{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:25:56Z","timestamp":1784643956092,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3680528.3687658","type":"proceedings-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T08:14:37Z","timestamp":1733213677000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["ReVersion: Diffusion-Based Relation Inversion from Images"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8008-5873","authenticated-orcid":false,"given":"Ziqi","family":"Huang","sequence":"first","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7345-0254","authenticated-orcid":false,"given":"Tianxing","family":"Wu","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7653-4015","authenticated-orcid":false,"given":"Yuming","family":"Jiang","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5456-8991","authenticated-orcid":false,"given":"Kelvin C.K.","family":"Chan","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"e_1_3_3_3_2_1","doi-asserted-by":"crossref","unstructured":"Yuval Alaluf Elad Richardson Gal Metzer and Daniel Cohen-Or. 2023. A neural space-time representation for text-to-image personalization. ACM TOG 42 6 (2023) 1\u201310.","DOI":"10.1145\/3618322"},{"key":"e_1_3_3_3_3_1","unstructured":"Tomer Amit Eliya Nachmani Tal Shaharbany and Lior Wolf. 2021. SegDiff: Image Segmentation with Diffusion Probabilistic Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2112.00390 (2021)."},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"crossref","unstructured":"Moab Arar Rinon Gal Yuval Atzmon Gal Chechik Daniel Cohen-Or Ariel Shamir and Amit\u00a0H Bermano. 2023. Domain-agnostic tuning-encoder for fast personalization of text-to-image models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.06925 (2023).","DOI":"10.1145\/3610548.3618173"},{"key":"e_1_3_3_3_5_1","volume-title":"NeurIPS","author":"Austin Jacob","year":"2021","unstructured":"Jacob Austin, Daniel\u00a0D Johnson, Jonathan Ho, Daniel Tarlow, and Rianne van\u00a0den Berg. 2021. Structured denoising diffusion models in discrete state-spaces. In NeurIPS."},{"key":"e_1_3_3_3_6_1","volume-title":"ICLR","author":"Baranchuk Dmitry","year":"2022","unstructured":"Dmitry Baranchuk, Ivan Rubachev, Andrey Voynov, Valentin Khrulkov, and Artem Babenko. 2022. Label-efficient semantic segmentation with diffusion models. In ICLR."},{"key":"e_1_3_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_3_3_8_1","unstructured":"Hong Chen Yipeng Zhang Xin Wang Xuguang Duan Yuwei Zhou and Wenwu Zhu. 2023b. DisenBooth: Disentangled Parameter-Efficient Tuning for Subject-Driven Text-to-Image Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.03374 (2023)."},{"key":"e_1_3_3_3_9_1","unstructured":"Wenhu Chen Hexiang Hu Yandong Li Nataniel Ruiz Xuhui Jia Ming-Wei Chang and William\u00a0W Cohen. 2023a. Subject-driven Text-to-Image Generation via Apprenticeship Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.00186 (2023)."},{"key":"e_1_3_3_3_10_1","unstructured":"Jooyoung Choi Yunjey Choi Yunji Kim Junho Kim and Sungroh Yoon. 2023. Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.15779 (2023)."},{"key":"e_1_3_3_3_11_1","volume-title":"NeurIPS","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion Models Beat GANs on Image Synthesis. In NeurIPS."},{"key":"e_1_3_3_3_12_1","volume-title":"NeurIPS","author":"Esser Patrick","year":"2021","unstructured":"Patrick Esser, Robin Rombach, Andreas Blattmann, and Bjorn Ommer. 2021. ImageBART: Bidirectional context with multinomial diffusion for autoregressive image synthesis. In NeurIPS."},{"key":"e_1_3_3_3_13_1","volume-title":"Diffusers","author":"Face Hugging","unstructured":"Hugging Face. [n. d.]. Diffusers."},{"key":"e_1_3_3_3_14_1","unstructured":"Rinon Gal Yuval Alaluf Yuval Atzmon Or Patashnik Amit\u00a0H. 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:https:\/\/arXiv.org\/abs\/2208.01618 (2022)."},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"crossref","unstructured":"Rinon Gal Moab Arar Yuval Atzmon Amit\u00a0H Bermano Gal Chechik and Daniel Cohen-Or. 2023. Encoder-based domain tuning for fast personalization of text-to-image models. ACM TOG (2023).","DOI":"10.1145\/3592133"},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"crossref","unstructured":"Yuan Gong Youxin Pang Xiaodong Cun Menghan Xia Haoxin Chen Longyue Wang Yong Zhang Xintao Wang Ying Shan and Yujiu Yang. 2023. TaleCrafter: Interactive Story Visualization with Multiple Characters. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.18247 (2023).","DOI":"10.1145\/3610548.3618184"},{"key":"e_1_3_3_3_17_1","volume-title":"NeurIPS","author":"Goodfellow Ian\u00a0J","year":"2014","unstructured":"Ian\u00a0J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron\u00a0C Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In NeurIPS. https:\/\/dl.acm.org\/doi\/10.5555\/2969033.2969125"},{"key":"e_1_3_3_3_18_1","volume-title":"NeurIPS","author":"Graikos Alexandros","year":"2022","unstructured":"Alexandros Graikos, Nikolay Malkin, Nebojsa Jojic, and Dimitris Samaras. 