{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T21:36:10Z","timestamp":1778276170979,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":54,"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 Key R&D Program of China","award":["2021YFB3301503"],"award-info":[{"award-number":["2021YFB3301503"]}]},{"name":"National Natural Science Foundation of China","award":["61902028"],"award-info":[{"award-number":["61902028"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612492","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"4340-4348","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Style Transfer Meets Super-Resolution: Advancing Unpaired Infrared-to-Visible Image Translation with Detail Enhancement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0092-7867","authenticated-orcid":false,"given":"Yirui","family":"Shen","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2605-9265","authenticated-orcid":false,"given":"Jingxuan","family":"Kang","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6807-9905","authenticated-orcid":false,"given":"Shuang","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9709-9315","authenticated-orcid":false,"given":"Zhenjie","family":"Yu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3598-0443","authenticated-orcid":false,"given":"Shuigen","family":"Wang","sequence":"additional","affiliation":[{"name":"Yantai IRay Technologies Lt. Co., Yantai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Matthew Amodio and Smita Krishnaswamy. 2019. TraVeLGAN: Image-To-Image Translation by Transformation Vector Learning. In CVPR. 8983--8992.","DOI":"10.1109\/CVPR.2019.00919"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Adrian Bulat Jing Yang and Georgios Tzimiropoulos. 2018. To Learn Image Super-Resolution Use a GAN to Learn How to Do Image Degradation First. In ECCV. 187--202.","DOI":"10.1007\/978-3-030-01231-1_12"},{"key":"e_1_3_2_1_3_1","volume-title":"Kaiming He, and Xiaoou Tang.","author":"Dong Chao","year":"2014","unstructured":"Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. 2014. Learning a Deep Convolutional Network for Image Super-Resolution. In ECCV. 184--199."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_3_2_1_5_1","volume-title":"Chen Change Loy, and Xiaoou Tang","author":"Dong Chao","year":"2016","unstructured":"Chao Dong, Chen Change Loy, and Xiaoou Tang. 2016a. Accelerating the Super-Resolution Convolutional Neural Network. In ECCV. 391--407."},{"key":"e_1_3_2_1_6_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR."},{"key":"e_1_3_2_1_7_1","unstructured":"FLIR. 2018. FREE FLIR Thermal Dataset for Algorithm Training. https:\/\/www.flir.com\/oem\/adas\/adas-dataset-form\/"},{"key":"e_1_3_2_1_8_1","volume-title":"Deepu Rajan, Ee Sin Ng, and Zhiyong Huang.","author":"Gupta Raj Kumar","year":"2012","unstructured":"Raj Kumar Gupta, Alex Yong Sang Chia, Deepu Rajan, Ee Sin Ng, and Zhiyong Huang. 2012. Image colorization using similar images. In ACM MM. 369--378."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Muhammad Haris Gregory Shakhnarovich and Norimichi Ukita. 2018. Deep Back-Projection Networks for Super-Resolution. In CVPR. 1664--1673.","DOI":"10.1109\/CVPR.2018.00179"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"M. A. Hogervorst and A. Toet. 2007. Fast and true-to-life application of daytime colours to night-time imagery. In ICIF. 1--8.","DOI":"10.1109\/ICIF.2007.4407987"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Jiaxing Huang Dayan Guan Aoran Xiao and Shijian Lu. 2021. Cross-View Regularization for Domain Adaptive Panoptic Segmentation. In CVPR. 10133--10144.","DOI":"10.1109\/CVPR46437.2021.01000"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Xun Huang Ming-Yu Liu Serge J. Belongie and Jan Kautz. 