{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T19:05:59Z","timestamp":1774638359665,"version":"3.50.1"},"reference-count":80,"publisher":"Association for Computing Machinery (ACM)","issue":"12","license":[{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021YF3300700"],"award-info":[{"award-number":["2021YF3300700"]}]},{"name":"Beijing Natural Science Foundation","award":["4232025"],"award-info":[{"award-number":["4232025"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2024,12,31]]},"abstract":"<jats:p>\n            Image enhancement methods leveraging learning-based approaches have demonstrated impressive results when trained on synthetic degraded-clear image pairs. However, when deployed in real-world scenarios, such models often suffer significant performance degradation due to the inherent domain gap between synthetic and real degradations. To bridge this gap, we propose a novel\n            <jats:bold>Two-stage Contrastive Domain Adaptation image Enhancement (TCDAE)<\/jats:bold>\n            framework consisting of two key strategies: (1)\n            <jats:bold>Synthetic-to-Real Domain Transfer Learning (S2R-DTL)<\/jats:bold>\n            that effectively translates images from the synthetic degraded domain to the real degraded domain, aligning the domains at the pixel level, and (2)\n            <jats:bold>Degraded-to-Clear Domain Transfer Learning (D2C-DTL)<\/jats:bold>\n            that further adapts the enhancement model from the synthetic to the real domain by translating images from the real degraded domain to the real clean domain in both supervised and unsupervised branches. A unique aspect of our approach is the integration of a\n            <jats:bold>Domain Noise Contrastive Estimation (DoNCE)<\/jats:bold>\n            loss in both learning strategies. This specialized loss formulation enables TCDAE to robustly translate images across domains, even in scenarios lacking strong positive examples. Consequently, our framework can generate enhanced images with natural, realistic appearances akin to real clear images. Comprehensive experiments on real-world degraded scenes across diverse tasks, including dehazing, deraining, and deblurring, demonstrate the superiority of TCDAE over state-of-the-art methods, achieving improved visual quality, quantitative metrics, and downstream task performance.\n          <\/jats:p>","DOI":"10.1145\/3694973","type":"journal-article","created":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T16:49:55Z","timestamp":1725641395000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Real-World Scene Image Enhancement with Contrastive Domain Adaptation Learning"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5953-1215","authenticated-orcid":false,"given":"Yongheng","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China and School of Computer, BUPT, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8041-012X","authenticated-orcid":false,"given":"Yuanqiang","family":"Cai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China and School of Computer, BUPT, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6553-3444","authenticated-orcid":false,"given":"Danfeng","family":"Yan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China and School of Computer, BUPT, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9562-7356","authenticated-orcid":false,"given":"Rongheng","family":"Lin","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China and School of Computer, BUPT, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,26]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803046"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00230"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.185"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.18"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2598681"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/83.661187"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/2726947"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01713"},{"key":"e_1_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Xiang Chen Zhe-Cheng Fan Zhuoran Zheng Yufeng Li Yufeng Huang Longgang Dai Caihua Kong and Peng Li. 2022. Unpaired deep image dehazing using contrastive disentanglement learning. arXiv:2203.07677. Retrieved from https:\/\/arxiv.org\/pdf\/2203.07677","DOI":"10.1007\/978-3-031-19790-1_38"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00206"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475496"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00710"},{"key":"e_1_3_1_14_2","first-page":"11","article-title":"Referenceless prediction of perceptual fog density and perceptual image defogging","volume":"24","author":"Choi Lark Kwon","year":"2015","unstructured":"Lark Kwon Choi, Jaehee You, and Alan Conrad Bovik. 2015. Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Transactions on Image Processing 24, 11 (2015), 3888\u20133901.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00255"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00223"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2108306"},{"issue":"3","key":"e_1_3_1_18_2","first-page":"1","article-title":"Invertible grayscale with sparsity enforcing priors","volume":"17","author":"Du Yong","year":"2021","unstructured":"Yong Du, Yangyang Xu, Taizhong Ye, Qiang Wen, Chufeng Xiao, Junyu Dong, Guoqiang Han, and Shengfeng He. 2021. Invertible grayscale with sparsity enforcing priors. ACM Transactions on Multimedia Computing, Communications, and Applications 17, 3 (2021), 1\u201317.