{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T14:48:39Z","timestamp":1758811719578,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906018,62076032"],"award-info":[{"award-number":["61906018,62076032"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Project of State Grid Corporation of China","award":["SGJSXT00SGJS2000329"],"award-info":[{"award-number":["SGJSXT00SGJS2000329"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3657616","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"1130-1134","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["DiffHarmony: Latent Diffusion Model Meets Image Harmonization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8469-1123","authenticated-orcid":false,"given":"Pengfei","family":"Zhou","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4798-4233","authenticated-orcid":false,"given":"Fangxiang","family":"Feng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0314-8951","authenticated-orcid":false,"given":"Xiaojie","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Understanding and improving the realism of image composites. ACM Transactions on graphics (TOG), 31(4):1--10","author":"Xue Su","year":"2012","unstructured":"Su Xue, Aseem Agarwala, Julie Dorsey, and Holly Rushmeier. Understanding and improving the realism of image composites. ACM Transactions on graphics (TOG), 31(4):1--10, 2012."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.449"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.299"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"e_1_3_2_1_5_1","first-page":"4832","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Jiang Yifan","year":"2021","unstructured":"Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, and Zhangyang Wang. Ssh: a selfsupervised framework for image harmonization. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pages 4832--4841, 2021."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01460"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00166"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548031"},{"key":"e_1_3_2_1_9_1","article-title":"A structurepreserving and illumination-consistent cycle framework for image harmonization","author":"Cai Xun","year":"2023","unstructured":"Xun Cai, Qingjie Shi, Yanbo Gao, Shuai Li, Wei Hua, and Tian Xie. A structurepreserving and illumination-consistent cycle framework for image harmonization. IEEE Transactions on Multimedia, pages 1--15, 2023.","journal-title":"IEEE Transactions on Multimedia, pages 1--15"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611747"},{"key":"e_1_3_2_1_11_1","volume-title":"Segment anything model meets image harmonization","author":"Chen Haoxing","year":"2023","unstructured":"Haoxing Chen, Yaohui Li, Zhangxuan Gu, Zhuoer Xu, Jun Lan, and Huaxiong Li. Segment anything model meets image harmonization, 2023."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612404"},{"key":"e_1_3_2_1_13_1","series-title":"Proceedings of Machine Learning Research","first-page":"2256","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. Deep unsupervised learning using nonequilibrium thermodynamics. In Francis Bach and David Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research, pages 2256--2265, Lille, France, 07--09 Jul 2015. PMLR."},{"key":"e_1_3_2_1_14_1","volume-title":"Variational diffusion models","author":"Kingma Diederik P.","year":"2021","unstructured":"Diederik P. Kingma, Tim Salimans, Ben Poole, and Jonathan Ho. Variational diffusion models, 2021."},{"key":"e_1_3_2_1_15_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33:6840--6851, 2020.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"e_1_3_2_1_17_1","volume-title":"Denoising diffusion probabilistic models for robust image super-resolution in the wild","author":"Sahak Hshmat","year":"2023","unstructured":"Hshmat Sahak, Daniel Watson, Chitwan Saharia, and David Fleet. Denoising diffusion probabilistic models for robust image super-resolution in the wild, 2023."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_19_1","volume-title":"Image harmonization with diffusion model","author":"Li Jiajie","year":"2023","unstructured":"Jiajie Li, Jian Wang, Chen Wang, and Jinjun Xiong. Image harmonization with diffusion model, 2023."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"e_1_3_2_1_21_1","volume-title":"ACM SIGGRAPH 2022 Conference Proceedings","author":"Saharia Chitwan","year":"2021","unstructured":"Chitwan Saharia, William Chan, Huiwen Chang, Chris A. Lee, Jonathan Ho, Tim Salimans, David J. Fleet, and Mohammad Norouzi. Palette: Image-to-image diffusion models. ACM SIGGRAPH 2022 Conference Proceedings, 2021."},{"key":"e_1_3_2_1_22_1","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems, 34:8780--8794, 2021.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho Jonathan","year":"2021","unstructured":"Jonathan Ho and Tim Salimans. Classifier-free diffusion guidance. In NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications, 2021."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2975979"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428394"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01610"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00924"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01909"},{"key":"e_1_3_2_1_29_1","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras Tero","year":"2022","unstructured":"Tero Karras, Miika Aittala, Timo Aila, and Samuli Laine. Elucidating the design space of diffusion-based generative models. Advances in Neural Information Processing Systems, 35:26565--26577, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Phuket Thailand","acronym":"ICMR '24"},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3657616","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3657616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:49:01Z","timestamp":1755766141000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3657616"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":30,"alternative-id":["10.1145\/3652583.3657616","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3657616","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}