{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:57:47Z","timestamp":1772823467798,"version":"3.50.1"},"reference-count":54,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072345, 41671382"],"award-info":[{"award-number":["62072345, 41671382"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Hyperspectral compression is one of the most common techniques in hyperspectral image processing. Most recent learned image compression methods have exhibited excellent rate-distortion performance for natural images, but they have not been fully explored for hyperspectral compression tasks. In this paper, we propose a trainable network architecture for hyperspectral compression tasks, which not only considers the anisotropic characteristic of hyperspectral images but also embeds an accurate entropy model using the non-Gaussian prior knowledge of hyperspectral images and nonlinear transform. Specifically, we first design a spatial-spectral block, involving a spatial net and a spectral net as the base components of the core autoencoder, which is more consistent with the anisotropic hyperspectral cubes than the existing compression methods based on deep learning. Then, we design a Student\u2019s T hyperprior that merges the statistics of the latents and the side information concepts into a unified neural network to provide an accurate entropy model used for entropy coding. This not only remarkably enhances the flexibility of the entropy model by adjusting various values of the degree of freedom, but also leads to a superior rate-distortion performance. The results illustrate that the proposed compression scheme supersedes the Gaussian hyperprior universally for virtually all learned natural image codecs and the optimal linear transform coding methods for hyperspectral compression. Specifically, the proposed method provides a 1.51% to 59.95% average increase in peak signal-to-noise ratio, a 0.17% to 18.17% average increase in the structural similarity index metric and a 6.15% to 64.60% average reduction in spectral angle mapping over three public hyperspectral datasets compared to the Gaussian hyperprior and the optimal linear transform coding methods.<\/jats:p>","DOI":"10.3390\/rs13214390","type":"journal-article","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T22:24:22Z","timestamp":1635805462000},"page":"4390","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Learned Hyperspectral Compression Using a Student\u2019s T Hyperprior"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4647-6517","authenticated-orcid":false,"given":"Yuanyuan","family":"Guo","sequence":"first","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-8515","authenticated-orcid":false,"given":"Yanwen","family":"Chong","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, China"}]},{"given":"Yun","family":"Ding","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6789-3876","authenticated-orcid":false,"given":"Shaoming","family":"Pan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, China"}]},{"given":"Xiaolin","family":"Gu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,10,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.isprsjprs.2019.09.006","article-title":"Deep Learning Classifiers for Hyperspectral Imaging: A Review","volume":"158","author":"Paoletti","year":"2019","journal-title":"ISPRS J. Photogramm."},{"key":"ref_2","first-page":"38","article-title":"3D Imaging Spectroscopy for Measuring Hyperspectral Patterns on Solid Objects","volume":"31","author":"Kim","year":"2012","journal-title":"ACM Trans. Graph. Tog."},{"key":"ref_3","unstructured":"Nguyen, H.V., Banerjee, A., and Chellappa, R. (2010, January 13\u201318). Tracking via Object Reflectance Using a Hyperspectral Video Camera. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition\u2014Workshops, San Francisco, CA, USA."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1552","DOI":"10.1109\/TPAMI.2003.1251148","article-title":"Face Recognition in Hyperspectral Images","volume":"25","author":"Pan","year":"2003","journal-title":"IEEE Trans. Pattern Anal."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Qu, Y., Qi, H., and Kwan, C. (2018, January 18\u201323). Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00266"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2334","DOI":"10.1109\/TIP.2008.2005824","article-title":"Hyperspectral Image Compression: Adapting SPIHT and EZW to Anisotropic 3-D Wavelet Coding","volume":"17","author":"Christophe","year":"2008","journal-title":"IEEE Trans. Image Process."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1109\/TGRS.2007.894565","article-title":"Transform Coding Techniques for Lossy Hyperspectral Data Compression","volume":"45","author":"Penna","year":"2007","journal-title":"IEEE Trans. Geosci. Remote."