{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:13:50Z","timestamp":1777130030962,"version":"3.51.4"},"reference-count":39,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201806220060"],"award-info":[{"award-number":["201806220060"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Multi-exposure image fusion (MEF) methods for high dynamic range (HDR) imaging suffer from ghosting artifacts when dealing with moving objects in dynamic scenes. The state-of-the-art methods use optical flow to align low dynamic range (LDR) images before merging, introducing distortion into the aligned LDR images from inaccurate motion estimation due to large motion and occlusion. In place of pre-alignment, attention-based methods calculate the correlation between the reference LDR image and non-reference LDR images, thus excluding misaligned regions in LDR images. Nevertheless, they also exclude the saturated details at the same time. Taking advantage of both the alignment and attention-based methods, we propose an efficient Deep HDR Deghosting Fusion Network (DDFNet) guided by optical flow and image correlation attentions. Specifically, the DDFNet estimates the optical flow of the LDR images by a motion estimation module and encodes that optical flow as a flow feature. Additionally, it extracts correlation features between the reference LDR and other non-reference LDR images. The optical flow and correlation features are employed to adaptably combine information from LDR inputs in an attention-based fusion module. Following the merging of features, a decoder composed of Dense Networks reconstructs the HDR image without ghosting. Experimental results indicate that the proposed DDFNet achieves state-of-the-art image fusion performance on different public datasets.<\/jats:p>","DOI":"10.3390\/s22207853","type":"journal-article","created":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T03:43:58Z","timestamp":1665978238000},"page":"7853","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Deep HDR Deghosting by Motion-Attention Fusion Network"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9040-6394","authenticated-orcid":false,"given":"Yifan","family":"Xiao","sequence":"first","affiliation":[{"name":"Department of Telecommunications and Information Processing, IPI-IMEC, Ghent University, 9000 Ghent, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4746-9087","authenticated-orcid":false,"given":"Peter","family":"Veelaert","sequence":"additional","affiliation":[{"name":"Department of Telecommunications and Information Processing, IPI-IMEC, Ghent University, 9000 Ghent, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wilfried","family":"Philips","sequence":"additional","affiliation":[{"name":"Department of Telecommunications and Information Processing, IPI-IMEC, Ghent University, 9000 Ghent, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,10,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1146\/annurev-vision-093019-115521","article-title":"Mobile computational photography: A tour","volume":"7","author":"Delbracio","year":"2021","journal-title":"Annu. Rev. Vis. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wang, L., and Yoon, K.J. (2021). Deep Learning for HDR Imaging: State-of-the-Art and Future Trends. IEEE Trans. Pattern Anal. Mach. Intell.","DOI":"10.1109\/TPAMI.2021.3123686"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.inffus.2021.02.005","article-title":"Benchmarking and comparing multi-exposure image fusion algorithms","volume":"74","author":"Zhang","year":"2021","journal-title":"Inf. Fusion"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1109\/TIP.2019.2940678","article-title":"Perceptual evaluation for multi-exposure image fusion of dynamic scenes","volume":"29","author":"Fang","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"203:1","DOI":"10.1145\/2366145.2366222","article-title":"Robust patch-based hdr reconstruction of dynamic scenes","volume":"31","author":"Sen","year":"2012","journal-title":"ACM Trans. Graph."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1016\/j.image.2012.02.001","article-title":"Ghost detection and removal for high dynamic range images: Recent advances","volume":"27","author":"Srikantha","year":"2012","journal-title":"Signal Process. Image Commun."},{"key":"ref_7","first-page":"93","article-title":"A review on high-dynamic-range imaging with its technique","volume":"8","author":"Tiwari","year":"2015","journal-title":"Int. J. Signal Process. Image Process. Pattern Recognit."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1111\/cgf.12593","article-title":"The state of the art in HDR deghosting: A survey and evaluation","volume":"Volume 34","author":"Tursun","year":"2015","journal-title":"Computer Graphics Forum"},{"key":"ref_9","first-page":"198","article-title":"High dynamic range imaging\u2014A review","volume":"9","author":"Johnson","year":"2015","journal-title":"Int. J. Image Process. (IJIP)"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hu, J., Gallo, O., Pulli, K., and Sun, X. (2013, January 23\u201328). HDR deghosting: How to deal with saturation?. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.","DOI":"10.1109\/CVPR.2013.154"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1109\/LSP.2014.2323404","article-title":"Ghost-free high dynamic range imaging via rank minimization","volume":"21","author":"Lee","year":"2014","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1109\/TPAMI.2014.2361338","article-title":"Robust high dynamic range imaging by rank minimization","volume":"37","author":"Oh","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4372","DOI":"10.1109\/TIP.2014.2349432","article-title":"Selectively detail-enhanced fusion of differently exposed images with moving objects","volume":"23","author":"Li","year":"2014","journal-title":"IEEE Trans. Image Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2519","DOI":"10.1109\/TIP.2017.2671921","article-title":"Robust multi-exposure image fusion: A structural patch decomposition approach","volume":"26","author":"Ma","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wu, S., Xu, J., Tai, Y.W., and Tang, C.K. (2018, January 8\u201314). Deep high dynamic range imaging with large foreground motions. