{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:20:16Z","timestamp":1776277216681,"version":"3.50.1"},"reference-count":50,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2020,8,12]],"date-time":"2020-08-12T00:00:00Z","timestamp":1597190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"crossref","award":["161268\/2018-8"],"award-info":[{"award-number":["161268\/2018-8"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"crossref"}]},{"name":"TAMU T3","award":["246451"],"award-info":[{"award-number":["246451"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2020,8,31]]},"abstract":"<jats:p>Digital cameras can only capture a limited range of real-world scenes' luminance, producing images with saturated pixels. Existing single image high dynamic range (HDR) reconstruction methods attempt to expand the range of luminance, but are not able to hallucinate plausible textures, producing results with artifacts in the saturated areas. In this paper, we present a novel learning-based approach to reconstruct an HDR image by recovering the saturated pixels of an input LDR image in a visually pleasing way. Previous deep learning-based methods apply the same convolutional filters on wellexposed and saturated pixels, creating ambiguity during training and leading to checkerboard and halo artifacts. To overcome this problem, we propose a feature masking mechanism that reduces the contribution of the features from the saturated areas. Moreover, we adapt the VGG-based perceptual loss function to our application to be able to synthesize visually pleasing textures. Since the number of HDR images for training is limited, we propose to train our system in two stages. Specifically, we first train our system on a large number of images for image inpainting task and then fine-tune it on HDR reconstruction. Since most of the HDR examples contain smooth regions that are simple to reconstruct, we propose a sampling strategy to select challenging training patches during the HDR fine-tuning stage. We demonstrate through experimental results that our approach can reconstruct visually pleasing HDR results, better than the current state of the art on a wide range of scenes.<\/jats:p>","DOI":"10.1145\/3386569.3392403","type":"journal-article","created":{"date-parts":[[2020,8,12]],"date-time":"2020-08-12T11:44:27Z","timestamp":1597232667000},"update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":130,"title":["Single image HDR reconstruction using a CNN with masked features and perceptual loss"],"prefix":"10.1145","volume":"39","author":[{"given":"Marcel Santana","family":"Santos","sequence":"first","affiliation":[{"name":"Universidade Federal de Pernambuco"}]},{"given":"Tsang Ing","family":"Ren","sequence":"additional","affiliation":[{"name":"Universidade Federal de Pernambuco"}]},{"given":"Nima Khademi","family":"Kalantari","sequence":"additional","affiliation":[{"name":"Texas A&amp;M University"}]}],"member":"320","published-online":{"date-parts":[[2020,8,12]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1174429.1174489"},{"key":"e_1_2_2_2_1","article-title":"Semantic Photo Manipulation with a Generative Image Prior","volume":"38","author":"Bau David","year":"2019","unstructured":"David Bau, Hendrik Strobelt, William Peebles, Jonas Wulff, Bolei Zhou, Jun-Yan Zhu, and Antonio Torralba. 2019. Semantic Photo Manipulation with a Generative Image Prior. ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH) 38, 4 (2019).","journal-title":"ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH)"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2016.12.006"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186954.1187029"},{"key":"e_1_2_2_5_1","volume-title":"Proceeding of the SPIE: Image Sensors","volume":"3965","author":"Debevec PE","year":"1997","unstructured":"PE Debevec and J Malik. 1997. Recovering high dynamic range images. In Proceeding of the SPIE: Image Sensors, Vol. 3965. 392--401."},{"key":"e_1_2_2_6_1","volume-title":"Computer Graphics Forum","author":"Didyk Piotr","unstructured":"Piotr Didyk, Rafal Mantiuk, Matthias Hein, and Hans-Peter Seidel. 2008. Enhancement of bright video features for HDR displays. In Computer Graphics Forum, Vol. 27. Wiley Online Library, 1265--1274."},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/566570.566574"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130816"},{"key":"e_1_2_2_10_1","volume-title":"Single-frame Regularization for Temporally Stable CNNs. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Eilertsen Gabriel","year":"2019","unstructured":"Gabriel Eilertsen, Rafa\u0142Mantiuk, and Jonas Unger. 2019. Single-frame Regularization for Temporally Stable CNNs. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130834"},{"key":"e_1_2_2_12_1","volume-title":"A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576","author":"Gatys Leon A","year":"2015","unstructured":"Leon A Gatys, Alexander S Ecker, and Matthias Bethge. 2015. A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576 (2015)."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_2_2_14_1","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS). 249--256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS). 249--256."