{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:37:59Z","timestamp":1784389079814,"version":"3.55.0"},"reference-count":58,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2017,7,20]],"date-time":"2017-07-20T00:00:00Z","timestamp":1500508800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"UC San Diego Center for Visual Computing"},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N000141512013"],"award-info":[{"award-number":["N000141512013"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1617234"],"award-info":[{"award-number":["1617234"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2017,8,31]]},"abstract":"<jats:p>Producing a high dynamic range (HDR) image from a set of images with different exposures is a challenging process for dynamic scenes. A category of existing techniques first register the input images to a reference image and then merge the aligned images into an HDR image. However, the artifacts of the registration usually appear as ghosting and tearing in the final HDR images. In this paper, we propose a learning-based approach to address this problem for dynamic scenes. We use a convolutional neural network (CNN) as our learning model and present and compare three different system architectures to model the HDR merge process. Furthermore, we create a large dataset of input LDR images and their corresponding ground truth HDR images to train our system. We demonstrate the performance of our system by producing high-quality HDR images from a set of three LDR images. Experimental results show that our method consistently produces better results than several state-of-the-art approaches on challenging scenes.<\/jats:p>","DOI":"10.1145\/3072959.3073609","type":"journal-article","created":{"date-parts":[[2017,7,21]],"date-time":"2017-07-21T12:24:07Z","timestamp":1500639847000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":521,"title":["Deep high dynamic range imaging of dynamic scenes"],"prefix":"10.1145","volume":"36","author":[{"given":"Nima Khademi","family":"Kalantari","sequence":"first","affiliation":[{"name":"University of California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ravi","family":"Ramamoorthi","sequence":"additional","affiliation":[{"name":"University of California"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,7,20]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPHOT.2015.7168373"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2000.903475"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.316"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.55"},{"key":"e_1_2_2_5_1","volume-title":"Debevec and Jitendra Malik","author":"Paul","year":"1997"},{"key":"e_1_2_2_6_1","volume-title":"D. Cremers, and T. Brox.","author":"Dosovitskiy A.","year":"2015"},{"key":"e_1_2_2_7_1","volume-title":"DeepStereo: Learning to Predict New Views from the World\u00e2\u0102&Zacute;s Imagery","author":"Flynn John"},{"key":"e_1_2_2_8_1","first-page":"90230X","article-title":"Creating cinematic wide gamut HDR-video for the evaluation of tone mapping operators and HDR-displays","volume":"9023","author":"Froehlich Jan","year":"2014","journal-title":"SPIE"},{"key":"e_1_2_2_9_1","volume-title":"The Rehabilitation of MaxRGB. Color and Imaging Conference 2010","author":"Funt Brian","year":"2010"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPHOT.2009.5559003"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301366"},{"key":"e_1_2_2_12_1","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"Glorot Xavier","year":"2010","journal-title":"AISTATS"},{"key":"e_1_2_2_13_1","unstructured":"I. J. Goodfellow J. Pouget-Abadie M. Mirza B. Xu D. Warde-Farley S. Ozair A. Courville and Y. Bengio. 2014. Generative Adversarial Networks. ArXiv e-prints (June 2014). arXiv:stat.ML\/1406.2661  I. J. Goodfellow J. Pouget-Abadie M. Mirza B. Xu D. Warde-Farley S. Ozair A. Courville and Y. Bengio. 2014. Generative Adversarial Networks. ArXiv e-prints (June 2014). arXiv:stat.ML\/1406.2661"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540208"},{"key":"e_1_2_2_15_1","volume-title":"James Tompkin, and Christian Theobalt.","author":"Granados Miguel","year":"2013"},{"key":"e_1_2_2_16_1","unstructured":"T. Grosch. 2006. Fast and Robust High Dynamic Range Image Generation with Camera and Object Movement. In Vision Modeling and Visualization. 277--284.  T. Grosch. 2006. Fast and Robust High Dynamic Range Image Generation with Camera and Object Movement. In Vision Modeling and Visualization. 277--284."},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1240119"},{"key":"e_1_2_2_18_1","volume-title":"Article 70","author":"HaCohen Yoav","year":"2011"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-015-0095-0"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540167"},{"key":"e_1_2_2_21_1","volume-title":"Article 192 (Nov.","author":"Hasinoff Samuel W.","year":"2016"},{"key":"e_1_2_2_22_1","volume-title":"Article 231 (Nov.","author":"Heide Felix","year":"2014"},{"key":"e_1_2_2_23_1","first-page":"486","article-title":"Ghost-free high dynamic range imaging","volume":"4","author":"Heo Yong Seok","year":"2010","journal-title":"ACCV"},{"key":"e_1_2_2_24_1","volume-title":"Exposure Stacks of Live Scenes with Hand-Held Cameras","author":"Hu Jun"},{"key":"e_1_2_2_25_1","doi-asserted-by":"crossref","unstructured":"J. Hu O. Gallo K. Pulli and X. Sun. 2013. HDR Deghosting: How to Deal with Saturation?. In IEEE CVPR. 1163--1170.  