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01216-8_8"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yan, Q., Gong, D., Shi, Q., Hengel, A.v.d., Shen, C., Reid, I., and Zhang, Y. (2019, January 15\u201320). Attention-guided network for ghost-free high dynamic range imaging. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00185"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Prabhakar, K.R., Agrawal, S., Singh, D.K., Ashwath, B., and Babu, R.V. (2020). Towards practical and efficient high-resolution HDR deghosting with CNN. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-030-58589-1_30"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"144:1","DOI":"10.1145\/3072959.3073609","article-title":"Deep high dynamic range imaging of dynamic scenes","volume":"36","author":"Kalantari","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref_19","unstructured":"Liu, C. (2009). Beyond Pixels: Exploring New Representations and Applications for Motion Analysis. [Ph.D. Thesis, Massachusetts Institute of Technology]."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Peng, F., Zhang, M., Lai, S., Tan, H., and Yan, S. (2018, January 27\u201329). Deep HDR reconstruction of dynamic scenes. Proceedings of the 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), Chongqing, China.","DOI":"10.1109\/ICIVC.2018.8492856"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Metwaly, K., and Monga, V. (2020, January 4\u20138). Attention-mask dense merger (attendense) deep hdr for ghost removal. Proceedings of the ICASSP 2020\u20142020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.","DOI":"10.1109\/ICASSP40776.2020.9053180"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3885","DOI":"10.1109\/TIP.2021.3064433","article-title":"HDR-GAN: HDR image reconstruction from multi-exposed ldr images with large motions","volume":"30","author":"Niu","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Choi, S., Cho, J., Song, W., Choe, J., Yoo, J., and Sohn, K. (2020). Pyramid inter-attention for high dynamic range imaging. Sensors, 20.","DOI":"10.3390\/s20185102"},{"key":"ref_24","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yan, Q., Gong, D., Zhang, P., Shi, Q., Sun, J., Reid, I., and Zhang, Y. (2019, January 7\u201311). Multi-scale dense networks for deep high dynamic range imaging. Proceedings of the 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa Village, HI, USA.","DOI":"10.1109\/WACV.2019.00012"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., Van Der Smagt, P., Cremers, D., and Brox, T. (2015, January 7\u201313). Flownet: Learning optical flow with convolutional networks. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., and Kautz, J. (2018, January 18\u201322). Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Van Gool, L., and Timofte, R. (2021, January 20\u201325). Deep burst super-resolution. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00909"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tian, Y., Kong, Y., Zhong, B., and Fu, Y. (2018, January 18\u201322). Residual dense network for image super-resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00262"},{"key":"ref_31","unstructured":"Yu, F., and Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2010324.1964935","article-title":"HDR-VDP-2: A calibrated visual metric for visibility and quality predictions in all luminance conditions","volume":"30","author":"Mantiuk","year":"2011","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1109\/TCYB.2014.2355140","article-title":"Robust match fusion using optimization","volume":"45","author":"Qin","year":"2014","journal-title":"IEEE Trans. Cybern."},{"key":"ref_34","unstructured":"Photomatix (2022, October 11). Commercially-Available HDR Processing Software. Available online: https:\/\/www.hdrsoft.com\/."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1109\/TCE.2012.6227469","article-title":"Fast multi-exposure image fusion with median filter and recursive filter","volume":"58","author":"Li","year":"2012","journal-title":"IEEE Trans. Consum. Electron."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"5190","DOI":"10.1109\/TIP.2013.2283401","article-title":"Hybrid patching for a sequence of differently exposed images with moving objects","volume":"22","author":"Zheng","year":"2013","journal-title":"IEEE Trans. Image Process."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1109\/TIP.2004.833105","article-title":"Region filling and object removal by exemplar-based image inpainting","volume":"13","author":"Criminisi","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1007\/s10994-019-05855-6","article-title":"A survey on semi-supervised learning","volume":"109","author":"Hoos","year":"2020","journal-title":"Mach. Learn."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"3048","DOI":"10.1109\/TPAMI.2021.3055564","article-title":"Knowledge distillation and student-teacher learning for visual intelligence: A review and new outlooks","volume":"44","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/20\/7853\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:55:05Z","timestamp":1760144105000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/20\/7853"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":39,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["s22207853"],"URL":"https:\/\/doi.org\/10.3390\/s22207853","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,16]]}}}