{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:51:58Z","timestamp":1781020318915,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":74,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62131003 and 62021001"],"award-info":[{"award-number":["62131003 and 62021001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612261","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"1779-1788","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Mutual-Guided Dynamic Network for Image Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3468-1417","authenticated-orcid":false,"given":"Yuanshen","family":"Guan","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6662-3671","authenticated-orcid":false,"given":"Ruikang","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5994-6288","authenticated-orcid":false,"given":"Mingde","family":"Yao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1953-3339","authenticated-orcid":false,"given":"Lizhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9787-7460","authenticated-orcid":false,"given":"Zhiwei","family":"Xiong","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2019.2956873"},{"key":"e_1_3_2_1_2_1","volume-title":"Image fusion of visible and thermal images for fruit detection. Biosystems engineering 103, 1","author":"Bulanon DM","year":"2009","unstructured":"DM Bulanon, TF Burks, and V Alchanatis. 2009. Image fusion of visible and thermal images for fruit detection. Biosystems engineering 103, 1 (2009), 12--22."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2794218"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276506"},{"key":"e_1_3_2_1_5_1","volume-title":"A new automated quality assessment algorithm for image fusion. Image and vision computing 27, 10","author":"Chen Yin","year":"2009","unstructured":"Yin Chen and Rick S Blum. 2009. A new automated quality assessment algorithm for image fusion. Image and vision computing 27, 10 (2009), 1421--1432."},{"key":"e_1_3_2_1_6_1","volume-title":"Deep convolutional neural network for multi-modal image restoration and fusion","author":"Deng Xin","year":"2020","unstructured":"Xin Deng and Pier Luigi Dragotti. 2020. Deep convolutional neural network for multi-modal image restoration and fusion. IEEE transactions on pattern analysis and machine intelligence 43, 10 (2020), 3333--3348."},{"key":"e_1_3_2_1_7_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005601"},{"key":"e_1_3_2_1_9_1","volume-title":"A new image fusion performance metric based on visual information fidelity. Information fusion 14, 2","author":"Han Yu","year":"2013","unstructured":"Yu Han, Yunze Cai, Yin Cao, and Xiaoming Xu. 2013. A new image fusion performance metric based on visual information fidelity. Information fusion 14, 2 (2013), 127--135."},{"key":"e_1_3_2_1_10_1","volume-title":"Guided image filtering","author":"He Kaiming","year":"2012","unstructured":"Kaiming He, Jian Sun, and Xiaoou Tang. 2012. Guided image filtering. IEEE transactions on pattern analysis and machine intelligence 35, 6 (2012), 1397--1409."},{"key":"e_1_3_2_1_11_1","unstructured":"Lingzhi He Hongguang Zhu Feng Li Huihui Bai Runmin Cong Chunjie Zhang Chunyu Lin Meiqin Liu and Yao Zhao. 2021. Towards fast and accurate realworld depth super-resolution: Benchmark dataset and baseline. In CVPR."},{"key":"e_1_3_2_1_12_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Jun Hu Orazio Gallo Kari Pulli and Xiaobai Sun. 2013. HDR deghosting: How to deal with saturation?. In CVPR.","DOI":"10.1109\/CVPR.2013.154"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aqpro.2015.02.019"},{"key":"e_1_3_2_1_15_1","volume-title":"Tinne Tuytelaars, and Luc V Gool.","author":"Jia Xu","year":"2016","unstructured":"Xu Jia, Bert De Brabandere, Tinne Tuytelaars, and Luc V Gool. 2016. Dynamic filter networks. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_16_1","volume-title":"Jaeyeon Kang, and Seon Joo Kim.","author":"Jo Younghyun","year":"2018","unstructured":"Younghyun Jo, Seoung Wug Oh, Jaeyeon Kang, and Seon Joo Kim. 2018. Deep video super-resolution network using dynamic upsampling filters without explicit motion compensation. In CVPR."