2018. Multimodal Unsupervised Image-to-Image Translation. In ECCV. 179--196.","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"e_1_3_2_1_13_1","unstructured":"Yan Huang Wei Wang and Liang Wang. 2015. Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution. In NIPS. 235--243."},{"key":"e_1_3_2_1_14_1","volume-title":"Generative Adversarial Networks. arXiv preprint arXiv:1406.2661","author":"Goodfellow Ian","year":"2014","unstructured":"Goodfellow Ian J., Pouget-Abadie Jean, Mirza Mehdi, Xu Bing, Warde-Farley David, Ozair Sherjil, Courville Aaron, and Bengio Yoshua. 2014. Generative Adversarial Networks. arXiv preprint arXiv:1406.2661 (2014)."},{"key":"e_1_3_2_1_15_1","volume-title":"TSIT: A Simple and Versatile Framework for Image-to-Image Translation. In ECCV. 206--222.","author":"Jiang Liming","year":"2020","unstructured":"Liming Jiang, Changxu Zhang, Mingyang Huang, Chunxiao Liu, Jianping Shi, and Chen Change Loy. 2020. TSIT: A Simple and Versatile Framework for Image-to-Image Translation. In ECCV. 206--222."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Zhu Jun-Yan Park Taesung Isola Phillip and Efros Alexei A. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In ICCV. 2223--2232.","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Chanyong Jung Gihyun Kwon and Jong Chul Ye. 2022. Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks. In CVPR. 18239--18248.","DOI":"10.1109\/CVPR52688.2022.01772"},{"key":"e_1_3_2_1_18_1","volume-title":"Jung Kwon Lee, and Kyoung Mu Lee","author":"Kim Jiwon","year":"2016","unstructured":"Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee. 2016. Accurate Image Super-Resolution Using Very Deep Convolutional Networks. In CVPR. 1646--1654."},{"key":"e_1_3_2_1_19_1","volume-title":"Jung Kwon Lee, and Jiwon Kim","author":"Kim Taeksoo","year":"2017","unstructured":"Taeksoo Kim, Moonsu Cha, Hyunsoo Kim, Jung Kwon Lee, and Jiwon Kim. 2017. Learning to discover cross-domain relations with generative adversarial networks. In ICML. 1857--1865."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Christian Ledig Lucas Theis Ferenc Huszar Jose Caballero Andrew Cunningham Alejandro Acosta Andrew P. Aitken Alykhan Tejani Johannes Totz Zehan Wang and Wenzhe Shi. 2017. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. In CVPR. 105--114.","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Hsin-Ying Lee Hung-Yu Tseng Jia-Bin Huang Maneesh Singh and Ming-Hsuan Yang. 2018. Diverse Image-to-Image Translation via Disentangled Representations. In ECCV. 36--52.","DOI":"10.1007\/978-3-030-01246-5_3"},{"key":"e_1_3_2_1_22_1","volume-title":"Kai Chen, and Shuigen Wang.","author":"Li Shuang","year":"2021","unstructured":"Shuang Li, Bingfeng Han, Zhenjie Yu, Chi Harold Liu, Kai Chen, and Shuigen Wang. 2021. I2V-GAN: Unpaired Infrared-to-Visible Video Translation. In ACM MM. 3061--3069."},{"key":"e_1_3_2_1_23_1","volume-title":"SwinIR: Image Restoration Using Swin Transformer. In ICCV Workshop. 1833--1844","author":"Liang Jingyun","year":"2021","unstructured":"Jingyun Liang, Jiezhang Cao, Guolei Sun, Kai Zhang, Luc Van Gool, and Radu Timofte. 2021. SwinIR: Image Restoration Using Swin Transformer. In ICCV Workshop. 1833--1844."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Yaoyuan Liang. 2021. Unsupervised Super Resolution Reconstruction of Traffic Surveillance Vehicle Images. In ICMLC. 336--341.","DOI":"10.1145\/3457682.3457734"},{"key":"e_1_3_2_1_25_1","unstructured":"Ming-Yu Liu and Oncel Tuzel. 2016. Coupled generative adversarial networks. In NIPS. 469--477."},{"key":"e_1_3_2_1_26_1","unstructured":"Heusel Martin Ramsauer Hubert Unterthiner Thomas Nessler Bernhard and Hochreiter Sepp. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. In NIPS. 6626--6637."