🌇🌆 Hyperspectral Image Fusion Benchmarking 🏙🌃

Comparison of the multispectral (MS) and hyperspectral (HS) image fusion techniques used for the spatial resolution enhancement of HS images.

Existing hyperspectral imaging systems produce images that lack spatial resolution due to hardware limitations. Even with the proven efficacy of this technology in several computer vision tasks, the aforementioned limitation obstructs its applicability. Contrarily, conventional RGB images have a much larger resolution with just three spectra. Since the issue of low resolution images arises from hardware limitations, there have been several developments in software-based approaches to improve the spatial resolution of hyperspectral images.

This work allows for an easy-to-use framework for testing and comparing existing hyperspectral image fusion (HIF) methods for spatial resolution enhancement.

Content

• Citation
• Instructions
• Datasets
• Methods
  • Implemented Methods
  • Other Methods
  • Extensions
• Metrics
• Requirements

Citation

If you use any part of this work, please use the following citation:

Magalhães, Miguel. “Hyperspectral Image Fusion: A Comprehensive Review”. Master’s Programme in Imaging and Light in Extended Reality (IMLEX). MSc. thesis. KU Leuven, 2022.

@mastersthesis{hif_review_2022,
    title={Hyperspectral Image Fusion: A Comprehensive Review},
    author={Miguel Magalhães},
    year={2022},
    school={KU Leuven},
    note={Master’s Programme in Imaging and Light in Extended Reality (IMLEX)}
}

Instructions

Download and process dataset(s) (e.g.: CAVE, Harvard). This will also create MS image and downsampled HS image by a factor of 4, 8 and 16 (or any other power of 2 that you add as input to the script):

python main/dataset_CAVE.py

Run all algorithms over the datasets (you can edit run.py to customize the combinatory that you wish to process in terms of datasets, methods and scaling factors):

python main/run.py

Finally, compute the metrics that compare the output of the image fusion methods with the ground truth data:

python main/metrics.py

Datasets

Compilation of publically available hyperspectral datasets. The datasets in bold can be automatically downloaded and processed using the respective script main/dataset_{name}.py as per the instructions above.

Dataset	Year	Qty	Resolution*	Download	Paper
CAVE	2008	32	512x512x31 [400,700]nm	All	Yasuma, F., Mitsunaga, T., Iso, D., & Nayar, S. K. (2010). Generalized assorted pixel camera: postcapture control of resolution, dynamic range, and spectrum. IEEE transactions on image processing, 19(9), 2241-2253.
Harvard	2011	77	1040x1392x31 [420,720]nm	All	Chakrabarti, A., & Zickler, T. (2011, June). Statistics of real-world hyperspectral images. In CVPR 2011 (pp. 193-200). IEEE.
NUS**	2014	88	?×?x31 [400,700]nm	-	Nguyen, R. M., Prasad, D. K., & Brown, M. S. (2014, September). Training-based spectral reconstruction from a single RGB image. In European Conference on Computer Vision (pp. 186-201). Springer, Cham.
iCVL**	2016	201	1392×1300x519 [400,1000]nm	All	Arad, B., & Ben-Shahar, O. (2016, October). Sparse recovery of hyperspectral signal from natural RGB images. In European Conference on Computer Vision (pp. 19-34). Springer, Cham.

As a demo image, we include the hyperspectral measurement of a resolution chart (ISO 12233:2017 Edge eSFR Inkjet chart) with a resolution of 512x512x108 and a wavelength interval from 403.09nm to 717.54nm, measured with a Specim IQ camera.

Additionally, remote sensing hyperspectral scenes are also available and widely used accross the field.

Click to show list of Hyperspectral Remote Sensing Scenes

Below, we list the publically available hyperspectral remote sensing scenes. The ones in italic were collected by the GIC from EHU, and can be downloaded using main/_dataset_EHU.py, the processing part to generate the MS and downsampled HS images is still missing.

