{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:21:50Z","timestamp":1760149310851,"version":"build-2065373602"},"reference-count":32,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2023,7,23]],"date-time":"2023-07-23T00:00:00Z","timestamp":1690070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>High Dynamic Range (HDR) images are widely used in automotive, aerospace, AI, and other fields but are limited by the maximum dynamic range of a single data acquisition using CMOS image sensors. High dynamic range images are usually synthesized through multiple exposure techniques and image processing techniques. One of the most challenging task in multiframe Low Dynamic Range (LDR) images fusion for HDR is to eliminate ghosting artifacts caused by motion. In traditional algorithms, optical flow is generally used to align dynamic scenes before image fusion, which can achieve good results in cases of small-scale motion scenes but causes obvious ghosting artifacts when motion magnitude is large. Recently, attention mechanisms have been introduced during the alignment stage to enhance the network\u2019s ability to remove ghosts. However, significant ghosting artifacts still occur in some scenarios with large-scale motion or oversaturated areas. We proposea novel Distilled Feature TransformerBlock (DFTB) structure to distill and re-extract information from deep image features obtained after U-Net downsampling, achieving ghost removal at the semantic level for HDR fusion. We introduce a Feature Distillation Transformer Block (FDTB), based on the Swin-Transformer and RFDB structure. FDTB uses multiple distillation connections to learn more discriminative feature representations. For the multiexposure moving scene image fusion HDR ghost removal task, in the previous method, the use of deep learning to remove the ghost effect in the composite image has been perfect, and it is almost difficult to observe the ghost residue of moving objects in the composite HDR image. The method in this paper focuses more on how to save the details of LDR image more completely after removing the ghost to synthesize high-quality HDR image. After using the proposed FDTB, the edge texture details of the synthesized HDR image are saved more perfectly, which shows that FDTB has a better effect in saving the details of image fusion. Futhermore, we propose a new depth framework based on DFTB for fusing and removing ghosts from deep image features, called TransU-Fusion. First of all, we use the encoder in U-Net to extract image features of different exposures and map them to different dimensional feature spaces. By utilizing the symmetry of the U-Net structure, we can ultimately output these feature images as original size HDR images. Then, we further fuse high-dimensional space features using Dilated Residual Dense Block (DRDB) to expand the receptive field, which is beneficial for repairing over-saturated regions. We use the transformer in DFTB to perform low-pass filtering on low-dimensional space features and interact with global information to remove ghosts. Finally, the processed features are merged and output as an HDR image without ghosting artifacts through the decoder. After testing on datasets and comparing with benchmark and state-of-the-art models, the results demonstrate our model\u2019s excellent information fusion ability and stronger ghost removal capability.<\/jats:p>","DOI":"10.3390\/sym15071463","type":"journal-article","created":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T00:57:30Z","timestamp":1690160250000},"page":"1463","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhanced LDR Detail Rendering for HDR Fusion by TransU-Fusion Network"],"prefix":"10.3390","volume":"15","author":[{"given":"Bo","family":"Song","sequence":"first","affiliation":[{"name":"State Key Laboratory of Electronic Thin Films and Integrated Devices, School of Integrated Circult Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electronic Thin Films and Integrated Devices, School of Integrated Circult Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"Chengdu Image Design Technology Co., Ltd., 171# Hele 2nd Street, Chengdu 610213, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Yu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electronic Thin Films and Integrated Devices, School of Integrated Circult Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,7,23]]},"reference":[{"key":"ref_1","unstructured":"Nayar, S.K., and Mitsunaga, T. (2000, January 15). High dynamic range imaging: Spatially varying pixel exposures. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hilton Head, SC, USA."},{"key":"ref_2","unstructured":"Tumblin, J., Agrawal, A., and Raskar, R. (2005, January 20\u201325). Why I want a gradient camera. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"144","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_4","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_5","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015: 18th International Conference, Munich, Germany, 5\u20139 October 2015, Proceedings, Part III 18, Springer."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Yan, Q., Gong, D., Shi, Q., Hengel, A.V.D., Shen, C., Reid, I., and Zhang, Y. (2019, January 16\u201320). Attention-guided network for ghost-free high dynamic range imaging. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00185"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tian, Y., Kong, Y., Zhong, B., and Fu, Y. (2018, January 18\u201323). Residual dense network for image super-resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00262"},{"key":"ref_8","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_9","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_10","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_11","unstructured":"Park, N., and Kim, S. (2022). How do vision transformers work?. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4308","DOI":"10.1109\/TIP.2020.2971346","article-title":"Deep HDR imaging via a non-local network","volume":"29","author":"Yan","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_13","unstructured":"Grosch, T. (2006). Vision, Modeling and Visualization, RWTH Aachen."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1109\/MCG.2008.23","article-title":"Automatic high-dynamic range image generation for dynamic scenes","volume":"28","author":"Jacobs","year":"2008","journal-title":"IEEE Comput. Graph. Appl."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Pece, F., and Kautz, J. (2010, January 17\u201318). Bitmap movement detection: HDR for dynamic scenes. Proceedings of the Conference on Visual Media Production, London, UK.","DOI":"10.1109\/CVMP.2010.8"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2318","DOI":"10.1109\/TIP.2011.2170079","article-title":"Gradient-directed multiexposure composition","volume":"21","author":"Zhang","year":"2011","journal-title":"IEEE Trans. Image Process."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Heo, Y.S., Lee, K.M., Lee, S.U., Moon, Y., and Cha, J. (2010, January 8\u201312). Ghost-free high dynamic range imaging. Proceedings of the Computer Vision\u2014ACCV 2010: 10th Asian Conference on Computer Vision, Queenstown, New Zealand.","DOI":"10.1007\/978-3-642-19282-1_39"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Bogoni, L. (2000, January 3\u20137). Extending dynamic range of monochrome and color images through fusion. Proceedings of the 15th International Conference on Pattern Recognition, ICPR-2000, Barcelona, Spain.","DOI":"10.1109\/ICPR.2000.903475"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1145\/882262.882270","article-title":"High dynamic range video","volume":"22","author":"Kang","year":"2003","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1111\/j.1467-8659.2011.01870.x","article-title":"Freehand HDR imaging of moving scenes with simultaneous resolution enhancement","volume":"30","author":"Zimmer","year":"2011","journal-title":"Comput. Graph. Forum"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Gallo, O., Troccoli, A., Hu, J., Pulli, K., and Kautz, J. (2015, January 7\u201312). Locally non-rigid registration for mobile HDR photography. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Boston, MA, USA.","DOI":"10.1109\/CVPRW.2015.7301366"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"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_23","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_24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11\u201317). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Online.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Liu, J., Tang, J., and Wu, G. (2020, January 23\u201328). Residual feature distillation network for lightweight image super-resolution. Proceedings of the Computer Vision\u2014ECCV 2020 Workshops, Glasgow, UK.","DOI":"10.1007\/978-3-030-67070-2_2"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., and Timofte, R. (2021). Swinir: Image restoration using swin transformer. Electrical Engineering and Systems Science\u2014Image and Video Processing. arXiv.","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hui, Z., Gao, X., Yang, Y., and Wang, X. (2019, January 21\u201325). Lightweight image super-resolution with information multi-distillation network. Proceedings of the 27th ACM International Conference on Multimedia, Nice, France.","DOI":"10.1145\/3343031.3351084"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1109\/TPAMI.2020.3012548","article-title":"U2Fusion: A unified unsupervised image fusion network","volume":"44","author":"Xu","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., and Fei-Fei, L. (2016, January 11\u201314). Perceptual losses for real-time style transfer and super-resolution. Proceedings of the Computer Vision\u2014ECCV 2016: 14th European Conference, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref_30","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1111\/cgf.12818","article-title":"An objective deghosting quality metric for HDR images","volume":"35","author":"Tursun","year":"2016","journal-title":"Comput. Graph. Forum"},{"key":"ref_32","unstructured":"Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., and Liang, J. (2018). Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, 20 September 2018, Proceedings 4, Springer."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/15\/7\/1463\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:17:23Z","timestamp":1760127443000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/15\/7\/1463"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,23]]},"references-count":32,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["sym15071463"],"URL":"https:\/\/doi.org\/10.3390\/sym15071463","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2023,7,23]]}}}