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073609"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01386-z"},{"key":"e_1_3_2_1_19_1","volume-title":"Koalanet: Blind superresolution using kernel-oriented adaptive local adjustment. In CVPR.","author":"Kim Soo Ye","year":"2021","unstructured":"Soo Ye Kim, Hyeonjun Sim, and Munchurl Kim. 2021. Koalanet: Blind superresolution using kernel-oriented adaptive local adjustment. In CVPR."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_21_1","unstructured":"Junyong Lee Hyeongseok Son Jaesung Rim Sunghyun Cho and Seungyong Lee. 2021. Iterative filter adaptive network for single image defocus deblurring. In CVPR."},{"key":"e_1_3_2_1_22_1","volume-title":"Overcoming catastrophic forgetting by incremental moment matching. Advances in neural information processing systems 30","author":"Lee Sang-Woo","year":"2017","unstructured":"Sang-Woo Lee, Jin-Hwa Kim, Jaehyun Jun, Jung-Woo Ha, and Byoung-Tak Zhang. 2017. Overcoming catastrophic forgetting by incremental moment matching. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.optcom.2014.12.048"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2976190"},{"key":"e_1_3_2_1_25_1","unstructured":"Yijun Li Jia-Bin Huang Narendra Ahuja and Ming-Hsuan Yang. 2016. Deep joint image filtering. In ECCV."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2890623"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"e_1_3_2_1_28_1","volume-title":"A general framework for image fusion based on multi-scale transform and sparse representation. Information fusion 24","author":"Liu Yu","year":"2015","unstructured":"Yu Liu, Shuping Liu, and Zengfu Wang. 2015. A general framework for image fusion based on multi-scale transform and sparse representation. Information fusion 24 (2015), 147--164."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2014.05.004"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Zhen Liu Yinglong Wang Bing Zeng and Shuaicheng Liu. 2022. Ghost-free High Dynamic Range Imaging with Context-aware Transformer. In ECCV.","DOI":"10.1007\/978-3-031-19800-7_20"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2016.02.001"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105686"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2952716"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2671921"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Jonathan T Barron Jiawen Chen Dillon Sharlet Ren Ng and Robert Carroll. 2018. Burst denoising with kernel prediction networks. In CVPR.","DOI":"10.1109\/CVPR.2018.00265"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2014.10.004"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3064433"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01687"},{"key":"e_1_3_2_1_40_1","volume-title":"Deepfuse: A deep unsupervised approach for exposure fusion with extreme exposure image pairs. In ICCV.","author":"Prabhakar K Ram","year":"2017","unstructured":"K Ram Prabhakar, V Sai Srikar, and R Venkatesh Babu. 2017. Deepfuse: A deep unsupervised approach for exposure fusion with extreme exposure image pairs. In ICCV."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.2945910"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366222"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2290435"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2150235"},{"key":"e_1_3_2_1_45_1","volume-title":"Indoor segmentation and support inference from rgbd images. ECCV","author":"Silberman Nathan","year":"2012","unstructured":"Nathan Silberman, Derek Hoiem, Pushmeet Kohli, and Rob Fergus. 2012. Indoor segmentation and support inference from rgbd images. ECCV (2012)."},{"key":"e_1_3_2_1_46_1","unstructured":"Irwin Sobel Gary Feldman et al. 1968. A 3x3 isotropic gradient operator for image processing. a talk at the Stanford Artificial Project in (1968) 271--272."},{"key":"e_1_3_2_1_47_1","unstructured":"Hang Su Varun Jampani Deqing Sun Orazio Gallo Erik Learned-Miller and Jan Kautz. 2019. Pixel-adaptive convolutional neural networks. In CVPR."},{"key":"e_1_3_2_1_48_1","volume-title":"Bilateral filtering for gray and color images","author":"Tomasi Carlo","unstructured":"Carlo Tomasi and Roberto Manduchi. 1998. Bilateral filtering for gray and color images. In ICCV. IEEE, 839--846."