{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T03:18:37Z","timestamp":1760239117573,"version":"build-2065373602"},"reference-count":25,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2020,10,13]],"date-time":"2020-10-13T00:00:00Z","timestamp":1602547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Spectral reconstruction from RGB or spectral super-resolution (SSR) offers a cheap alternative to otherwise costly and more complex spectral imaging devices. In recent years, deep learning based methods consistently achieved the best reconstruction quality in terms of spectral error metrics. However, there are important properties that are not maintained by deep neural networks. This work is primarily dedicated to scale invariance, also known as brightness invariance or exposure invariance. When RGB signals only differ in their absolute scale, they should lead to identical spectral reconstructions apart from the scaling factor. Scale invariance is an essential property that signal processing must guarantee for a wide range of practical applications. At the moment, scale invariance can only be achieved by relying on a diverse database during network training that covers all possibly occurring signal intensities. In contrast, we propose and evaluate a fundamental approach for deep learning based SSR that holds the property of scale invariance by design and is independent of the training data. The approach is independent of concrete network architectures and instead focuses on reevaluating what neural networks should actually predict. The key insight is that signal magnitudes are irrelevant for acquiring spectral reconstructions from camera signals and are only useful for a potential signal denoising.<\/jats:p>","DOI":"10.3390\/s20205789","type":"journal-article","created":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T21:24:39Z","timestamp":1602710679000},"page":"5789","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Brightness Invariant Deep Spectral Super-Resolution"],"prefix":"10.3390","volume":"20","author":[{"given":"Tarek","family":"Stiebel","sequence":"first","affiliation":[{"name":"Institute of Imaging &amp; Computer Vision, RWTH Aachen University, 52072 Aachen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1672-2185","authenticated-orcid":false,"given":"Dorit","family":"Merhof","sequence":"additional","affiliation":[{"name":"Institute of Imaging &amp; Computer Vision, RWTH Aachen University, 52072 Aachen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,10,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"4817","DOI":"10.1364\/AO.34.004817","article-title":"Computed-tomography imaging spectrometer: Experimental calibration and reconstruction results","volume":"34","author":"Descour","year":"1995","journal-title":"Appl. Opt."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1898","DOI":"10.1364\/AO.45.001898","article-title":"Spatial-spectral modulating snapshot hyperspectral imager","volume":"45","author":"Johnson","year":"2006","journal-title":"Appl. Opt."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1109\/MSP.2016.2582378","article-title":"Computational Snapshot Multispectral Cameras: Toward dynamic capture of the spectral world","volume":"33","author":"Cao","year":"2016","journal-title":"IEEE Signal Process Mag."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1109\/MSP.2013.2278763","article-title":"Compressive Coded Aperture Spectral Imaging: An Introduction","volume":"31","author":"Arce","year":"2014","journal-title":"IEEE Signal Process Mag."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wang, L., Sun, C., Zhang, M., Fu, Y., and Huang, H. (2020, January 14\u201319). DNU: Deep Non-Local Unrolling for Computational Spectral Imaging. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00173"},{"key":"ref_6","unstructured":"Brauers, J., and Aach, T. (2006). A Color Filter Array Based Multispectral Camera. 12. Workshop Farbbildverarbeitung, German Color Group."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Nguyen, R.M.H., Prasad, D.K., and Brown, M.S. (2014, January 6\u201312). Training-Based Spectral Reconstruction from a Single RGB Image. Proceedings of the European Conference on Computer Vision (ECCV), Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10584-0_13"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Arad, B., and Shahar, O. (2016, January 11\u201314). Sparse Recovery of Hyperspectral Signal from Natural RGB Images. Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46478-7_2"},{"key":"ref_9","unstructured":"Aeschbacher, J., Wu, J., and Timofte, R. (2017, January 22\u201329). In Defense of Shallow Learned Spectral Reconstruction from RGB Images. Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, Italy."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Timofte, R., De Smet, V., and Van Gool, L. (2014, January 1\u20135). A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution. Proceedings of the Asian Conference on Computer Vision, Singapore.","DOI":"10.1109\/ICCV.2013.241"},{"key":"ref_11","unstructured":"Arad, B., Timofte, R., Ben-Shahar, O., Lin, Y.T., and Finlayson, G. (2020, January 14\u201319). NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, Seattle, WA, USA."},{"key":"ref_12","unstructured":"Arad, B., Ben-Shahar, O., and Timofte, R. (2018, January 19\u201321). NTIRE 2018 Challenge on Spectral Reconstruction From RGB Images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Salt Lake City, UT, USA."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhang, L., Lang, Z., Wang, P., Wei, W., Liao, S., Shao, L., and Zhang, Y. (2020, January 7\u201312). Pixel-Aware Deep Function-Mixture Network for Spectral Super-Resolution. Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, New York, NY, USA.","DOI":"10.1609\/aaai.v34i07.6978"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Po, L.M., Yan, Q., Liu, W., and Lin, T. (2020, January 14\u201319). Hierarchical Regression Network for Spectral Reconstruction From RGB Images. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00219"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Li, J., Wu, C., Song, R., Li, Y., and Liu, F. (2020, January 14\u201319). Adaptive Weighted Attention Network With Camera Spectral Sensitivity Prior for Spectral Reconstruction From RGB Images. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00239"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yan, Y., Zhang, L., Li, J., Wei, W., and Zhang, Y. (2018, January 23\u201326). Accurate Spectral Super-Resolution from Single RGB Image Using Multi-scale CNN. Proceedings of theChinese Conference on Pattern Recognition and Computer Vision (PRCV), Guangzhou, China.","DOI":"10.1007\/978-3-030-03335-4_18"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Shi, Z., Chen, C., Xiong, Z., Liu, D., and Wu, F. (2018, January 19\u201321). HSCNN+: Advanced CNN-Based Hyperspectral Recovery from RGB Images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPRW.2018.00139"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Stiebel, T., Koppers, S., Seltsam, P., and Merhof, D. (2018, January 19\u201321). Reconstructing Spectral Images from RGB-Images Using a Convolutional Neural Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPRW.2018.00140"},{"key":"ref_19","unstructured":"Galliani, S., Lanaras, C., Marmanis, D., Baltsavias, E., and Schindler, K. (2017). Learned Spectral Super-Resolution. arXiv."},{"key":"ref_20","unstructured":"Lin, Y.T., and Finlayson, G. (2019, January 21\u201325). Exposure Invariance in Spectral Reconstruction from RGB Images. Proceedings of the Color and Imaging Conference, Paris, France."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"4311","DOI":"10.1109\/TSP.2006.881199","article-title":"K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation","volume":"54","author":"Aharon","year":"2006","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_22","unstructured":"Pati, Y.C., Rezaiifar, R., and Krishnaprasad, P.S. (1993, January 1\u20133). Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition. Proceedings of the 27th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, USA."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 13\u201316). Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Proceedings of the IEEE International Conference on Computer Vision (ICCV 2015), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Windrim, L., Ramakrishnan, R., Melkumyan, A., Murphy, R.J., and Chlingaryan, A. (2019). Unsupervised Feature-Learning for Hyperspectral Data with Autoencoders. Remote Sens., 11.","DOI":"10.3390\/rs11070864"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Gewali, U., Monteiro, S., and Saber, E. (2019). Spectral Super-Resolution with Optimized Bands. Remote Sens., 11.","DOI":"10.3390\/rs11141648"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/20\/5789\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:20:30Z","timestamp":1760178030000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/20\/5789"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,13]]},"references-count":25,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2020,10]]}},"alternative-id":["s20205789"],"URL":"https:\/\/doi.org\/10.3390\/s20205789","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2020,10,13]]}}}