2022. Diffusion Models as Plug-and-Play Priors. In NeurIPS."},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"e_1_3_3_3_20_1","unstructured":"Ligong Han Yinxiao Li Han Zhang Peyman Milanfar Dimitris Metaxas and Feng Yang. 2023. SVDiff: Compact Parameter Space for Diffusion Fine-Tuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.11305 (2023)."},{"key":"e_1_3_3_3_21_1","unstructured":"William Harvey Saeid Naderiparizi Vaden Masrani Christian Weilbach and Frank Wood. 2022. Flexible Diffusion Modeling of Long Videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.11495 (2022)."},{"key":"e_1_3_3_3_22_1","unstructured":"Yingqing He Tianyu Yang Yong Zhang Ying Shan and Qifeng Chen. 2022. Latent video diffusion models for high-fidelity video generation with arbitrary lengths. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.13221 (2022)."},{"key":"e_1_3_3_3_23_1","volume-title":"NeurIPS","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In NeurIPS."},{"key":"e_1_3_3_3_24_1","unstructured":"Jonathan Ho Chitwan Saharia William Chan David\u00a0J Fleet Mohammad Norouzi and Tim Salimans. 2022a. Cascaded Diffusion Models for High Fidelity Image Generation. JMLR (2022)."},{"key":"e_1_3_3_3_25_1","unstructured":"Jonathan Ho Tim Salimans Alexey Gritsenko William Chan Mohammad Norouzi and David\u00a0J Fleet. 2022b. Video diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.03458 (2022)."},{"key":"e_1_3_3_3_26_1","volume-title":"ICLR","author":"Hu Edward\u00a0J","year":"2022","unstructured":"Edward\u00a0J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In ICLR."},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00589"},{"key":"e_1_3_3_3_28_1","unstructured":"Aapo Hyv\u00e4rinen and Peter Dayan. 2005. Estimation of non-normalized statistical models by score matching. JMLR (2005)."},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"e_1_3_3_3_30_1","unstructured":"Xuhui Jia Yang Zhao Kelvin\u00a0C.K. Chan Yandong Li Han Zhang Boqing Gong Tingbo Hou Huisheng Wang and Yu-Chuan Su. 2023. Taming Encoder for Zero Fine-tuning Image Customization with Text-to-Image Diffusion. (2023)."},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"crossref","unstructured":"Yuming Jiang Shuai Yang Haonan Qju Wayne Wu Chen\u00a0Change Loy and Ziwei Liu. 2022. Text2human: Text-driven controllable human image generation. ACM TOG (2022).","DOI":"10.1145\/3528223.3530104"},{"key":"e_1_3_3_3_32_1","unstructured":"Bahjat Kawar Shiran Zada Oran Lang Omer Tov Huiwen Chang Tali Dekel Inbar Mosseri and Michal Irani. 2022. Imagic: Text-based real image editing with diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.09276 (2022)."},{"key":"e_1_3_3_3_33_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David\u00a0A Shamma Michael Bernstein and Fei-Fei Li. 2017. Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations. IJCV (2017).","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_3_3_34_1","unstructured":"Nupur Kumari Bingliang Zhang Richard Zhang Eli Shechtman and Jun-Yan Zhu. 2022. Multi-Concept Customization of Text-to-Image Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.04488 (2022)."},{"key":"e_1_3_3_3_35_1","unstructured":"Dongxu Li Junnan Li and Steven\u00a0CH Hoi. 2023a. BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.14720 (2023)."},{"key":"e_1_3_3_3_36_1","unstructured":"Yuheng Li Haotian Liu Yangming Wen and Yong\u00a0Jae Lee. 2023b. Generate Anything Anywhere in Any Scene. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.17154 (2023)."},{"key":"e_1_3_3_3_37_1","unstructured":"Jun\u00a0Hao Liew Hanshu Yan Daquan Zhou and Jiashi Feng. 2022. MagicMix: Semantic Mixing with Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.16056 (2022)."},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"e_1_3_3_3_39_1","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:https:\/\/arXiv.org\/abs\/2307.11410 (2023)."},{"key":"e_1_3_3_3_40_1","volume-title":"ICLR","author":"Meng Chenlin","year":"2022","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_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"e_1_3_3_3_42_1","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 preprint arXiv:https:\/\/arXiv.org\/abs\/2112.10741 (2021)."},{"key":"e_1_3_3_3_43_1","unstructured":"Aaron van\u00a0den Oord Yazhe Li and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1807.03748 (2018)."},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"e_1_3_3_3_45_1","volume-title":"ICML","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In ICML."},{"key":"e_1_3_3_3_46_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.06125 (2022)."},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_3_49_1","unstructured":"Nataniel Ruiz Yuanzhen Li Varun Jampani Yael Pritch Michael Rubinstein and Kfir Aberman. 