},{"key":"e_1_2_2_15_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems (NeurIPS). 2672--2680."},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00458"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980254"},{"key":"e_1_2_2_18_1","volume-title":"Reducing the dimensionality of data with neural networks. Science 313, 5786","author":"Hinton Geoffrey E","year":"2006","unstructured":"Geoffrey E Hinton and Ruslan R Salakhutdinov. 2006. Reducing the dimensionality of data with neural networks. Science 313, 5786 (2006), 504--507."},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.154"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073609"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1201775.882270"},{"key":"e_1_2_2_22_1","volume-title":"Jsi-gan: Gan-based joint super-resolution and inverse tone-mapping with pixel-wise task-specific filters for UHD HDR video. arXiv preprint arXiv:1909.04391","author":"Kim Soo Ye","year":"2019","unstructured":"Soo Ye Kim, Jihyong Oh, and Munchurl Kim. 2019. Jsi-gan: Gan-based joint super-resolution and inverse tone-mapping with pixel-wise task-specific filters for UHD HDR video. arXiv preprint arXiv:1909.04391 (2019)."},{"key":"e_1_2_2_23_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Kingma Diederick P","year":"2015","unstructured":"Diederick P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2014.29"},{"key":"e_1_2_2_25_1","first-page":"11","article-title":"Production-ready global illumination","volume":"16","author":"Landis Hayden","year":"2002","unstructured":"Hayden Landis. 2002. Production-ready global illumination. SIGGRAPH Course Notes 16, 2002 (2002), 11.","journal-title":"SIGGRAPH Course Notes"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2868246"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_37"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/PCS.2018.8456253"},{"key":"e_1_2_2_30_1","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","volume":"30","author":"Maas Andrew L","year":"2013","unstructured":"Andrew L Maas, Awni Y Hannun, and Andrew Y Ng. 2013. Rectifier nonlinearities improve neural network acoustic models. In Proceedings of International Conference on Machine Learning (ICML), Vol. 30. 3."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964935"},{"key":"e_1_2_2_32_1","volume-title":"Computer Graphics Forum","author":"Marnerides Demetris","unstructured":"Demetris Marnerides, Thomas Bashford-Rogers, Jonathan Hatchett, and Kurt Debattista. 2018. ExpandNet: A deep convolutional neural network for high dynamic range expansion from low dynamic range content. In Computer Graphics Forum, Vol. 37. Wiley Online Library, 37--49."},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2007.45"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462444"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2361338"},{"key":"e_1_2_2_37_1","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et al. 2019. PyTorch: An imperative style high-performance deep learning library. In Advances in Neural Information Processing Systems (NeurIPS). 8024--8035."},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1275808.1276426"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366222"},{"key":"e_1_2_2_41_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations (ICLR).","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964936"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1278780.1278867"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_8"},{"key":"e_1_2_2_45_1","volume-title":"Gan Based Multi-Exposure Inverse Tone Mapping. In 2019 IEEE International Conference on Image Processing (ICIP). IEEE, 1--5.","author":"Xu Yucheng","year":"2019","unstructured":"Yucheng Xu, Shiyu Ning, Rong Xie, and Li Song. 2019. Gan Based Multi-Exposure Inverse Tone Mapping. In 2019 IEEE International Conference on Image Processing (ICIP). IEEE, 1--5."},{"key":"e_1_2_2_46_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 6721--6729","author":"Yang Chao","year":"2017","unstructured":"Chao Yang, Xin Lu, Zhe Lin, Eli Shechtman, Oliver Wang, and Hao Li. 2017. Highresolution image inpainting using multi-scale neural patch synthesis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 6721--6729."},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00193"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"e_1_2_2_50_1","unstructured":"Bolei Zhou Agata Lapedriza Jianxiong Xiao Antonio Torralba and Aude Oliva. 2014. Learning deep features for scene recognition using places database. In Advances in Neural Information Processing Systems (NeurIPS). 487--495."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386569.3392403","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3386569.3392403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T05:36:48Z","timestamp":1750829808000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386569.3392403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,12]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,8,31]]}},"alternative-id":["10.1145\/3386569.3392403"],"URL":"https:\/\/doi.org\/10.1145\/3386569.3392403","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,12]]},"assertion":[{"value":"2020-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}