Methods for hyperspectral and multispectral images fusion based on per pixel spectral transformations and cyclic consistency
Khodyrev R. R.
1, Bazhenov S. A.
1, Kabanova T. V.
1, Vrazhnov D. A.
1, Kistenev Y.V.
11Tomsk State University, Tomsk, Russia
Email: hodarev.ruslan@mail.ru, bazhenov.stepan1@gmail.com, tvk@bk.ru, vda@iao.ru, yuk@iao.ru
The paper presents two approaches for hyperspectral and multispectral images fusion. The first approach is based on the WMatrixGenerator module, which generates per pixel spectral transformation matrices with quadratic correction. The second approach uses the HSIMSICycleGAN architecture with cyclical consistency and physically motivated losses. The experimental evaluation showed the competitiveness of the proposed methods for the PSNR, SSIM, SAM and ERGAS metrics on the Real HSI/MSI/PAN dataset. The methods work on paired observations of hyperspectral and multispectral images of the same scene, but do not require high-resolution reference data. Keywords: image fusion, hyperspectral images, multispectral images, deep learning, non-negative least squares, CycleGAN, remote sensing, neural networks.
- Hyperspectral Data Exploitation: Theory and Applications, ed. by C.I. Chang (John Wiley \& Sons, 2007). DOI: 10.1002/9780470124628.ch3
- T. Adao, J. Hruv ska, L. Padua, J. Bessa, E. Peres, R. Morais, J.J. Sousa. Remote Sensing, 9 (11), 1110 (2017). DOI: 10.3390/rs9111110
- G. Avola, A. Matese, E. Riggi. Remote Sensing, 15 (7), 1917 (2023). DOI: 10.3390/rs15071917
- S. Du, Y. Zou, Z. Wang, X. Li, Y. Li, C. Shang, Q. Shen. arXiv:2412.04802, (2024). DOI: 10.48550/arXiv.2412.04802
- J. Yang, L. Xiao, Y.-Q. Zhao, J.C.-W. Chan. IEEE Transactions on Neural Networks and Learning Systems, 35 (9), 13017-13031 (2024). DOI: 10.1109/TNNLS.2023.3266038
- J. Liu, Z. Wu, L. Xiao, X.-J. Wu. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-12 (2021). DOI: 10.1109/TGRS.2022.3143156
- K. Zheng, L. Gao, W. Liao, D. Hong, B. Zhang, X. Cui. IEEE Transactions on Neural Networks and Learning Systems, 59 (3), 2487-2502 (2021). DOI: 10.1109/TGRS.2020.3006534
- J. Yao, D. Hong, J. Chanussot, D. Meng, X. Zhu, Z. Xu. European Conference on Computer Vision (Cham: Springer International Publishing, 2020), p. 208-224. DOI: 10.1007/978-3-030-58526-6_13
- Y. Qu, H. Qi, C. Kwan. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2511-2520 (2018). DOI: 10.48550/arXiv.1904.12175
- S. Li, R. Dian, L. Fang, J.M. Bioucas-Dias. IEEE Transactions on Image Processing, 2018. DOI: 10.1109/TIP.2018.2836307
- M. Simoes, J. Bioucas-Dias, L.B. Almeida, J. Chanussot. IEEE Transactions on Geoscience and Remote Sensing, 2015. DOI: 10.1109/TGRS.2014.2375320
- W. Dong, F. Fu, G. Shi, X. Cao, J. Wu, G. Li, X. Li. IEEE Transactions on Image Processing, 2016. DOI: 10.1109/TIP.2016.2542360
- J. Yang, L. Xiao, Y. Zhao, J.C.-W. Chan. IEEE Transactions on Neural Networks and Learning Systems. 35 (9), 13017-13031 (2023). DOI: 10.1109/TNNLS.2023.3266038