Dataset	Year	Qty	Resolution*	Download	Paper
Indian Pines	1992	1	145x145x220 [400,2500]nm***	URL	Baumgardner, M. F., Biehl, L. L., & Landgrebe, D. A. (2015). 220 band aviris hyperspectral image data set: June 12, 1992 indian pine test site 3. Purdue University Research Repository, 10, R7RX991C. / AVIRIS NASA.
Kennedy Space Center	1996	1	512x614x176 [400,2500]nm***	URL	AVIRIS NASA. Information about removed bands unavailable.
Salinas	1998	1	512x217x224 [400,2500]nm***	Full Subscene	AVIRIS NASA.
Cuprite	1998	1	512x614x224 [400,2500]nm***	URL	AVIRIS NASA.
Botswana	2001	1	1476x256x145 [400,2500]nm***	URL	AVIRIS NASA. Information about removed bands is incorrect.
Pavia	2008	2	?x?x103 [430,860]nm	Centre University	Dataset provided by Prof. Paolo Gamba from the Telecommunications and Remote Sensing Laboratory, Pavia university (Italy).
Chikusei**	2016	1	2517x2335x128 [363,1018]nm	URL	Yokoya, N., & Iwasaki, A. (2016). Airborne hyperspectral data over Chikusei. Space Appl. Lab., Univ. Tokyo, Tokyo, Japan, Tech. Rep. SAL-2016-05-27.
WHU-Hi**	2020	3	varies	All	Zhong, Y., Hu, X., Luo, C., Wang, X., Zhao, J., & Zhang, L. (2020). WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF. Remote Sensing of Environment, 250, 112012.

Further remote sensing scenes can be found at rslab.ut.ac.ir/data.

* the first line represents the size of the spectral cubes (width x height x spectral bands), and the second line the wavelength interval of the dataset.

** script for automatic download and processing not implemented yet.

*** some bands in between were removed.

Methods

Hyperspectral image fusion (HIF) methods with code publicly available.

Implemented Methods

Methods with code available together with an implemented wrapper in this repository (some of the wrappers are adapted from "Hyperspectral and Multispectral Data Fusion: A Comparative Review" ¹).

Method	Year	Code	Paper
SFIM*	2000	Matlab	Liu, J. G. (2000). Smoothing filter-based intensity modulation: A spectral preserve image fusion technique for improving spatial details. International Journal of Remote Sensing, 21(18), 3461-3472.
MAPSMM	2004	Matlab	Eismann, M. T. (2004). Resolution enhancement of hyperspectral imagery using maximum a posteriori estimation with a stochastic mixing model. University of Dayton.
GLP*	2006	Matlab	Aiazzi, B., Alparone, L., Baronti, S., Garzelli, A., & Selva, M. (2006). MTF-tailored multiscale fusion of high-resolution MS and Pan imagery. Photogrammetric Engineering & Remote Sensing, 72(5), 591-596.
GSA	2007	Matlab	Aiazzi, B., Baronti, S., & Selva, M. (2007). Improving component substitution pansharpening through multivariate regression of MS +Pan data. IEEE Transactions on Geoscience and Remote Sensing, 45(10), 3230-3239.
CNMF	2011	Python Matlab	Yokoya, N., Yairi, T., & Iwasaki, A. (2011, July). Coupled non-negative matrix factorization (CNMF) for hyperspectral and multispectral data fusion: Application to pasture classification. In 2011 IEEE International Geoscience and Remote Sensing Symposium (pp. 1779-1782). IEEE.
GSOMP	2014	Matlab	Akhtar, N., Shafait, F., & Mian, A. (2014, September). Sparse spatio-spectral representation for hyperspectral image super-resolution. In European conference on computer vision (pp. 63-78). Springer, Cham.
HySure	2014	Matlab	Simoes, M., Bioucas-Dias, J., Almeida, L. B., & Chanussot, J. (2014, October). Hyperspectral image superresolution: An edge-preserving convex formulation.Hysure In 2014 IEEE International Conference on Image Processing (ICIP) (pp. 4166-4170). IEEE.
BayesianSparse (very slow)	2015	Matlab	Akhtar, N., Shafait, F., & Mian, A. (2015). Bayesian sparse representation for hyperspectral image super resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3631-3640).
FUSE	2015	Matlab	Wei, Q., Dobigeon, N., & Tourneret, J. Y. (2015). Bayesian fusion of multi-band images. IEEE Journal of Selected Topics in Signal Processing, 9(6), 1117-1127.
SupResPALM	2015	Matlab	Lanaras, C., Baltsavias, E., & Schindler, K. (2015). Hyperspectral super-resolution by coupled spectral unmixing. In Proceedings of the IEEE international conference on computer vision (pp. 3586-3594).
NSSR	2016	Matlab	Dong, W., Fu, F., Shi, G., Cao, X., Wu, J., Li, G., & Li, X. (2016). Hyperspectral image super-resolution via non-negative structured sparse representation. IEEE Transactions on Image Processing, 25(5), 2337-2352.
CNN-FUS	2018	Matlab	Dian, R., Li, S., & Kang, X. (2020). Regularizing hyperspectral and multispectral image fusion by CNN denoiser. IEEE transactions on neural networks and learning systems, 32(3), 1124-1135.
CSTF (unstable)	2018	Matlab	Li, S., Dian, R., Fang, L., & Bioucas-Dias, J. M. (2018). Fusing hyperspectral and multispectral images via coupled sparse tensor factorization. IEEE Transactions on Image Processing, 27(8), 4118-4130.
LTMR	2019	Matlab	Dian, R., & Li, S. (2019). Hyperspectral image super-resolution via subspace-based low tensor multi-rank regularization. IEEE Transactions on Image Processing, 28(10), 5135-5146.
LTTR	2019	Matlab	Dian, R., Li, S., & Fang, L. (2019). Learning a low tensor-train rank representation for hyperspectral image super-resolution. IEEE transactions on neural networks and learning systems, 30(9), 2672-2683.