2022. DreamBooth: Fine Tuning Text-to-image Diffusion Models for Subject-Driven Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.12242 (2022)."},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"e_1_3_3_3_51_1","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily Denton Seyed Kamyar\u00a0Seyed Ghasemipour Burcu\u00a0Karagol Ayan S\u00a0Sara Mahdavi Rapha\u00a0Gontijo Lopes et\u00a0al. 2022a. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.11487 (2022)."},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"crossref","unstructured":"Chitwan Saharia Jonathan Ho William Chan Tim Salimans David\u00a0J Fleet and Mohammad Norouzi. 2022b. Image super-resolution via iterative refinement. IEEE TPAMI (2022).","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"e_1_3_3_3_53_1","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman et\u00a0al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.08402 (2022)."},{"key":"e_1_3_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123380"},{"key":"e_1_3_3_3_55_1","unstructured":"Uriel Singer Adam Polyak Thomas Hayes Xi Yin Jie An Songyang Zhang Qiyuan Hu Harry Yang Oron Ashual Oran Gafni et\u00a0al. 2022. Make-a-video: Text-to-video generation without text-video data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.14792 (2022)."},{"key":"e_1_3_3_3_56_1","volume-title":"ICML","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 ICML. https:\/\/dl.acm.org\/doi\/10.5555\/3045118.3045358"},{"key":"e_1_3_3_3_57_1","volume-title":"ICLR","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021a. Denoising diffusion implicit models. In ICLR."},{"key":"e_1_3_3_3_58_1","volume-title":"ICLR","author":"Song Yang","year":"2021","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik\u00a0P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2021b. Score-based generative modeling through stochastic differential equations. In ICLR."},{"key":"e_1_3_3_3_59_1","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. JMLR 9 11 (2008)."},{"key":"e_1_3_3_3_60_1","unstructured":"Ruben Villegas Mohammad Babaeizadeh Pieter-Jan Kindermans Hernan Moraldo Han Zhang Mohammad\u00a0Taghi Saffar Santiago Castro Julius Kunze and Dumitru Erhan. 2022. Phenaki: Variable length video generation from open domain textual description. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.02399 (2022)."},{"key":"e_1_3_3_3_61_1","doi-asserted-by":"crossref","unstructured":"Pascal Vincent. 2011. A connection between score matching and denoising autoencoders. Neural Computation (2011).","DOI":"10.1162\/NECO_a_00142"},{"key":"e_1_3_3_3_62_1","unstructured":"Andrey Voynov Qinghao Chu Daniel Cohen-Or and Kfir Aberman. 2023. p+: Extended textual conditioning in text-to-image generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.09522 (2023)."},{"key":"e_1_3_3_3_63_1","unstructured":"Binxu Wang and John\u00a0J. Vastola. 2023. Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First Details Later. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.02490 (2023)."},{"key":"e_1_3_3_3_64_1","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:https:\/\/arXiv.org\/abs\/2302.13848 (2023)."},{"key":"e_1_3_3_3_65_1","unstructured":"Jay\u00a0Zhangjie Wu Yixiao Ge Xintao Wang Stan\u00a0Weixian Lei Yuchao Gu Wynne Hsu Ying Shan Xiaohu Qie and Mike\u00a0Zheng Shou. 2022. Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.11565 (2022)."},{"key":"e_1_3_3_3_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"e_1_3_3_3_67_1","unstructured":"Xingqian Xu Jiayi Guo Zhangyang Wang Gao Huang Irfan Essa and Humphrey Shi. 2023. Prompt-Free Diffusion: Taking \"Text\" out of Text-to-Image Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.16223 (2023)."},{"key":"e_1_3_3_3_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_11"},{"key":"e_1_3_3_3_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01791"},{"key":"e_1_3_3_3_70_1","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:https:\/\/arXiv.org\/abs\/2308.06721 (2023)."},{"key":"e_1_3_3_3_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.121"},{"key":"e_1_3_3_3_72_1","unstructured":"Yufan Zhou Ruiyi Zhang Tong Sun and Jinhui Xu. 2023. Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.13579 (2023)."},{"key":"e_1_3_3_3_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.71"}],"event":{"name":"SA '24: SIGGRAPH Asia 2024 Conference Papers","location":"Tokyo Japan","acronym":"SA '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2024 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687658","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3680528.3687658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:20Z","timestamp":1750295900000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687658"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":72,"alternative-id":["10.1145\/3680528.3687658","10.1145\/3680528"],"URL":"https:\/\/doi.org\/10.1145\/3680528.3687658","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}