Based Target Recognition Method. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium.10.1109/IGARSS47720.2021.9554871 ↗
4. Research on denoising optimization algorithm of point cloud in 3d reconstruction10.1088/1742-6596/1345/5/052073 ↗
5. Rasti, B., Sveinsson, J.R., Ulfarsson, M.O., and Benediktsson, J.A. (2012, January 22–27). Hyperspectral image denoising using 3D wavelets. Proceedings of the 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, Germany.10.1109/IGARSS.2012.6351286 ↗
6. Comparison of Non Local Means Filtering with Wavelet Transform Technique for Denoising ECG signal10.15680/IJIRSET.2015.0408048 ↗
7. Low-frequency noise suppression method based on improved DnCNN in desert seismic data10.1109/LGRS.2018.2882058 ↗
8. Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., and Timofte, R. (2021, January 10–17). Swinir: Image restoration using swin transformer. Proceedings of the IEEE/CVF International Conference on Computer Vision, Virtual.10.1109/ICCVW54120.2021.00210 ↗
9. Modern Trends in Hyperspectral Image Analysis: A Review10.1109/ACCESS.2018.2812999 ↗
10. A review of hyperspectral remote sensing and its application in vegetation and water resource studies
11. Multispectral and hyperspectral imaging technologies in conservation: Current research and potential applications10.1179/sic.2006.51.Supplement-1.3 ↗
12. Carrasco, O., Gomez, R.B., Chainani, A., and Roper, W.E. (2003, January 21–25). Hyperspectral imaging applied to medical diagnoses and food safety. Proceedings of the Geo-Spatial and Temporal Image and Data Exploitation III, SPIE, Orlando, FL, USA.10.1117/12.502589 ↗
13. Clark, R.N., and Swayze, G.A. (1995, January 23–26). Mapping minerals, amorphous materials, environmental materials, vegetation, water, ice and snow, and other materials: The USGS Tricorder algorithm. Proceedings of the JPL, Summaries of the Fifth Annual JPL Airborne Earth Science Workshop, AVIRIS Workshop, Pasadena, CA, USA.
14. Kuula, J., Pölönen, I., Puupponen, H.H., Selander, T., Reinikainen, T., Kalenius, T., and Saari, H. (2012, January 23–27). Using VIS/NIR and IR spectral cameras for detecting and separating crime scene details. Proceedings of the Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense XI, SPIE, Baltimore, MD, USA.10.1117/12.918555 ↗
15. A Single Model CNN for Hyperspectral Image Denoising10.1109/TGRS.2019.2952062 ↗
16. SMDS-Net: Model Guided Spectral-Spatial Network for Hyperspectral Image Denoising10.1109/TIP.2022.3196826 ↗
17. Deep Learning Applications for Hyperspectral Imaging: A Systematic Review10.33969/JIEC.2020.21004 ↗
18. Palsson, F., Ulfarsson, M.O., and Sveinsson, J.R. (2014, January 13–18). Hyperspectral image denoising using a sparse low rank model and dual-tree complex wavelet transform. Proceedings of the 2014 IEEE Geoscience and Remote Sensing Symposium, Quebec City, QC, Canada.10.1109/IGARSS.2014.6947279 ↗
19. Rasti, B., Scheunders, P., Ghamisi, P., Licciardi, G., and Chanussot, J. (2018). Noise reduction in hyperspectral imagery: Overview and application. Remote Sens., 10.10.3390/rs10030482 ↗
20. Wavelet analysis and its application in denoising the spectrum of hyperspectral image
21. Hyperspectral Imagery Denoising by Deep Learning With Trainable Nonlinearity Function10.1109/LGRS.2017.2743738 ↗
22. Deep Spatial–Spectral Representation Learning for Hyperspectral Image Denoising10.1109/TCI.2019.2911881 ↗
23. Del Bue, A., Canton, C., Pont-Tuset, J., and Tommasi, T. (October, January 29). Hybrid Spatial-Spectral Neural Network for Hyperspectral Image Denoising. Proceedings of the Computer Vision—ECCV 2024 Workshops, Milan, Italy.