* pan-sharpening methods adapted to HS–MS fusion ¹ via hypersharpening ².

Other Methods

Code is available but wrapper is not implemented yet.

Method	Year	Code	Paper
MF	2011	Matlab	Kawakami, R., Matsushita, Y., Wright, J., Ben-Ezra, M., Tai, Y. W., & Ikeuchi, K. (2011, June). High-resolution hyperspectral imaging via matrix factorization. In CVPR 2011 (pp. 2329-2336). IEEE.
SNMF	2013	Matlab	Wycoff, E., Chan, T. H., Jia, K., Ma, W. K., & Ma, Y. (2013, May). A non-negative sparse promoting algorithm for high resolution hyperspectral imaging. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 1409-1413). IEEE.
BSR	2015	Matlab	Wei, Q., Bioucas-Dias, J., Dobigeon, N., & Tourneret, J. Y. (2015). Hyperspectral and multispectral image fusion based on a sparse representation. IEEE Transactions on Geoscience and Remote Sensing, 53(7), 3658-3668.
BlindFuse	2016	Matlab	Wei, Q., Bioucas-Dias, J., Dobigeon, N., Tourneret, J. Y., & Godsill, S. (2016, September). Blind model-based fusion of multi-band and panchromatic images. In 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) (pp. 21-25). IEEE.
FUMI	2016	Matlab	Wei, Q., Bioucas-Dias, J., Dobigeon, N., Tourneret, J. Y., Chen, M., & Godsill, S. (2016). Multiband image fusion based on spectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 54(12), 7236-7249.
MSDCNN *	2017	Python	Yuan, Q., Wei, Y., Meng, X., Shen, H., & Zhang, L. (2018). A multiscale and multidepth convolutional neural network for remote sensing imagery pan-sharpening. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(3), 978-989.
BRS	2018	Matlab	Bungert, L., Coomes, D. A., Ehrhardt, M. J., Rasch, J., Reisenhofer, R., & Schönlieb, C. B. (2018). Blind image fusion for hyperspectral imaging with the directional total variation. Inverse Problems, 34(4), 044003.
CMS	2018	Matlab	Zhang, L., Wei, W., Bai, C., Gao, Y., & Zhang, Y. (2018). Exploiting clustering manifold structure for hyperspectral imagery super-resolution. IEEE Transactions on Image Processing, 27(12), 5969-5982.
DHSIS	2018	Python	Dian, R., Li, S., Guo, A., & Fang, L. (2018). Deep hyperspectral image sharpening. IEEE transactions on neural networks and learning systems, 29(11), 5345-5355.
SSF-CNN & PDCon-SSF *	2018	Python	Han, X. H., Shi, B., & Zheng, Y. (2018, October). SSF-CNN: Spatial and spectral fusion with CNN for hyperspectral image super-resolution. In 2018 25th IEEE International Conference on Image Processing (ICIP) (pp. 2506-2510). IEEE.
STEREO	2018	Matlab	Kanatsoulis, C. I., Fu, X., Sidiropoulos, N. D., & Ma, W. K. (2018). Hyperspectral super-resolution: A coupled tensor factorization approach. IEEE Transactions on Signal Processing, 66(24), 6503-6517.
uSDN	2018	Python	Qu, Y., Qi, H., & Kwan, C. (2018). Unsupervised sparse dirichlet-net for hyperspectral image super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2511-2520).
