{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:56:40Z","timestamp":1783439800587,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Fund of China","award":["62176064"],"award-info":[{"award-number":["62176064"]}]},{"name":"Shanghai Municipal Science and Technology Commission","award":["22dz1204900"],"award-info":[{"award-number":["22dz1204900"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680848","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"10824-10832","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8160-1670","authenticated-orcid":false,"given":"Yibin","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7311-0698","authenticated-orcid":false,"given":"Weizhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Data Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6017-0552","authenticated-orcid":false,"given":"Jianwei","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3063-1957","authenticated-orcid":false,"given":"Cheng","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Omri Avrahami Dani Lischinski and Ohad Fried. 2022. Blended diffusion for text-driven editing of natural images. In CVPR. 18208--18218.","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01336-9"},{"key":"e_1_3_2_1_4_1","volume-title":"End-to-end visual editing with a generatively pre-trained artist","author":"Brown Andrew","unstructured":"Andrew Brown, Cheng-Yang Fu, Omkar Parkhi, Tamara L Berg, and Andrea Vedaldi. 2022. End-to-end visual editing with a generatively pre-trained artist. In ECCV. Springer, 18--35."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Peter J Burt and Edward H Adelson. 1987. The Laplacian pyramid as a compact image code. In Readings in computer vision. 671--679.","DOI":"10.1016\/B978-0-08-051581-6.50065-9"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Yanlu Cai Weizhong Zhang Yuan Wu and Cheng Jin. 2024. PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization. In CVPR. 2124--2133.","DOI":"10.1109\/CVPR52733.2024.00207"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Bor-Chun Chen and Andrew Kae. 2019. Toward realistic image compositing with adversarial learning. In CVPR. 8415--8424.","DOI":"10.1109\/CVPR.2019.00861"},{"key":"e_1_3_2_1_9_1","volume-title":"Dovenet: Deep image harmonization via domain verification. In CVPR. 8394--8403.","author":"Cong Wenyan","year":"2020","unstructured":"Wenyan Cong, Jianfu Zhang, Li Niu, Liu Liu, Zhixin Ling, Weiyuan Li, and Liqing Zhang. 2020. Dovenet: Deep image harmonization via domain verification. In CVPR. 8394--8403."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2975979"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Debidatta Dwibedi Ishan Misra and Martial Hebert. 2017. Cut paste and learn: Surprisingly easy synthesis for instance detection. In ICCV. 1301--1310.","DOI":"10.1109\/ICCV.2017.146"},{"key":"e_1_3_2_1_12_1","volume-title":"Xin Eric Wang, and William Yang Wang","author":"Feng Weixi","year":"2022","unstructured":"Weixi Feng, Xuehai He, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Pradyumna Narayana, Sugato Basu, Xin Eric Wang, and William Yang Wang. 2022. Training-free structured diffusion guidance for compositional text-to-image synthesis. arXiv preprint arXiv:2212.05032 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Oran Gafni and Lior Wolf. 2020. Wish you were here: Context-aware human generation. In CVPR. 7840--7849.","DOI":"10.1109\/CVPR42600.2020.00786"},{"key":"e_1_3_2_1_14_1","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)."},{"key":"e_1_3_2_1_15_1","volume-title":"Designing an encoder for fast personalization of text-to-image models. arXiv preprint arXiv:2302.12228","author":"Gal Rinon","year":"2023","unstructured":"Rinon Gal, Moab Arar, Yuval Atzmon, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2023. Designing an encoder for fast personalization of text-to-image models. arXiv preprint arXiv:2302.12228 (2023)."},{"key":"e_1_3_2_1_16_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. 2020. Denoising diffusion probabilistic models. NeurIPS, Vol. 33 (2020), 6840--6851.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_17_1","volume-title":"Classifier-Free Diffusion Guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19974"},{"key":"e_1_3_2_1_19_1","volume-title":"Ssh: A self-supervised framework for image harmonization. In ICCV. 4832--4841.","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. 