- B. Li, X. Wang, H. Xu. arXiv:2409.06705, 2024. DOI: 10.48550/arXiv.2409.06705
- H. Wang, Y. Xu, Z. Wu, Z. Wei. IEEE Transactions on Neural Networks and Learning Systems, 2024. DOI: 10.1109/TNNLS.2024.3457781
- K. Yang, M. Bai, T. Lu. arXiv preprint arXiv:2407.05279, 2024. DOI: 10.48550/arXiv.2407.05279
- L. Wald. Data Fusion: Definitions and Architectures: Fusion of Images of Different Spatial Resolutions (Presses des MINES, 2002)
- R.A. Schowengerdt. Remote Sensing: Models and Methods for Image Processing, 3rd ed. (Academic Press, London, 2006)
- A. Hore, D. Ziou. 20th International Conference on Pattern Recognition. IEEE, 2366-2369 (2010). DOI: 10.1109/ICPR.2010.579
- Z. Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli. IEEE Transactions on Image Processing, 13 (4), 600-612 (2004). DOI: 10.1109/TIP.2003.819861
- R.H. Yuhas, A.F.H. Goetz, J.W. Boardman. JPL, Summaries of the Third Annual JPL Airborne Geoscience Workshop, vol. 1: AVIRIS Workshop (1992)
- K. Kolikov, G. Krastev, Y. Epitropov, D. Hristozov. Chemometrics and Intelligent Laboratory Systems, 102 (1), 15-19 (2010). DOI: 10.1016/j.chemolab.2010.03.001
- G.H. Golub, C.F. Van Loan. Matrix Computations, 4th ed. (Baltimore, MD, 2013). DOI: 10.56021/9781421407944
- G. Strang. Introduction to Linear Algebra (Wellesley-Cambridge Press, 2022). DOI: 10.1137/1.9781733146678
- K. He, X. Zhang, S. Ren, J. Sun. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p. 770-778 (2016). DOI: 10.1109/CVPR.2016.90
- J.-Y. Zhu, T. Park, P. Isola, A. Efros. Proceedings of the IEEE International Conference on Computer Vision, 2223-2232 (2017). DOI: 10.1109/ICCV.2017.244
- Z. Salahuddin, H.C. Woodruff, A. Chatterjee, P. Lambin. Computers in Biology and Medicine, 140, 105111 (2022). DOI: 10.1016/j.compbiomed.2021.105111
- M. Yako. Optical Review, 1-13 (2025). DOI: 10.1007/s10043-025-01001-x
- M.M. Antony, C.S.S. Sandeep, H.-T. Lim, M.V. Matham. J. Biomedical Photonics \& Engineering, 9 (3), 030304 (2023). DOI: 10.18287/JBPE23.09.030304
- I.A. Bratchenko, V.P. Sherendak, O.O. Myakinin, D.N. Artemyev, A.A. Moryatov, E. Borisova, L. Avramov, L.A. Zherdeva, A.E. Orlov, S.V. Kozlov, V.P. Zakharov J. Biomedical Photonics \& Engineering, 4 (1), 5-12 (2018). DOI: 10.18287/JBPE17.04.010301
- B.V. Grechkin, V.O. Vinokurov, Y.A. Khristoforova, I.A. Matveeva. J. Biomedical Photonics \& Engineering, 9 (4), 50-55 (2023). DOI: 10.18287/JBPE23.09.040304
- I.A. Bratchenko, O.O. Myakinin, V.P. Sherendak, P.N. Volkhin, Y.A. Khristoforova, L.A. Bratchenko, D.N. Artemyev, A.A. Moryatov, O.V. Polschikova, A.S. Machikhin, V.E. Pozhar, S.V. Kozlov, V.P. Zakharov. J. Biomedical Photonics \& Engineering, 4 (4), 040301 (2018). DOI: 10.18287/JBPE18.04.040301
- Z. Lai, Y. Fu, J. Zhang. IEEE Transactions on Neural Networks and Learning Systems, 2024. DOI: 10.1109/TNNLS.2023.3340561