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Taubman, D.S., and Marcellin, M.W. (2002). JPEG2000 Image Compression Fundamentals, Standards and Practice, Springer.","DOI":"10.1007\/978-1-4615-0799-4"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1109\/TMM.2008.917357","article-title":"Joined Spectral Trees for Scalable SPIHT-Based Multispectral Image Compression","volume":"10","author":"Khelifi","year":"2008","journal-title":"IEEE Trans. Multimedia"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hou, Y., and Liu, G. (July, January 30). Hyperspectral Image Lossy-to-Lossless Compression Using the 3D Embedded ZeroBlock Coding Alogrithm. Proceedings of the 2008 International Workshop on Earth Observation and Remote Sensing Applications, Beijing, China.","DOI":"10.1109\/EORSA.2008.4620308"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Karami, A., Beheshti, S., and Yazdi, M. (2012, January 2\u20135). Hyperspectral Image Compression Using 3d Discrete Cosine Transform and Support Vector Machine Learning. Proceedings of the 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA), Montreal, QC, Canada.","DOI":"10.1109\/ISSPA.2012.6310664"},{"key":"ref_12","first-page":"444","article-title":"Compression of Hyperspectral Images Using Discerete Wavelet Transform and Tucker Decomposition","volume":"5","author":"Karami","year":"2012","journal-title":"IEEE J. Sel. Top. Appl."},{"key":"ref_13","unstructured":"Schelkens, P., Munteanu, A., Tzannes, A., and Brislawn, C. (2006, January 21\u201324). JPEG2000. Part 10. Volumetric Data Encoding. Proceedings of the 2006 IEEE International Symposium on Circuits and Systems, Kos, Greece."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2103","DOI":"10.1109\/TGRS.2005.853931","article-title":"Quality Criteria Benchmark for Hyperspectral Imagery","volume":"43","author":"Christophe","year":"2005","journal-title":"IEEE Trans. Geosci. Remote."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/LGRS.2006.888109","article-title":"Hyperspectral Image Compression Using JPEG2000 and Principal Component Analysis","volume":"4","author":"Du","year":"2007","journal-title":"IEEE Geosci. Remote. S"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.patrec.2018.09.013","article-title":"Hyperspectral Image Compression Based on Simultaneous Sparse Representation and General-Pixels","volume":"116","author":"Fu","year":"2018","journal-title":"Pattern Recogn. Lett."},{"key":"ref_17","first-page":"139","article-title":"Perceptually Lossless Compression for Mastcam Multispectral Images: A Comparative Study","volume":"10","author":"Kwan","year":"2019","journal-title":"J. Signal. Inf. Process."},{"key":"ref_18","first-page":"96","article-title":"New Results in Perceptually Lossless Compression of Hyperspectral Images","volume":"10","author":"Kwan","year":"2019","journal-title":"J. Signal. Inf. Process."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chakrabarti, A., and Zickler, T. (2011, January 20\u201325). Statistics of Real-World Hyperspectral Images. Proceedings of the CVPR 2011, Colorado Springs, CO, USA.","DOI":"10.1109\/CVPR.2011.5995660"},{"key":"ref_20","unstructured":"Lee, J., Cho, S., and Beack, S.-K. (2018). Context-Adaptive Entropy Model for End-to-End Optimized Image Compression. arXiv."},{"key":"ref_21","unstructured":"Ball\u00e9, J., Laparra, V., and Simoncelli, E.P. (2017, January 24\u201326). End-to-End Optimized Image Compression. Proceedings of the 5th International Conference on Learning Representations, Toulon, France."},{"key":"ref_22","unstructured":"Golinski, A., Pourreza, R., Yang, Y., Sautiere, G., and Cohen, T.S. (2020). Feedback Recurrent Autoencoder for Video Compression. arXiv."},{"key":"ref_23","unstructured":"Mentzer, F., Toderici, G., Tschannen, M., and Agustsson, E. (2020). High-Fidelity Generative Image Compression. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Toderici, G., Vincent, D., Johnston, N., Hwang, S.J., Minnen, D., Shor, J., and Covell, M. (2017, January 21\u201326). Full Resolution Image Compression with Recurrent Neural Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.577"},{"key":"ref_25","unstructured":"Minnen, D., Ball\u00e9, J., and Toderici, G. (2018). Joint Autoregressive and Hierarchical Priors for Learned Image Compression. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Sun, H., Takeuchi, M., and Katto, J. (2020, January 13\u201319). Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3612","DOI":"10.1109\/TIP.2020.2963956","article-title":"Learning a Single Tucker Decomposition Network for Lossy Image Compression With Multiple Bits-per-Pixel Rates","volume":"29","author":"Cai","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Mentzer, F., Agustsson, E., Tschannen, M., Timofte, R., and Gool, L.V. (2019, January 15\u201320). Practical Full Resolution Learned Lossless Image Compression. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01088"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Choi, Y., El-Khamy, M., and Lee, J. (2019, January 15\u201320). Variable Rate Deep Image Compression with a Conditional Autoencoder. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/ICCV.2019.00324"},{"key":"ref_30","unstructured":"Ball\u00e9, J., Minnen, D., Singh, S., Hwang, S.J., and Johnston, N. (2018). Variational Image Compression with a Scale Hyperprior. arXiv."},{"key":"ref_31","unstructured":"Liu, H., Chen, T., Shen, Q., Yue, T., and Ma, Z. (2018). Deep Image Compression via End-to-End Learning. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3179","DOI":"10.1109\/TIP.2021.3058615","article-title":"End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling","volume":"30","author":"Chen","year":"2021","journal-title":"IEEE Trand. Image Process."