DBIN	2019	Python	Wang, W., Zeng, W., Huang, Y., Ding, X., & Paisley, J. (2019). Deep blind hyperspectral image fusion. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 4150-4159).
CUCaNet	2020	Python	Yao, J., Hong, D., Chanussot, J., Meng, D., Zhu, X., & Xu, Z. (2020, August). Cross-attention in coupled unmixing nets for unsupervised hyperspectral super-resolution. In European Conference on Computer Vision (pp. 208-224). Springer, Cham.
GDD	2020	Python	Uezato, T., Hong, D., Yokoya, N., & He, W. (2020, August). Guided deep decoder: Unsupervised image pair fusion. In European Conference on Computer Vision (pp. 87-102). Springer, Cham.
TFNet & ResTFNet *	2020	Python	Liu, X., Liu, Q., & Wang, Y. (2020). Remote sensing image fusion based on two-stream fusion network. Information Fusion, 55, 1-15.
MHF-net	2020	Python	Xie, Q., Zhou, M., Zhao, Q., Xu, Z., & Meng, D. (2020). MHF-net: An interpretable deep network for multispectral and hyperspectral image fusion. IEEE Transactions on Pattern Analysis and Machine Intelligence.
PZRes-Net	2020	Python	Zhu, Z., Hou, J., Chen, J., Zeng, H., & Zhou, J. (2020). Hyperspectral image super-resolution via deep progressive zero-centric residual learning. IEEE Transactions on Image Processing, 30, 1423-1438.
RecHSISR	2020	Python	Wei, W., Nie, J., Zhang, L., & Zhang, Y. (2020). Unsupervised recurrent hyperspectral imagery super-resolution using pixel-aware refinement. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-15.
SSRNET	2020	Python	Zhang, X., Huang, W., Wang, Q., & Li, X. (2020). SSR-NET: Spatial–spectral reconstruction network for hyperspectral and multispectral image fusion. IEEE Transactions on Geoscience and Remote Sensing, 59(7), 5953-5965.
TONWMD	2020	Python	Shen, D., Liu, J., Xiao, Z., Yang, J., & Xiao, L. (2020). A twice optimizing net with matrix decomposition for hyperspectral and multispectral image fusion. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 4095-4110.
Two-CNN	2020	Matlab	Yang, J., Zhao, Y. Q., & Chan, J. C. W. (2018). Hyperspectral and multispectral image fusion via deep two-branches convolutional neural network. Remote Sensing, 10(5), 800.
UAL	2020	Python	Zhang, L., Nie, J., Wei, W., Zhang, Y., Liao, S., & Shao, L. (2020). Unsupervised adaptation learning for hyperspectral imagery super-resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 3073-3082).
ADMM-HFNET	2021	Python	Shen, D., Liu, J., Wu, Z., Yang, J., & Xiao, L. (2021). ADMM-HFNet: A Matrix Decomposition-Based Deep Approach for Hyperspectral Image Fusion. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-17.
Fusformer	2021	Python	Hu, J. F., Huang, T. Z., & Deng, L. J. (2021). Fusformer: A Transformer-based Fusion Approach for Hyperspectral Image Super-resolution. arXiv preprint arXiv:2109.02079.
MoG-DCN	2021	Python	Dong, W., Zhou, C., Wu, F., Wu, J., Shi, G., & Li, X. (2021). Model-guided deep hyperspectral image super-resolution. IEEE Transactions on Image Processing, 30, 5754-5768.
