{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:05:28Z","timestamp":1765343128595,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"name":"NSFC62431015\u00f0the Fundamental Research Funds for the Central Universities, Shanghai\u00a0Key\u00a0Laboratory\u00a0of\u00a0Digital\u00a0Media\u00a0Processing and Transmission under Grant","award":["22DZ2229005, 111 project BP0719010"],"award-info":[{"award-number":["22DZ2229005, 111 project BP0719010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755603","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:27:39Z","timestamp":1761377259000},"page":"10361-10369","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["<i>FreeInsert<\/i>\n                    : Personalized Object Insertion with Geometric and Style Control"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8902-0013","authenticated-orcid":false,"given":"Yuhong","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0995-0092","authenticated-orcid":false,"given":"Han","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6575-907X","authenticated-orcid":false,"given":"Yiwen","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8261-5337","authenticated-orcid":false,"given":"Rong","family":"Xie","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7124-5182","authenticated-orcid":false,"given":"Li","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"e_1_3_2_1_2_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, Vol. 34 (2021), 8780-8794."},{"key":"e_1_3_2_1_3_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_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_1_5_1","volume-title":"Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626","author":"Hertz Amir","year":"2022","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"e_1_3_2_1_7_1","volume-title":"Lrm: Large reconstruction model for single image to 3d. arXiv preprint arXiv:2311.04400","author":"Hong Yicong","year":"2023","unstructured":"Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, and Hao Tan. 2023. Lrm: Large reconstruction model for single image to 3d. arXiv preprint arXiv:2311.04400 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_2_1_10_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_3_2_1_12_1","volume-title":"Threestudio: A modular framework for diffusion-guided 3d generation.","author":"Liu Ying-Tian","year":"2023","unstructured":"Ying-Tian Liu, Yuan-Chen Guo, Vikram Voleti, Ruizhi Shao, Chia-Hao Chen, Guan Luo, Zixin Zou, Chen Wang, Christian Laforte, Yan-Pei Cao, et al., 2023a. Threestudio: A modular framework for diffusion-guided 3d generation."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"e_1_3_2_1_14_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00603"},{"key":"e_1_3_2_1_16_1","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)."},{"key":"e_1_3_2_1_18_1","unstructured":"Guocheng Qian Jinjie Mai Abdullah Hamdi Jian Ren Aliaksandr Siarohin Bing Li Hsin-Ying Lee Ivan Skorokhodov Peter Wonka Sergey Tulyakov et al. 2023. Magic123: One image to high-quality 3d object generation using both 2d and 3d diffusion priors. arXiv preprint arXiv:2306.17843 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_21_1","volume-title":"Magic Insert: Style-Aware Drag-and-Drop. arXiv preprint arXiv:2407.02489","author":"Ruiz Nataniel","year":"2024","unstructured":"Nataniel Ruiz, Yuanzhen Li, Neal Wadhwa, Yael Pritch, Michael Rubinstein, David E Jacobs, and Shlomi Fruchter. 2024. Magic Insert: Style-Aware Drag-and-Drop. arXiv preprint arXiv:2407.02489 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems, Vol. 35 (2022), 36479-36494."},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Sohn Kihyuk","year":"2024","unstructured":"Kihyuk Sohn, Lu Jiang, Jarred Barber, Kimin Lee, Nataniel Ruiz, Dilip Krishnan, Huiwen Chang, Yuanzhen Li, Irfan Essa, Michael Rubinstein, et al., 2024. Styledrop: Text-to-image synthesis of any style. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_25_1","volume-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation. arXiv preprint arXiv:2309.16653","author":"Tang Jiaxiang","year":"2023","unstructured":"Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, and Gang Zeng. 2023. Dreamgaussian: Generative gaussian splatting for efficient 3d content creation. arXiv preprint arXiv:2309.16653 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Triposr: Fast 3d object reconstruction from a single image. arXiv preprint arXiv:2403.02151","author":"Tochilkin Dmitry","year":"2024","unstructured":"Dmitry Tochilkin, David Pankratz, Zexiang Liu, Zixuan Huang, Adam Letts, Yangguang Li, Ding Liang, Christian Laforte, Varun Jampani, and Yan-Pei Cao. 2024. Triposr: Fast 3d object reconstruction from a single image. arXiv preprint arXiv:2403.02151 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_2_1_28_1","volume-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:2404.02733","author":"Wang Haofan","year":"2024","unstructured":"Haofan Wang, Qixun Wang, Xu Bai, Zekui Qin, and Anthony Chen. 2024a. Instantstyle: Free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:2404.02733 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering. arXiv preprint arXiv:2403.05053","author":"Wang Yibin","year":"2024","unstructured":"Yibin Wang, Weizhong Zhang, Jianwei Zheng, and Cheng Jin. 2024b. PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering. arXiv preprint arXiv:2403.05053 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Styleadapter: A single-pass lora-free model for stylized image generation. arXiv preprint arXiv:2309.01770","author":"Wang Zhouxia","year":"2023","unstructured":"Zhouxia Wang, Xintao Wang, Liangbin Xie, Zhongang Qi, Ying Shan, Wenping Wang, and Ping Luo. 2023. Styleadapter: A single-pass lora-free model for stylized image generation. arXiv preprint arXiv:2309.01770 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion. arXiv preprint arXiv:2403.18818","author":"Winter Daniel","year":"2024","unstructured":"Daniel Winter, Matan Cohen, Shlomi Fruchter, Yael Pritch, Alex Rav-Acha, and Yedid Hoshen. 2024. ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion. arXiv preprint arXiv:2403.18818 (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3067498"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_2_1_34_1","volume-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721","author":"Ye Hu","year":"2023","unstructured":"Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00406"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0136-1"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:01:50Z","timestamp":1765342910000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755603"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":37,"alternative-id":["10.1145\/3746027.3755603","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755603","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}