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Guo, Z., Wu, Y., Feng, R., Zhang, Z., and Chen, Z. (2020, January 14\u201319). 3-D Context Entropy Model for Improved Practical Image Compression. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00066"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3446","DOI":"10.1109\/TPAMI.2020.2983926","article-title":"Learning Content-Weighted Deep Image Compression","volume":"43","author":"Li","year":"2019","journal-title":"IEEE Trans. Pattern Anal."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the Dimensionality of Data with Neural Networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"ref_36","unstructured":"Theis, L., Shi, W., Cunningham, A., and Husz\u00e1r, F. (2017). Lossy Image Compression with Compressive Autoencoders. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Habibian, A., Rozendaal, T., van Tomczak, J.M., and Cohen, T.S. (November, January 27). Video CompressionWith Rate-Distortion Autoencoders. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.","DOI":"10.1109\/ICCV.2019.00713"},{"key":"ref_38","unstructured":"Ball\u00e9, J., Laparra, V., and Simoncelli, E.P. (2015). Density Modeling of Images Using a Generalized Normalization Transformation. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Mentzer, F., Agustsson, E., Tschannen, M., Timofte, R., and Gool, L.V. (2018, January 18\u201323). Conditional Probability Models for Deep Image Compression. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00462"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Johnston, N., Vincent, D., Minnen, D., Covell, M., Singh, S., Chinen, T., Hwang, S.J., Shor, J., and Toderici, G. (2018, January 18\u201323). Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00461"},{"key":"ref_41","first-page":"855","article-title":"Scale Mixtures of Gaussians and the Statistics of Natural Images","volume":"12","author":"Wainwright","year":"1999","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Takahashi, H., Iwata, T., Yamanaka, Y., Yamada, M., and Yagi, S. (2018, January 13\u201319). Student-t Variational Autoencoder for Robust Density Estimation. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Stockholm, Sweden.","DOI":"10.24963\/ijcai.2018\/374"},{"key":"ref_43","unstructured":"Abiri, N., and Ohlsson, M. (2020). Variational Auto-Encoders with Student\u2019s t-Prior. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1109\/79.952802","article-title":"Theoretical Foundations of Transform Coding","volume":"18","author":"Goyal","year":"2001","journal-title":"IEEE Signal. Proc. Mag."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1109\/TIT.1981.1056282","article-title":"Universal Modeling and Coding","volume":"27","author":"Rissanen","year":"1981","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.1109\/29.90373","article-title":"Efficient Bit Allocation for an Arbitrary Set of Quantizers (Speech Coding)","volume":"36","author":"Shoham","year":"1988","journal-title":"IEEE Trans. Acoust. Speech Signal. Process."},{"key":"ref_47","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-Encoding Variational Bayes. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3130800.3130810","article-title":"High-Quality Hyperspectral Reconstruction Using a Spectral Prior","volume":"36","author":"Choi","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"2241","DOI":"10.1109\/TIP.2010.2046811","article-title":"Generalized Assorted Pixel Camera: Postcapture Control of Resolution, Dynamic Range, and Spectrum","volume":"19","author":"Yasuma","year":"2010","journal-title":"IEEE Trans. Image Process."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Elderton, W.P., and Johnson, N.L. (1969). Systems of Frequency Curves, Cambridge University.","DOI":"10.1017\/CBO9780511569654"},{"key":"ref_51","unstructured":"Wang, Z., Simoncelli, E.P., and Bovik, A.C. (2003, January 9\u201312). Multi-Scale Structural Similarity for Image Quality Assessment. Proceedings of the Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, Pacific Grove, CA, USA."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/0034-4257(93)90013-N","article-title":"The Spectral Image Processing System (SIPS)\u2014Interactive Visualization and Analysis of Imaging Spectrometer Data","volume":"44","author":"Kruse","year":"1993","journal-title":"Remote Sens. Environ."},{"key":"ref_53","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_54","unstructured":"Tang, X., and Pearlman, W.A. (2004, January 24\u201327). Lossy-to-Lossless Block-Based Compression of Hyperspectral Volumetric Data. Proceedings of the 2004 International Conference on Image Processing, Singapore."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/21\/4390\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:23:47Z","timestamp":1760167427000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/21\/4390"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,31]]},"references-count":54,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2021,11]]}},"alternative-id":["rs13214390"],"URL":"https:\/\/doi.org\/10.3390\/rs13214390","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,31]]}}}