HyperFusion	2021	Python	Tian, X., Zhang, W., Chen, Y., Wang, Z., & Ma, J. (2021). Hyperfusion: A computational approach for hyperspectral, multispectral, and panchromatic image fusion. IEEE Transactions on Geoscience and Remote Sensing.
HSRnet	2021	Python	Dong, W., Zhou, C., Wu, F., Wu, J., Shi, G., & Li, X. (2021). Model-guided deep hyperspectral image super-resolution. IEEE Transactions on Image Processing, 30, 5754-5768.
TSFN	2021	Python	Wang, X., Chen, J., Wei, Q., & Richard, C. (2021). Hyperspectral Image Super-Resolution via Deep Prior Regularization with Parameter Estimation. IEEE Transactions on Circuits and Systems for Video Technology.
u2MDN	2021	Python	Qu, Y., Qi, H., Kwan, C., Yokoya, N., & Chanussot, J. (2021). Unsupervised and unregistered hyperspectral image super-resolution with mutual Dirichlet-Net. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-18.
DBSR	2022	Python	Zhang, L., Nie, J., Wei, W., Li, Y., & Zhang, Y. (2020). Deep blind hyperspectral image super-resolution. IEEE Transactions on Neural Networks and Learning Systems, 32(6), 2388-2400.
DHIF	2022	Python	Huang, T., Dong, W., Wu, J., Li, L., Li, X., & Shi, G. (2022). Deep Hyperspectral Image Fusion Network With Iterative Spatio-Spectral Regularization. IEEE Transactions on Computational Imaging, 8, 201-214.
HSI-CSR	2022	Caffe	Fu, Y., Zhang, T., Zheng, Y., Zhang, D., & Huang, H. (2019). Hyperspectral image super-resolution with optimized RGB guidance. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 11661-11670).
RGBaux	2022	Python	Li, K., Dai, D., & Van Gool, L. (2022). Hyperspectral Image Super-Resolution with RGB Image Super-Resolution as an Auxiliary Task. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 3193-3202).
MIAE	2022	Python	Liu, J., Wu, Z., Xiao, L., & Wu, X. J. (2022). Model Inspired Autoencoder for Unsupervised Hyperspectral Image Super-Resolution. IEEE Transactions on Geoscience and Remote Sensing.
NonRegSRNet	2022	Python	Zheng, K., Gao, L., Hong, D., Zhang, B., & Chanussot, J. (2021). NonRegSRNet: A Nonrigid Registration Hyperspectral Super-Resolution Network. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-16.
RAFnet	2022	Python	Lu, R., Chen, B., Cheng, Z., & Wang, P. (2020). RAFnet: Recurrent attention fusion network of hyperspectral and multispectral images. Signal Processing, 177, 107737.
SpfNet	2022	Python	Liu, J., Shen, D., Wu, Z., Xiao, L., Sun, J., & Yan, H. (2022). Patch-Aware Deep Hyperspectral and Multispectral Image Fusion by Unfolding Subspace-Based Optimization Model. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.
UDALN	2022	Python	Li, J., Zheng, K., Yao, J., Gao, L., & Hong, D. (2022). Deep Unsupervised Blind Hyperspectral and Multispectral Data Fusion. IEEE Geoscience and Remote Sensing Letters, 19, 1-5.