},{"key":"e_1_3_2_1_27_1","unstructured":"Youssef Alami Mejjati Christian Richardt James Tompkin Darren Cosker and Kwang In Kim. 2018. Unsupervised Attention-guided Image-to-Image Translation. In NIPS. 3697--3707."},{"key":"e_1_3_2_1_28_1","volume-title":"Conditional Generative Adversarial Nets. arXiv preprint arXiv:1411.1784","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero. 2014. Conditional Generative Adversarial Nets. arXiv preprint arXiv:1411.1784 (2014)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Taesung Park Alexei A. Efros Richard Zhang and Jun-Yan Zhu. 2020. Contrastive Learning for Unpaired Image-to-Image Translation. In ECCV. 319--345.","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Isola Phillip Zhu Jun-Yan Zhou Tinghui and Efros Alexei A. 2017. Image-to-image translation with conditional adversarial networks. In CVPR. 1125--1134.","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_31_1","unstructured":"Alec Radford Luke Metz and Soumith Chintala. 2016. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. In ICLR."},{"key":"e_1_3_2_1_32_1","volume-title":"YOLOv3: An Incremental Improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. YOLOv3: An Incremental Improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_33_1","unstructured":"Tim Salimans Ian Goodfellow Wojciech Zaremba Vicki Cheung Alec Radford and Xi Chen. 2016. Improved Techniques for Training GANs. In NIPS. 2226--2234."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Wenzhe Shi Jose Caballero Ferenc Huszar Johannes Totz Andrew P. Aitken Rob Bishop Daniel Rueckert and Zehan Wang. 2016. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. In CVPR. 1874--1883.","DOI":"10.1109\/CVPR.2016.207"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Assaf Shocher Nadav Cohen and Michal Irani. 2018. \"Zero-Shot\" Super-Resolution Using Deep Internal Learning. In CVPR. 3118--3126.","DOI":"10.1109\/CVPR.2018.00329"},{"key":"e_1_3_2_1_36_1","volume-title":"Angel Domingo Sappa, and Boris Xavier Vintimilla","author":"Suarez Patricia L.","year":"2017","unstructured":"Patricia L. Suarez, Angel Domingo Sappa, and Boris Xavier Vintimilla. 2017. Infrared Image Colorization Based on a Triplet DCGAN Architecture. In CVPR. 212--217."},{"key":"e_1_3_2_1_37_1","volume-title":"Natural colour mapping for multiband nightvision imagery. Information Fusion","author":"Toet Alexander","year":"2003","unstructured":"Alexander Toet. 2003. Natural colour mapping for multiband nightvision imagery. Information Fusion (2003)."},{"key":"e_1_3_2_1_38_1","unstructured":"Longguang Wang Yingqian Wang Xiaoyu Dong Qingyu Xu Jungang Yang Wei An and Yulan Guo. 2021a. Unsupervised Degradation Representation Learning for Blind Super-Resolution. In CVPR. 10581--10590."},{"key":"e_1_3_2_1_39_1","unstructured":"Longguang Wang Yingqian Wang Xiaoyu Dong Qingyu Xu Jungang Yang Wei An and Yulan Guo. 2021b. Unsupervised Degradation Representation Learning for Blind Super-Resolution. In CVPR. 10581--10590."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Ting-Chun Wang Ming-Yu Liu Jun-Yan Zhu Andrew Tao Jan Kautz and Bryan Catanzaro. 2018a. High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs. In CVPR. 8798--8807.","DOI":"10.1109\/CVPR.2018.00917"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Wei Wang Haochen Zhang Zehuan Yuan and Changhu Wang. 2021d. Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective. In ICCV. 4298--4307.","DOI":"10.1109\/ICCV48922.2021.00428"},{"key":"e_1_3_2_1_42_1","volume-title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data. In ICCV Workshops. 1905--1914","author":"Wang Xintao","year":"2021","unstructured":"Xintao Wang, Liangbin Xie, Chao Dong, and Ying Shan. 2021c. Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data. In ICCV Workshops. 1905--1914."},{"key":"e_1_3_2_1_43_1","volume-title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. In ECCV Workshops. 63--79","author":"Wang Xintao","year":"2018","unstructured":"Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, and Chen Change Loy. 2018c. ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. In ECCV Workshops. 63--79."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00131"},{"key":"e_1_3_2_1_45_1","volume-title":"Chi Harold Liu, and Xinjing Cheng","author":"Xie Binhui","year":"2022","unstructured":"Binhui Xie, Longhui Yuan, Shuang Li, Chi Harold Liu, and Xinjing Cheng. 2022. Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation. In CVPR. 8058--8068."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Xuewen Yang Dongliang Xie and Xin Wang. 2018. Crossing-Domain Generative Adversarial Networks for Unsupervised Multi-Domain Image-to-Image Translation. In ACM MM. 374--382.","DOI":"10.1145\/3240508.3240716"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Zili Yi Hao (Richard) Zhang Ping Tan and Minglun Gong. 2017. DualGAN: Unsupervised Dual Learning for Image-to-Image Translation. In ICCV. 2868--2876.","DOI":"10.1109\/ICCV.2017.310"},{"key":"e_1_3_2_1_48_1","volume-title":"Chi Harold Liu, and Shuigen Wang","author":"Yu Zhenjie","year":"2022","unstructured":"Zhenjie Yu, Kai Chen, Shuang Li, Bingfeng Han, Chi Harold Liu, and Shuigen Wang. 2022. ROMA: Cross-Domain Region Similarity Matching for Unpaired Nighttime Infrared to Daytime Visible Video Translation. In ACM MM. 5294--5302."},{"key":"e_1_3_2_1_49_1","volume-title":"Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In CVPR. 8789--8797.","author":"Yunjey Choi","year":"2018","unstructured":"Choi Yunjey, Choi Minje, Kim Munyoung, Ha Jung-Woo, Kim Sunghun, and Choo Jaegul. 2018. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In CVPR. 8789--8797."},{"key":"e_1_3_2_1_50_1","volume-title":"Self-Attention Generative Adversarial Networks. arXiv preprint arXiv:1805.08318","author":"Zhang Han","year":"2018","unstructured":"Han Zhang, Ian Goodfellow, Dimitris Metaxas, and Augustus Odena. 2018. Self-Attention Generative Adversarial Networks. arXiv preprint arXiv:1805.08318 (2018)."},{"key":"e_1_3_2_1_51_1","volume-title":"Luc Van Gool, and Radu Timofte","author":"Zhang Kai","year":"2021","unstructured":"Kai Zhang, Jingyun Liang, Luc Van Gool, and Radu Timofte. 2021. Designing a Practical Degradation Model for Deep Blind Image Super-Resolution. In ICCV. 4771--4780."},{"key":"e_1_3_2_1_52_1","volume-title":"VIFB: A Visible and Infrared Image Fusion Benchmark. In CVPR. 468--478.","author":"Zhang Xingchen","year":"2020","unstructured":"Xingchen Zhang, Ping Ye, and Gang Xiao. 2020. VIFB: A Visible and Infrared Image Fusion Benchmark. In CVPR. 468--478."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Chuanxia Zheng Tat-Jen Cham and Jianfei Cai. 2021. The Spatially-Correlative Loss for Various Image Translation Tasks. In CVPR. 16407--16417.","DOI":"10.1109\/CVPR46437.2021.01614"},{"key":"e_1_3_2_1_54_1","unstructured":"Jun-Yan Zhu Richard Zhang Deepak Pathak Trevor Darrell Alexei A Efros Oliver Wang and Eli Shechtman. 2017. Toward multimodal image-to-image translation. In NIPS. 465--476."}],"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\/3581783.3612492","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:02:39Z","timestamp":1755820959000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612492"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":54,"alternative-id":["10.1145\/3581783.3612492","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612492","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"}}]}}