{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:44:29Z","timestamp":1778082269139,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":46,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"SSTIC Grant","award":["KJZD20230923115106012, KJZD20230923114916032"],"award-info":[{"award-number":["KJZD20230923115106012, KJZD20230923114916032"]}]},{"name":"National Key R&D Program of China","award":["2022YFB4701400\/4701402"],"award-info":[{"award-number":["2022YFB4701400\/4701402"]}]},{"name":"Beijing Key Lab of Networked Multimedia."}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681396","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"10976-10984","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["CustomNet: Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1302-2352","authenticated-orcid":false,"given":"Ziyang","family":"Yuan","sequence":"first","affiliation":[{"name":"SIGS, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6577-4715","authenticated-orcid":false,"given":"Mingdeng","family":"Cao","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6585-8604","authenticated-orcid":false,"given":"Xintao","family":"Wang","sequence":"additional","affiliation":[{"name":"ARC Lab, Tencent PCG, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8298-4063","authenticated-orcid":false,"given":"Zhongang","family":"Qi","sequence":"additional","affiliation":[{"name":"ARC Lab, Tencent PCG, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3590-6676","authenticated-orcid":false,"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[{"name":"SIGS, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7673-8325","authenticated-orcid":false,"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"ARC Lab, Tencent PCG, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00861"},{"key":"e_1_3_2_1_4_1","volume-title":"Hierarchical Dynamic Image Harmonization. arXiv:2211.08639","author":"Chen Haoxing","year":"2022","unstructured":"Haoxing Chen, Zhangxuan Gu, Yaohui Li, Jun Lan, Changhua Meng, Weiqiang Wang, and Huaxiong Li. 2022. Hierarchical Dynamic Image Harmonization. arXiv:2211.08639 (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"DisenBooth: Disentangled Parameter-Efficient Tuning for Subject-Driven Text-to-Image Generation. arXiv preprint arXiv:2305.03374","author":"Chen Hong","year":"2023","unstructured":"Hong Chen, Yipeng Zhang, Xin Wang, Xuguang Duan, Yuwei Zhou, and Wenwu Zhu. 2023. DisenBooth: Disentangled Parameter-Efficient Tuning for Subject-Driven Text-to-Image Generation. arXiv preprint arXiv:2305.03374 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01792"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_2_1_9_1","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion. 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:2208.01618 (2022)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01610"},{"key":"e_1_3_2_1_11_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_12_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_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01271"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander C Berg Wan-Yen Lo et al. 2023. Segment anything. arXiv:2304.02643 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_2_1_16_1","volume-title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing. arXiv:2305.14720","author":"Li Dongxu","year":"2023","unstructured":"Dongxu Li, Junnan Li, and Steven CH Hoi. 2023. BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing. arXiv:2305.14720 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_2_1_19_1","volume-title":"Pavel Tokmakov, Sergey Zakharov, and Carl Vondrick.","author":"Liu Ruoshi","year":"2023","unstructured":"Ruoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov, Sergey Zakharov, and Carl Vondrick. 2023. Zero-1-to-3: Zero-shot one image to 3d object. arXiv preprint arXiv:2303.11328 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Cones: Concept neurons in diffusion models for customized generation. arXiv:2303.05125","author":"Liu Zhiheng","year":"2023","unstructured":"Zhiheng Liu, Ruili Feng, Kai Zhu, Yifei Zhang, Kecheng Zheng, Yu Liu, Deli Zhao, Jingren Zhou, and Yang Cao. 2023. Cones: Concept neurons in diffusion models for customized generation. arXiv:2303.05125 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_22_1","volume-title":"Subject-Diffusion: Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning. arXiv preprint arXiv:2307.11410","author":"Ma Jian","year":"2023","unstructured":"Jian Ma, Junhao Liang, Chen Chen, and Haonan Lu. 2023. Subject-Diffusion: Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning. arXiv preprint arXiv:2307.11410 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_2_1_24_1","volume-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453","author":"Mou Chong","year":"2023","unstructured":"Chong Mou, Xintao Wang, Liangbin Xie, Jian Zhang, Zhongang Qi, Ying Shan, and Xiaohu Qie. 2023. T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.82"},{"key":"e_1_3_2_1_27_1","volume-title":"Int. Conf. Mach. Learn.","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 Int. Conf. Mach. Learn."