24. Fu, G., Xiong, F., Tao, S., Lu, J., Zhou, J., and Qian, Y. (2021, January 11–16). Learning a Model-Based Deep Hyperspectral Denoiser from a Single Noisy Hyperspectral Image. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium.10.1109/IGARSS47720.2021.9553257 ↗
25. Leveraging Frequency and Spatial Domain Information for Underwater Image Restoration10.1088/1742-6596/2832/1/012001 ↗
26. Zheng, P., Chen, K., Huang, J., Chen, B., Liu, J., Ren, Y., and Pu, X. (2025). Lightweight Medical Image Restoration via Integrating Reliable Lesion-Semantic Driven Prior. arXiv.
27. Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., and Varol, G. (October, January 29). Efficient Frequency-Domain Image Deraining with Contrastive Regularization. Proceedings of the 18th European Conference on Computer Vision—ECCV 2024, Milan, Italy.10.1007/978-3-031-72980-5 ↗
28. Zhu, Y., Chen, J., Liang, L., Kuang, Z., Jin, L., and Zhang, W. (2021, January 20–25). Fourier Contour Embedding for Arbitrary-Shaped Text Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.00314 ↗
29. Kong, L., Dong, J., Ge, J., Li, M., and Pan, J. (2023, January 17–24). Efficient frequency domain-based transformers for high-quality image deblurring. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00570 ↗
30. Wang, Y., Wang, H., Wang, L., Wang, X., Zhu, L., Lu, W., and Huang, H. (2025, January 11–15). Complementary advantages: Exploiting cross-field frequency correlation for nir-assisted image denoising. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.10.1109/CVPR52734.2025.01183 ↗
31. A Denoising Network Based on Frequency-Spectral- Spatial-Feature for Hyperspectral Image10.1109/JSTARS.2023.3285454 ↗
32. Sheng, Z., Yu, Z., Liu, X., Cao, S.Y., Liu, Y., Shen, H.L., and Zhang, H. (2023, January 17–24). Structure Aggregation for Cross-Spectral Stereo Image Guided Denoising. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.01345 ↗
33. Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A.L. (2016). DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. arXiv.
34. Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation10.1016/j.patcog.2020.107622 ↗
35. ASPP-DF-PVNet: Atrous Spatial Pyramid Pooling and Distance-Filtered PVNet for occlusion resistant 6D object pose estimation10.1016/j.image.2021.116268 ↗
36. Li, M., Liu, J., Fu, Y., Zhang, Y., and Dou, D. (2023). Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising. arXiv.10.1109/CVPR52729.2023.00562 ↗
37. Hyperspectral Image Denoising: From Model-Driven, Data-Driven, to Model-Data-Driven10.1109/TNNLS.2023.3278866 ↗
38. Deep learning models for digital image processing: A review10.1007/s10462-023-10631-z ↗
39. Nonlocal transform-domain filter for volumetric data denoising and reconstruction10.1109/TIP.2012.2210725 ↗
40. He, W., Yao, Q., Li, C., Yokoya, N., and Zhao, Q. (2019, January 15–20). Non-local meets global: An integrated paradigm for hyperspectral denoising. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00703 ↗
41. Brook, A. (2014, January 24–27). 3-D wavelets-based denoising and enhancement of hyperspectral imagery. Proceedings of the 2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), Lausanne, Switzerland.10.1109/WHISPERS.2014.8077589 ↗
42. Hyperspectral Image Denoising Employing a Spatial–Spectral Deep Residual Convolutional Neural Network10.1109/TGRS.2018.2865197 ↗
43. MAC-Net: Model-aided nonlocal neural network for hyperspectral image denoising
44. Hyperspectral Image Denoising via Spatial–Spectral Recurrent Transformer
45. Image quality assessment through FSIM, SSIM, MSE and PSNR—A comparative study10.4236/jcc.2019.73002 ↗
46. A comprehensive survey of loss functions and metrics in deep learning10.1007/s10462-025-11198-7 ↗
47. Hyperspectral Image Denoising With Total Variation Regularization and Nonlocal Low-Rank Tensor Decomposition10.1109/TGRS.2019.2947333 ↗
48. 3-D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising10.1109/TNNLS.2020.2978756 ↗
49. Bodrito, T., Zouaoui, A., Chanussot, J., and Mairal, J. (2021). A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration. arXiv.