{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:21:41Z","timestamp":1761582101494,"version":"build-2065373602"},"reference-count":48,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,6,11]],"date-time":"2021-06-11T00:00:00Z","timestamp":1623369600000},"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>Inverse Tone Mapping (ITM) methods attempt to reconstruct High Dynamic Range (HDR) information from Low Dynamic Range (LDR) image content. The dynamic range of well-exposed areas must be expanded and any missing information due to over\/under-exposure must be recovered (hallucinated). The majority of methods focus on the former and are relatively successful, while most attempts on the latter are not of sufficient quality, even ones based on Convolutional Neural Networks (CNNs). A major factor for the reduced inpainting quality in some works is the choice of loss function. Work based on Generative Adversarial Networks (GANs) shows promising results for image synthesis and LDR inpainting, suggesting that GAN losses can improve inverse tone mapping results. This work presents a GAN-based method that hallucinates missing information from badly exposed areas in LDR images and compares its efficacy with alternative variations. The proposed method is quantitatively competitive with state-of-the-art inverse tone mapping methods, providing good dynamic range expansion for well-exposed areas and plausible hallucinations for saturated and under-exposed areas. A density-based normalisation method, targeted for HDR content, is also proposed, as well as an HDR data augmentation method targeted for HDR hallucination.<\/jats:p>","DOI":"10.3390\/s21124032","type":"journal-article","created":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T22:25:46Z","timestamp":1623709546000},"page":"4032","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Deep HDR Hallucination for Inverse Tone Mapping"],"prefix":"10.3390","volume":"21","author":[{"given":"Demetris","family":"Marnerides","sequence":"first","affiliation":[{"name":"WMG, University of Warwick, Coventry CV4 7AL, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4669-0417","authenticated-orcid":false,"given":"Thomas","family":"Bashford-Rogers","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Creative Technologies, University of the West of England, Bristol BS16 1GY, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2982-5199","authenticated-orcid":false,"given":"Kurt","family":"Debattista","sequence":"additional","affiliation":[{"name":"WMG, University of Warwick, Coventry CV4 7AL, UK"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Banterle, F., Artusi, A., Debattista, K., and Chalmers, A. (2017). Advanced High Dynamic Range Imaging, AK Peters (CRC Press). [2nd ed.].","DOI":"10.1201\/9781315119526"},{"key":"ref_2","unstructured":"Banterle, F., Ledda, P., Debattista, K., and Chalmers, A. (December, January 29). Inverse tone mapping. Proceedings of the GRAPHITE\u201906, Kuala Lumpur, Malaysia."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073659","article-title":"Globally and Locally Consistent Image Completion","volume":"36","author":"Iizuka","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., and Efros, A.A. (2016;, January 27\u201330). Context Encoders: Feature Learning by Inpainting. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1111\/cgf.13340","article-title":"ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content","volume":"37","author":"Marnerides","year":"2018","journal-title":"Comput. Graph. Forum"},{"key":"ref_6","unstructured":"Marnerides, D., Bashford-Rogers, T., and Debattista, K. (2020). Spectrally Consistent UNet for High Fidelity Image Transformations. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1145\/3130800.3130816","article-title":"HDR image reconstruction from a single exposure using deep CNNs","volume":"36","author":"Eilertsen","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1145\/3130800.3130834","article-title":"Deep reverse tone mapping","volume":"36","author":"Endo","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref_9","unstructured":"Landis, H. (2021, June 02). Production-Ready Global Illumination. Available online: https:\/\/www.semanticscholar.org\/paper\/Production-Ready-Global-Illumination-Landis\/4a9de79235445fdf346b274603dfa5447321aab6."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1145\/1276377.1276425","article-title":"Do HDR displays support LDR content? A psychophysical evaluation","volume":"26","author":"Fleming","year":"2007","journal-title":"ACM Trans. Graph."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1618452.1618506","article-title":"Evaluation of Reverse Tone Mapping Through Varying Exposure Conditions","volume":"28","author":"Masia","year":"2009","journal-title":"ACM Trans. Graph."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1007\/s11042-015-3036-0","article-title":"Dynamic range expansion based on image statistics","volume":"76","author":"Masia","year":"2017","journal-title":"Multimed. Tools Appl."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/1276377.1276426","article-title":"LDR2HDR: On-the-Fly Reverse Tone Mapping of Legacy Video and Photographs","volume":"26","author":"Rempel","year":"2007","journal-title":"ACM Trans. Graph."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kovaleski, R.P., and Oliveira, M.M. (2014, January 26\u201330). High-Quality Reverse Tone Mapping for a Wide Range of Exposures. Proceedings of the 27th SIBGRAPI Conference on Graphics, Patterns and Images, Rio de Janeiro, Brazil.","DOI":"10.1109\/SIBGRAPI.2014.29"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1007\/s00371-013-0875-4","article-title":"Physiological inverse tone mapping based on retina response","volume":"30","author":"Huo","year":"2014","journal-title":"Vis. Comput."},{"key":"ref_16","unstructured":"Wang, L., Wei, L.Y., Zhou, K., Guo, B., and Shum, H.Y. (2021, June 02). High Dynamic Range Image Hallucination. Available online: http:\/\/citeseerx.ist.psu.edu\/viewdoc\/download?doi=10.1.1.446.7833&rep=rep1&type=pdf."