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/2651362"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2691802"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.186"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00572"},{"key":"e_1_3_1_23_2","first-page":"12","article-title":"Single image haze removal using dark channel prior","volume":"33","author":"He Kaiming","year":"2010","unstructured":"Kaiming He, Jian Sun, and Xiaoou Tang. 2010. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence 33, 12 (2010), 2341\u20132353.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_24_2","first-page":"1989","volume-title":"ICML","author":"Hoffman Judy","year":"2018","unstructured":"Judy Hoffman, Eric Tzeng, Taesung Park, Jun-Yan Zhu, Phillip Isola, Kate Saenko, Alexei Efros, and Trevor Darrell. 2018. CyCADA: Cycle-consistent adversarial domain adaptation. In ICML. PMLR, 1989\u20131998."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.432"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00764"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.392"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01690"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00837"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3557897"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00897"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00436"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2867951"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475432"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2952690"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2980173"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.34"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.299"},{"key":"e_1_3_1_39_2","first-page":"138","volume-title":"Pattern Recognition","author":"Lin Che-Tsung","year":"2023","unstructured":"Che-Tsung Lin, Jie-Long Kew, Chee Seng Chan, Shang-Hong Lai, and Christopher Zach. 2023. Cycle-object consistency for image-to-image domain adaptation. Pattern Recognition 138 (2023), 109416."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00741"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475331"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00744"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.82"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.35"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.180"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01983"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6865"},{"key":"e_1_3_1_50_2","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv:1804.02767. Retrieved from https:\/\/arxiv.org\/pdf\/1804.02767"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_10"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00343"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_12"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00288"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511021"},{"key":"e_1_3_1_56_2","first-page":"19847","volume-title":"ICML","author":"Shen Kendrick","year":"2022","unstructured":"Kendrick Shen, Robbie M. Jones, Ananya Kumar, Sang Michael Xie, Jeff Z. HaoChen, Tengyu Ma, and Percy Liang. 2022. Connect, not collapse: Explaining contrastive learning for unsupervised domain adaptation. In ICML. PMLR, 19847\u201319878."},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00366"},{"issue":"2","key":"e_1_3_1_58_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478457","article-title":"Sadnet: Semi-supervised single image dehazing method based on an attention mechanism","volume":"18","author":"Sun Ziyi","year":"2022","unstructured":"Ziyi Sun, Yunfeng Zhang, Fangxun Bao, Ping Wang, Xunxiang Yao, and Caiming Zhang. 2022. Sadnet: Semi-supervised single image dehazing method based on an attention mechanism. ACM Transactions on Multimedia Computing, Communications, and Applications 18, 2 (2022), 1\u201323.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587643"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00250"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/NCC.2015.7084843"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01255"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489520"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00400"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3074804"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01041"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2981922"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00573"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_30"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00613"},{"key":"e_1_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00337"},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.300"},{"key":"e_1_3_1_77_2","unstructured":"Yulun Zhang Kunpeng Li Kai Li Bineng Zhong and Yun Fu. 2019. Residual non-local attention networks for image restoration. arXiv:1903.10082. Retrieved from https:\/\/arxiv.org\/pdf\/1903.10082"},{"key":"e_1_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2968521"},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00560"},{"key":"e_1_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02083"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3694973","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3694973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:07Z","timestamp":1750295887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3694973"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,26]]},"references-count":80,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12,31]]}},"alternative-id":["10.1145\/3694973"],"URL":"https:\/\/doi.org\/10.1145\/3694973","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,26]]},"assertion":[{"value":"2023-08-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}