},{"key":"e_1_3_2_1_49_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_50_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_51_1","unstructured":"Shangzhe Wu Jiarui Xu Yu-Wing Tai and Chi-Keung Tang. 2018. Deep high dynamic range imaging with large foreground motions. In ECCV."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3012548"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2999855"},{"key":"e_1_3_2_1_54_1","volume-title":"Understanding and improving layer normalization. Advances in Neural Information Processing Systems 32","author":"Xu Jingjing","year":"2019","unstructured":"Jingjing Xu, Xu Sun, Zhiyuan Zhang, Guangxiang Zhao, and Junyang Lin. 2019. Understanding and improving layer normalization. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00052"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475189"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00881"},{"key":"e_1_3_2_1_58_1","volume-title":"MFFW: A new dataset for multi-focus image fusion. arXiv preprint arXiv:2002.04780","author":"Xu Shuang","year":"2020","unstructured":"Shuang Xu, Xiaoli Wei, Chunxia Zhang, Junmin Liu, and Jiangshe Zhang. 2020. MFFW: A new dataset for multi-focus image fusion. arXiv preprint arXiv:2002.04780 (2020)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1049\/el:"},{"key":"e_1_3_2_1_60_1","unstructured":"Qingsen Yan Dong Gong Qinfeng Shi Anton van den Hengel Chunhua Shen Ian Reid and Yanning Zhang. 2019. Attention-guided network for ghost-free high dynamic range imaging. In CVPR."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548177"},{"key":"e_1_3_2_1_62_1","volume-title":"Spectral-depth imaging with deep learning based reconstruction. Optics express 27, 26","author":"Yao Mingde","year":"2019","unstructured":"Mingde Yao, Zhiwei Xiong, Lizhi Wang, Dong Liu, and Xuejin Chen. 2019. Spectral-depth imaging with deep learning based reconstruction. Optics express 27, 26 (2019), 38312--38325."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"e_1_3_2_1_64_1","volume-title":"International conference on machine learning. PMLR, 3987--3995","author":"Zenke Friedemann","year":"2017","unstructured":"Friedemann Zenke, Ben Poole, and Surya Ganguli. 2017. Continual learning through synaptic intelligence. In International conference on machine learning. PMLR, 3987--3995."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.08.022"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"crossref","unstructured":"Hao Zhang Han Xu Yang Xiao Xiaojie Guo and Jiayi Ma. 2020. Rethinking the image fusion: A fast unified image fusion network based on proportional maintenance of gradient and intensity. In AAAI.","DOI":"10.1609\/aaai.v34i07.6975"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00430"},{"key":"e_1_3_2_1_68_1","volume-title":"Benchmarking and comparing multi-exposure image fusion algorithms. Information Fusion","author":"Zhang Xingchen","year":"2021","unstructured":"Xingchen Zhang. 2021. Benchmarking and comparing multi-exposure image fusion algorithms. Information Fusion (2021), 111--131."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.07.011"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"crossref","unstructured":"Zixiang Zhao Jiangshe Zhang Shuang Xu Zudi Lin and Hanspeter Pfister. 2022. Discrete cosine transform network for guided depth map super-resolution. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00561"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"crossref","unstructured":"Man Zhou Keyu Yan Jie Huang Zihe Yang Xueyang Fu and Feng Zhao. 2022. Mutual information-driven pan-sharpening. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00184"},{"key":"e_1_3_2_1_73_1","unstructured":"Shangchen Zhou Jiawei Zhang Jinshan Pan Haozhe Xie Wangmeng Zuo and Jimmy Ren. 2019. Spatio-temporal filter adaptive network for video deblurring. In ICCV."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2013.11.005"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612261","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:04:26Z","timestamp":1755821066000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612261"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":74,"alternative-id":["10.1145\/3581783.3612261","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612261","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}