},{"key":"e_1_3_2_1_28_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv:2204.06125 (2022)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_31_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. Adv. Neural Inform. Process. Syst. (2022)."},{"key":"e_1_3_2_1_32_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Sitzmann Vincent","year":"2019","unstructured":"Vincent Sitzmann, Michael Zollh\u00f6fer, and Gordon Wetzstein. 2019. Scene representation networks: Continuous 3d-structure-aware neural scene representations. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PMLR, 2256--2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. PMLR, 2256--2265."},{"key":"e_1_3_2_1_34_1","volume-title":"Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems","author":"Song Yang","year":"2019","unstructured":"Yang Song and Stefano Ermon. 2019. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_35_1","volume-title":"ObjectStitch: Object Compositing With Diffusion Model. In IEEE Conf. Comput. Vis. Pattern Recog.","author":"Song Yizhi","year":"2023","unstructured":"Yizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen, Brian Price, Jianming Zhang, Soo Ye Kim, and Daniel Aliaga. 2023. ObjectStitch: Object Compositing With Diffusion Model. In IEEE Conf. Comput. Vis. Pattern Recog."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_10"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Kalyan Sunkavalli Micah K Johnson Wojciech Matusik and Hanspeter Pfister. 2010. Multi-scale image harmonization. ACM Trans. Graph. (2010).","DOI":"10.1145\/1833349.1778862"},{"key":"e_1_3_2_1_38_1","volume-title":"Diffusers: State-of-the-art diffusion models. https:\/\/github.com\/huggingface\/diffusers.","author":"von Platen Patrick","year":"2022","unstructured":"Patrick von Platen, Suraj Patil, Anton Lozhkov, Pedro Cuenca, Nathan Lambert, Kashif Rasul, Mishig Davaadorj, and Thomas Wolf. 2022. Diffusers: State-of-the-art diffusion models. https:\/\/github.com\/huggingface\/diffusers."},{"key":"e_1_3_2_1_39_1","volume-title":"Novel view synthesis with diffusion models. arXiv preprint arXiv:2210.04628","author":"Watson Daniel","year":"2022","unstructured":"Daniel Watson, William Chan, Ricardo Martin-Brualla, Jonathan Ho, Andrea Tagliasacchi, and Mohammad Norouzi. 2022. Novel view synthesis with diffusion models. arXiv preprint arXiv:2210.04628 (2022)."},{"key":"e_1_3_2_1_40_1","volume-title":"Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848","author":"Wei Yuxiang","year":"2023","unstructured":"Yuxiang Wei, Yabo Zhang, Zhilong Ji, Jinfeng Bai, Lei Zhang, and Wangmeng Zuo. 2023. Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_18"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_2_1_43_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_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_3_2_1_45_1","volume-title":"Adding conditional control to text-to-image diffusion models. arXiv:2302.05543","author":"Zhang Lvmin","year":"2023","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding conditional control to text-to-image diffusion models. arXiv:2302.05543 (2023)."},{"key":"e_1_3_2_1_46_1","volume-title":"Stereo magnification: Learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817","author":"Zhou Tinghui","year":"2018","unstructured":"Tinghui Zhou, Richard Tucker, John Flynn, Graham Fyffe, and Noah Snavely. 2018. Stereo magnification: Learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817 (2018)."}],"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\/3664647.3681396","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:44Z","timestamp":1750295864000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":46,"alternative-id":["10.1145\/3664647.3681396","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681396","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"}}]}}