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kuo, P.H., Liang, H.J., Tang, C.S., and Chien, S.Y. (2014, January 22\u201324). Automatic high dynamic range hallucination in inverse tone mapping. Proceedings of the 2014 IEEE 16th International Workshop on Multimedia Signal Processing (MMSP), Jakarta, Indonesia.","DOI":"10.1109\/MMSP.2014.6958828"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhang, J., and Lalonde, J.F. (2017, January 22\u201329). Learning high dynamic range from outdoor panoramas. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.484"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"49913","DOI":"10.1109\/ACCESS.2018.2868246","article-title":"Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Image","volume":"6","author":"Lee","year":"2018","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Han, J., Zhou, C., Duan, P., Tang, Y., Xu, C., Xu, C., Huang, T., and Shi, B. (2020, January 14\u201319). Neuromorphic camera guided high dynamic range imaging. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00180"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sun, Q., Tseng, E., Fu, Q., Heidrich, W., and Heide, F. (2020, January 14\u201319). Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00146"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Liu, Y.L., Lai, W.S., Chen, Y.S., Kao, Y.L., Yang, M.H., Chuang, Y.Y., and Huang, J.B. (2020, January 14\u201319). Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00172"},{"key":"ref_23","unstructured":"Sharif, S., Naqvi, R.A., Biswas, M., and Sungjun, K. (2021, June 02). A Two-stage Deep Network for High Dynamic Range Image Reconstruction. Available online: https:\/\/www.semanticscholar.org\/paper\/A-Two-stage-Deep-Network-for-High-Dynamic-Range-Sharif-Naqvi\/64236160dcc06a1370f2358c3e44b44d9054e796."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chen, X., Liu, Y., Zhang, Z., Qiao, Y., and Dong, C. (2021, June 02). HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization. Available online: https:\/\/arxiv.org\/abs\/2105.13084.","DOI":"10.1109\/CVPRW53098.2021.00045"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3386569.3392403","article-title":"Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss","volume":"39","author":"Santos","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"ref_26","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2021, June 02). U-Net: Convolutional Networks for Biomedical Image Segmentation. Available online: https:\/\/arxiv.org\/abs\/1505.04597."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2016). Image-to-Image Translation with Conditional Adversarial Networks. arXiv.","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., and Catanzaro, B. (2018, January 18\u201323). High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016). Identity Mappings in Deep Residual Networks. Computer Vision\u2014ECCV 2016, Springer International Publishing.","DOI":"10.1007\/978-3-319-46466-4"},{"key":"ref_30","unstructured":"Klambauer, G., Unterthiner, T., Mayr, A., and Hochreiter, S. (2021, June 02). Self-Normalizing Neural Networks. Available online: https:\/\/arxiv.org\/abs\/1706.02515."},{"key":"ref_31","unstructured":"Maas, A.L., Hannun, A.Y., and Ng, A.Y. (2013, January 16\u201321). Rectifier nonlinearities improve neural network acoustic models. Proceedings of the International Conference on Machine Learning (ICML), Atlanta, GA, USA."},{"key":"ref_32","unstructured":"Karras, T., Aila, T., Laine, S., and Lehtinen, J. (2017). Progressive Growing of GANs for Improved Quality, Stability, and Variation. arXiv."},{"key":"ref_33","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016). Improved Techniques for Training GANs. arXiv."},{"key":"ref_34","unstructured":"Kodali, N., Abernethy, J., Hays, J., and Kira, Z. (2017). On Convergence and Stability of GANs. arXiv."},{"key":"ref_35","unstructured":"Lim, J.H., and Ye, J.C. (2017). Geometric GAN. arXiv."},{"key":"ref_36","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., and Odena, A. (2018). Self-Attention Generative Adversarial Networks. arXiv."},{"key":"ref_37","unstructured":"Brock, A., Donahue, J., and Simonyan, K. (2018). Large Scale GAN Training for High Fidelity Natural Image Synthesis. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., and Fei-Fei, L. (2016). Perceptual losses for real-time style transfer and super-resolution. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref_39","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_41","unstructured":"(2021, June 02). Flickr. Available online: https:\/\/www.flickr.com\/."},{"key":"ref_42","unstructured":"Ioffe, S., and Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv."},{"key":"ref_43","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017). GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. arXiv."},{"key":"ref_44","unstructured":"Miyato, T., Kataoka, T., Koyama, M., and Yoshida, Y. (2018). Spectral normalization for generative adversarial networks. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"68060B","DOI":"10.1117\/12.765095","article-title":"Extending quality metrics to full luminance range images","volume":"Volume 6806","author":"Mantiuk","year":"2008","journal-title":"Human Vision and Electronic Imaging XIII"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_47","unstructured":"Wang, Z., Simoncelli, E.P., and Bovik, A.C. (2003, January 9\u201312). Multiscale structural similarity for image quality assessment. Proceedings of the Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, Pacific Grove, CA, USA."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"010501","DOI":"10.1117\/1.JEI.24.1.010501","article-title":"HDR-VDP-2.2: A calibrated method for objective quality prediction of high-dynamic range and standard images","volume":"24","author":"Narwaria","year":"2015","journal-title":"J. Electron. Imaging"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4032\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:13:15Z","timestamp":1760163195000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4032"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,11]]},"references-count":48,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["s21124032"],"URL":"https:\/\/doi.org\/10.3390\/s21124032","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2021,6,11]]}}}