* code available in another repo (from a different paper)

Extensions

Extensions of HSI methods with publicly available code. These should be regarded as extensions to the base pipelines and not as a separate methods. These take as input a super-resolution image (output of the HSI method) together with the MS and HS images (original HSI method input); and provide as input an improved super-resolution image. The wrappers for these extensions are not implemented in this repository yet.

Method	Year	Code	Paper
TVTVHS	2021	Python	Vella, M., Zhang, B., Chen, W., & Mota, J. F. (2021, September). Enhanced Hyperspectral Image Super-Resolution via RGB Fusion and TV-TV Minimization. In 2021 IEEE International Conference on Image Processing (ICIP) (pp. 3837-3841). IEEE.
DeepGrad	2022	Matlab	Wang, X., Chen, J., & Richard, C. (2022). Hyperspectral Image Super-resolution with Deep Priors and Degradation Model Inversion. arXiv preprint arXiv:2201.09851.

Metrics

To evaluate the quality of the methods, the output of the superresolution methods is compared with the ground truth of the dataset. We compute several metrics (listed below) using sewar.

Acronym	Full Name	Paper
RMSE	Root Mean Squared Error	-
PSNR	Peak Signal-to-Noise Ratio	Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4), 600-612.
SSIM	Structural Similarity Index	Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4), 600-612.
UQI	Universal Quality Image Index	Wang, Z., & Bovik, A. C. (2002). A universal image quality index. IEEE signal processing letters, 9(3), 81-84.
MS-SSIM	Multi-scale Structural Similarity Index	Wang, Z., Simoncelli, E. P., & Bovik, A. C. (2003, November). Multiscale structural similarity for image quality assessment. In The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 (Vol. 2, pp. 1398-1402). Ieee.
ERGAS	Erreur Relative Globale Adimensionnelle de Synthèse	Wald, L. (2000, January). Quality of high resolution synthesised images: Is there a simple criterion?. In Third conference" Fusion of Earth data: merging point measurements, raster maps and remotely sensed images" (pp. 99-103). SEE/URISCA.
SCC	Spatial Correlation Coefficient	Zhou, J., Civco, D. L., & Silander, J. A. (1998). A wavelet transform method to merge Landsat TM and SPOT panchromatic data. International journal of remote sensing, 19(4), 743-757.
RASE	Relative Average Spectral Error	González-Audícana, M., Saleta, J. L., Catalán, R. G., & García, R. (2004). Fusion of multispectral and panchromatic images using improved IHS and PCA mergers based on wavelet decomposition. IEEE Transactions on Geoscience and Remote sensing, 42(6), 1291-1299.
SAM	Spectral Angle Mapper	Yuhas, R. H., Goetz, A. F., & Boardman, J. W. (1992, June). Discrimination among semi-arid landscape endmembers using the spectral angle mapper (SAM) algorithm. In JPL, Summaries of the Third Annual JPL Airborne Geoscience Workshop. Volume 1: AVIRIS Workshop.
VIF	Visual Information Fidelity	Sheikh, H. R., & Bovik, A. C. (2006). Image information and visual quality. IEEE Transactions on image processing, 15(2), 430-444.
PSNR-B	Block Sensitive - Peak Signal-to-Noise Ratio	Yim, C., & Bovik, A. C. (2010). Quality assessment of deblocked images. IEEE Transactions on Image Processing, 20(1), 88-98.
Q2ⁿ *	Q2ⁿ	Garzelli, A., & Nencini, F. (2009). Hypercomplex quality assessment of multi/hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 6(4), 662-665.

* to be implemented in the future.

Requirements

• pip install -r auxiliary/requirements.txt
• SPAMS-2.6
• MatConvNet

Footnotes

1. Yokoya, N., Grohnfeldt, C., & Chanussot, J. (2017). Hyperspectral and multispectral data fusion: A comparative review of the recent literature. IEEE Geoscience and Remote Sensing Magazine, 5(2), 29-56. [paper] [code] ↩ ↩²

2. Selva, M., Aiazzi, B., Butera, F., Chiarantini, L., & Baronti, S. (2015). Hyper-sharpening: A first approach on SIM-GA data. IEEE Journal of selected topics in applied earth observations and remote sensing, 8(6), 3008-3024. [paper] ↩