J. Hu O. Gallo K. Pulli and X. Sun. 2013. HDR Deghosting: How to Deal with Saturation?. In IEEE CVPR. 1163--1170.","DOI":"10.1109\/CVPR.2013.154"},{"key":"e_1_2_2_26_1","volume-title":"Article 110 (July","author":"Iizuka Satoshi","year":"2016"},{"key":"e_1_2_2_27_1","volume-title":"Evolution of Optical Flow Estimation with Deep Networks. CoRR abs\/1612.01925","author":"Ilg Eddy","year":"2016"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2008.23"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2008.4712002"},{"key":"e_1_2_2_30_1","volume-title":"Article 193 (Nov.","author":"Kalantari Nima Khademi","year":"2016"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882270"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.2312\/egsh.20161007"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2006.312892"},{"key":"e_1_2_2_34_1","first-page":"9","article-title":"Ghost-Free High Dynamic Range Imaging via Rank Minimization","volume":"21","author":"Lee C.","year":"2014","journal-title":"IEEE SPL"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2349432"},{"key":"e_1_2_2_36_1","unstructured":"C. Liu. 2009. Beyond Pixels: Exploring New Representations and Applications for Motion Analysis. Doctoral thesis. Massachusetts Institute of Technology.  C. Liu. 2009. Beyond Pixels: Exploring New Representations and Applications for Motion Analysis. Doctoral thesis. Massachusetts Institute of Technology."},{"key":"e_1_2_2_37_1","volume-title":"Lucas and Takeo Kanade","author":"Bruce","year":"1981"},{"key":"e_1_2_2_38_1","volume-title":"Picard","author":"Mann Steve","year":"1995"},{"key":"e_1_2_2_39_1","volume-title":"Allan G. Rempel, and Wolfgang Heidrich.","author":"Mantiuk Rafat","year":"2011"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2007.45"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2361338"},{"key":"e_1_2_2_42_1","doi-asserted-by":"crossref","unstructured":"F. Pece and J. Kautz. 2010. Bitmap Movement Detection: HDR for Dynamic Scenes. In CVMP. 1--8.  F. Pece and J. Kautz. 2010. Bitmap Movement Detection: HDR for Dynamic Scenes. In CVMP. 1--8.","DOI":"10.1109\/CVMP.2010.8"},{"key":"e_1_2_2_43_1","unstructured":"Photomatix. 2017. Commercially-available HDR processing software. (2017). http:\/\/www.hdrsoft.com\/.  Photomatix. 2017. Commercially-available HDR processing software. (2017). http:\/\/www.hdrsoft.com\/."},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-011-0653-0"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_2_2_46_1","volume-title":"Maziar Yaesoubi, Soheil Darabi, Dan B. Goldman, and Eli Shechtman.","author":"Sen Pradeep","year":"2012"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12819"},{"key":"e_1_2_2_48_1","volume-title":"Article 41 (July","author":"Tocci Michael D.","year":"2011"},{"key":"e_1_2_2_49_1","unstructured":"A. Tomaszewska and R. Mantiuk. 2007. Image Registration for Multi-exposure High Dynamic Range Image Acquisition. In WSCG.  A. Tomaszewska and R. Mantiuk. 2007. Image Registration for Multi-exposure High Dynamic Range Image Acquisition. In WSCG."},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12818"},{"key":"e_1_2_2_51_1","volume-title":"The State of the Art in HDR Deghosting: A Survey and Evaluation. CGF 34, 2","author":"Tursun Okan Tarhan","year":"2015"},{"key":"e_1_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Andrea Vedaldi and Karel Lenc. 2015. MatConvNet: Convolutional neural networks for Matlab. In ACMMM. 689--692.  Andrea Vedaldi and Karel Lenc. 2015. MatConvNet: Convolutional neural networks for Matlab. In ACMMM. 689--692.","DOI":"10.1145\/2733373.2807412"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1080\/10867651.2003.10487583"},{"key":"e_1_2_2_54_1","doi-asserted-by":"crossref","unstructured":"L. Zhang A. Deshpande and X. Chen. 2010. Denoising vs. deblurring: HDR imaging techniques using moving cameras. In CVPR. 522--529.  L. Zhang A. Deshpande and X. Chen. 2010. Denoising vs. deblurring: HDR imaging techniques using moving cameras. In CVPR. 522--529.","DOI":"10.1109\/CVPR.2010.5540171"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2170079"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPHOT.2015.7168378"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2283401"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.01870.x"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3072959.3073609","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3072959.3073609","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3072959.3073609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:37:23Z","timestamp":1750217843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3072959.3073609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,20]]},"references-count":58,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,8,31]]}},"alternative-id":["10.1145\/3072959.3073609"],"URL":"https:\/\/doi.org\/10.1145\/3072959.3073609","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7,20]]},"assertion":[{"value":"2017-07-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}