2021. Ssh: A self-supervised framework for image harmonization. In ICCV. 4832--4841."},{"key":"e_1_3_2_1_20_1","volume-title":"Imagic: Text-based real image editing with diffusion models. In CVPR. 6007--6017.","author":"Kawar Bahjat","year":"2023","unstructured":"Bahjat Kawar, Shiran Zada, Oran Lang, Omer Tov, Huiwen Chang, Tali Dekel, Inbar Mosseri, and Michal Irani. 2023. Imagic: Text-based real image editing with diffusion models. In CVPR. 6007--6017."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Nupur Kumari Bingliang Zhang Richard Zhang Eli Shechtman and Jun-Yan Zhu. 2023. Multi-concept customization of text-to-image diffusion. In CVPR. 1931--1941.","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_2_1_22_1","volume-title":"Gligen: Open-set grounded text-to-image generation. In CVPR. 22511--22521.","author":"Li Yuheng","year":"2023","unstructured":"Yuheng Li, Haotian Liu, Qingyang Wu, Fangzhou Mu, Jianwei Yang, Jianfeng Gao, Chunyuan Li, and Yong Jae Lee. 2023. Gligen: Open-set grounded text-to-image generation. In CVPR. 22511--22521."},{"key":"e_1_3_2_1_23_1","volume-title":"St-gan: Spatial transformer generative adversarial networks for image compositing. In CVPR. 9455--9464.","author":"Lin Chen-Hsuan","year":"2018","unstructured":"Chen-Hsuan Lin, Ersin Yumer, Oliver Wang, Eli Shechtman, and Simon Lucey. 2018. St-gan: Spatial transformer generative adversarial networks for image compositing. In CVPR. 9455--9464."},{"key":"e_1_3_2_1_24_1","volume-title":"Arshadowgan: Shadow generative adversarial network for augmented reality in single light scenes. In CVPR. 8139--8148.","author":"Liu Daquan","year":"2020","unstructured":"Daquan Liu, Chengjiang Long, Hongpan Zhang, Hanning Yu, Xinzhi Dong, and Chunxia Xiao. 2020. Arshadowgan: Shadow generative adversarial network for augmented reality in single light scenes. In CVPR. 8139--8148."},{"key":"e_1_3_2_1_25_1","volume-title":"OPA: object placement assessment dataset. arXiv preprint arXiv:2107.01889","author":"Liu Liu","year":"2021","unstructured":"Liu Liu, Zhenchen Liu, Bo Zhang, Jiangtong Li, Li Niu, Qingyang Liu, and Liqing Zhang. 2021. OPA: object placement assessment dataset. arXiv preprint arXiv:2107.01889 (2021)."},{"key":"e_1_3_2_1_26_1","volume-title":"Compositional visual generation with composable diffusion models","author":"Liu Nan","unstructured":"Nan Liu, Shuang Li, Yilun Du, Antonio Torralba, and Joshua B Tenenbaum. 2022. Compositional visual generation with composable diffusion models. In ECCV. Springer, 423--439."},{"key":"e_1_3_2_1_27_1","volume-title":"Dpm-solver: Fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095","author":"Lu Cheng","year":"2022","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 2022. Dpm-solver: Fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Shilin Lu Yanzhu Liu and Adams Wai-Kin Kong. 2023. TF-ICON: Diffusion-based training-free cross-Domain image composition. In ICCV. 2294--2305.","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"e_1_3_2_1_29_1","unstructured":"Chenlin Meng Yutong He Yang Song Jiaming Song Jiajun Wu Jun-Yan Zhu and Stefano Ermon. 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In ICLR."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28231"},{"key":"e_1_3_2_1_31_1","volume-title":"Making images real again: A comprehensive survey on deep image composition. arXiv preprint arXiv:2106.14490","author":"Niu Li","year":"2021","unstructured":"Li Niu, Wenyan Cong, Liu Liu, Yan Hong, Bo Zhang, Jing Liang, and Liqing Zhang. 2021. Making images real again: A comprehensive survey on deep image composition. arXiv preprint arXiv:2106.14490 (2021)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28232"},{"key":"e_1_3_2_1_33_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In ICML. 8748--8763."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In CVPR. 10684--10695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_35_1","volume-title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In CVPR. 22500--22510.","author":"Ruiz Nataniel","year":"2023","unstructured":"Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, and Kfir Aberman. 2023. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In CVPR. 22500--22510."},{"key":"e_1_3_2_1_36_1","volume-title":"SSN: Soft shadow network for image compositing. In CVPR. 4380--4390.","author":"Sheng Yichen","year":"2021","unstructured":"Yichen Sheng, Jianming Zhang, and Bedrich Benes. 2021. SSN: Soft shadow network for image compositing. In CVPR. 4380--4390."},{"key":"e_1_3_2_1_37_1","volume-title":"Soo Ye Kim, and Daniel Aliaga","author":"Song Yizhi","year":"2022","unstructured":"Yizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen, Brian Price, Jianming Zhang, Soo Ye Kim, and Daniel Aliaga. 2022. Objectstitch: Generative object compositing. arXiv preprint arXiv:2212.00932 (2022)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Shashank Tripathi Siddhartha Chandra Amit Agrawal Ambrish Tyagi James M Rehg and Visesh Chari. 2019. Learning to generate synthetic data via compositing. In CVPR. 461--470.","DOI":"10.1109\/CVPR.2019.00055"},{"key":"e_1_3_2_1_39_1","volume-title":"NeurIPS","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS, Vol. 30."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Yibin Wang Yuchao Feng Jie Wu Honghui Xu and Jianwei Zheng. 2023. CA-GAN: Object placement via coalescing attention based generative adversarial network. In ICME. 2375--2380.","DOI":"10.1109\/ICME55011.2023.00405"},{"key":"e_1_3_2_1_41_1","unstructured":"Yibin Wang Yuchao Feng and Jianwei Zheng. 2024. Learning Object Placement via Convolution Scoring Attention. In BMVC. 1--12."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Yibin Wang Weizhong Zhang Jianwei Zheng and Cheng Jin. 2024. High-fidelity Person-centric Subject-to-Image Synthesis. In CVPR. 7675--7684.","DOI":"10.1109\/CVPR52733.2024.00733"},{"key":"e_1_3_2_1_43_1","volume-title":"Investigating prompt engineering in diffusion models. arXiv preprint arXiv:2211.15462","author":"Witteveen Sam","year":"2022","unstructured":"Sam Witteveen and Martin Andrews. 2022. Investigating prompt engineering in diffusion models. arXiv preprint arXiv:2211.15462 (2022)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350944"},{"key":"e_1_3_2_1_45_1","volume-title":"Dccf: Deep comprehensible color filter learning framework for high-resolution image harmonization","author":"Xue Ben","year":"2022","unstructured":"Ben Xue, Shenghui Ran, Quan Chen, Rongfei Jia, Binqiang Zhao, and Xing Tang. 2022. Dccf: Deep comprehensible color filter learning framework for high-resolution image harmonization. In ECCV. Springer, 300--316."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Binxin Yang Shuyang Gu Bo Zhang Ting Zhang Xuejin Chen Xiaoyan Sun Dong Chen and Fang Wen. 2023. Paint by example: Exemplar-based image editing with diffusion models. In CVPR. 18381--18391.","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"He Zhang Jianming Zhang Federico Perazzi Zhe Lin and Vishal M Patel. 2021. Deep image compositing. In WACV. 365--374.","DOI":"10.1109\/WACV48630.2021.00041"},{"key":"e_1_3_2_1_48_1","volume-title":"Learning object placement by inpainting for compositional data augmentation","author":"Zhang Lingzhi","unstructured":"Lingzhi Zhang, Tarmily Wen, Jie Min, Jiancong Wang, David Han, and Jianbo Shi. 2020. Learning object placement by inpainting for compositional data augmentation. In ECCV. Springer, 566--581."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Lingzhi Zhang Tarmily Wen and Jianbo Shi. 2020. Deep image blending. In WACV. 231--240.","DOI":"10.1109\/WACV45572.2020.9093632"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Richard Zhang Phillip Isola Alexei A Efros Eli Shechtman and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR. 586--595.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0136-1"},{"key":"e_1_3_2_1_52_1","volume-title":"Forgedit: Text guided image editing via learning and forgetting. arXiv preprint arXiv:2309.10556","author":"Zhang Shiwen","year":"2023","unstructured":"Shiwen Zhang, Shuai Xiao, and Weilin Huang. 2023. Forgedit: Text guided image editing via learning and forgetting. arXiv preprint arXiv:2309.10556 (2023)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680848","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:08Z","timestamp":1750295888000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680848"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":52,"alternative-id":["10.1145\/3664647.3680848","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680848","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}