{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:47:32Z","timestamp":1774021652696,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730702","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:40:47Z","timestamp":1753260047000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["StableMakeup: When Real-World Makeup Transfer Meets Diffusion Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3255-0901","authenticated-orcid":false,"given":"Yuxuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5269-575X","authenticated-orcid":false,"given":"Yirui","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shanghai Tech University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7028-3347","authenticated-orcid":false,"given":"Yiren","family":"Song","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4584-9388","authenticated-orcid":false,"given":"Jiaming","family":"Liu","sequence":"additional","affiliation":[{"name":"Tiamat AI, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_2_2_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_2_3_1","unstructured":"Rumeysa Bodur Erhan Gundogdu Binod Bhattarai Tae-Kyun Kim Michael Donoser and Loris Bazzani. 2023. iEdit: Localised Text-guided Image Editing with Weak Supervision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.05947 (2023)."},{"key":"e_1_3_3_2_4_1","unstructured":"Mingdeng Cao Xintao Wang Zhongang Qi Ying Shan Xiaohu Qie and Yinqiang Zheng. 2023. MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.08465 (2023)."},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00012"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"crossref","unstructured":"Hila Chefer Yuval Alaluf Yael Vinker Lior Wolf and Daniel Cohen-Or. 2023. Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2301.13826\u00a0[cs.CV]","DOI":"10.1145\/3592116"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00648"},{"key":"e_1_3_3_2_9_1","unstructured":"Dave Epstein Allan Jabri Ben Poole Alexei\u00a0A Efros and Aleksander Holynski. 2023. Diffusion self-guidance for controllable image generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.00986 (2023)."},{"key":"e_1_3_3_2_10_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. https:\/\/doi.org\/10.48550\/ARXIV.2208.01618"},{"key":"e_1_3_3_2_11_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. https:\/\/arxiv.org\/abs\/2302.12228","DOI":"10.1145\/3592133"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01058"},{"key":"e_1_3_3_2_13_1","volume-title":"International Conference on Learning Representations","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. 2022b. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01459"},{"key":"e_1_3_3_2_15_1","unstructured":"Xuhui Jia Yang Zhao Kelvin\u00a0CK 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 models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.02642 (2023)."},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00524"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67070-2_17"},{"key":"e_1_3_3_2_19_1","unstructured":"Pengzhi Li QInxuan Huang Yikang Ding and Zhiheng Li. 2023. LayerDiffusion: Layered Controlled Image Editing with Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.18676 (2023)."},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240618"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"crossref","unstructured":"Si Liu Wentao Jiang Chen Gao Ran He Jiashi Feng Bo Li and Shuicheng Yan. 2021. PSGAN++: robust detail-preserving makeup transfer and removal. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 11 (2021) 8538\u20138551.","DOI":"10.1109\/TPAMI.2021.3083484"},{"key":"e_1_3_3_2_22_1","unstructured":"Wan-Duo\u00a0Kurt Ma JP Lewis W\u00a0Bastiaan Kleijn and Thomas Leung. 2023. Directed diffusion: Direct control of object placement through attention guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.13153 (2023)."},{"key":"e_1_3_3_2_23_1","unstructured":"Chong Mou Xintao Wang Jiechong Song Ying Shan and Jian Zhang. 2023a. DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.02421 (2023)."},{"key":"e_1_3_3_2_24_1","unstructured":"Chong Mou Xintao Wang Liangbin Xie Jian Zhang Zhongang Qi Ying Shan and Xiaohu Qie. 2023b. T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.08453 (2023)."},{"key":"e_1_3_3_2_25_1","first-page":"13305","volume-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","author":"Nguyen Thao","year":"2021","unstructured":"Thao Nguyen, Anh\u00a0Tuan Tran, and Minh Hoai. 2021. Lipstick ain\u2019t enough: beyond color matching for in-the-wild makeup transfer. In Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition. 13305\u201313314."},{"key":"e_1_3_3_2_26_1","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:https:\/\/arXiv.org\/abs\/2307.01952 (2023)."},{"key":"e_1_3_3_2_27_1","volume-title":"33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022","author":"Prados-Torreblanca Andr\u00e9s","year":"2022","unstructured":"Andr\u00e9s Prados-Torreblanca, Jos\u00e9\u00a0M Buenaposada, and Luis Baumela. 2022. Shape Preserving Facial Landmarks with Graph Attention Networks. In 33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022. BMVA Press. https:\/\/bmvc2022.mpi-inf.mpg.de\/0155.pdf"},{"key":"e_1_3_3_2_28_1","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. arxiv:https:\/\/arXiv.org\/abs\/2103.00020\u00a0[cs.CV]"},{"key":"e_1_3_3_2_29_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. arxiv:https:\/\/arXiv.org\/abs\/2204.06125\u00a0[cs.CV]"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"crossref","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. (2022).","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_3_2_32_1","unstructured":"Nataniel Ruiz Yuanzhen Li Varun Jampani Wei Wei Tingbo Hou Yael Pritch Neal Wadhwa Michael Rubinstein and Kfir Aberman. 2023. HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.06949 (2023)."},{"key":"e_1_3_3_2_33_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 Tim Salimans Jonathan Ho David\u00a0J Fleet and Mohammad Norouzi. 2022a. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. arxiv:https:\/\/arXiv.org\/abs\/2205.11487\u00a0[cs.CV]"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"crossref","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily\u00a0L Denton Kamyar Ghasemipour Raphael Gontijo\u00a0Lopes Burcu Karagol\u00a0Ayan Tim Salimans et\u00a0al. 2022b. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems 35 (2022) 36479\u201336494.","DOI":"10.52202\/068431-2643"},{"key":"e_1_3_3_2_35_1","unstructured":"Zhaoyang Sun Yaxiong Chen and Shengwu Xiong. 2023. SSAT + + : A Semantic-Aware and Versatile Makeup Transfer Network With Local Color Consistency Constraint. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/PG.2007.21"},{"key":"e_1_3_3_2_37_1","unstructured":"Linoy Tsaban and Apolin\u00e1rio Passos. 2023. Ledits: Real image editing with ddpm inversion and semantic guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.00522 (2023)."},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00317"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"crossref","unstructured":"Zhou Wang Alan\u00a0C Bovik Hamid\u00a0R Sheikh and Eero\u00a0P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13 4 (2004) 600\u2013612.","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_3_2_40_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_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_41"},{"key":"e_1_3_3_2_42_1","unstructured":"Defeng Xie Ruichen Wang Jian Ma Chen Chen Haonan Lu Dong Yang Fobo Shi and Xiaodong Lin. 2023. Edit everything: A text-guided generative system for images editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.14006 (2023)."},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738660"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00117"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_42"},{"key":"e_1_3_3_2_46_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_2_47_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.05543 (2023).","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"e_1_3_3_2_51_1","unstructured":"Shihao Zhao Dongdong Chen Yen-Chun Chen Jianmin Bao Shaozhe Hao Lu Yuan and Kwan-Yee\u00a0K Wong. 2023. Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.16322 (2023)."},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_3_3_2_53_1","unstructured":"Mingrui Zhu Yun Yi N. Wang Xiaoyu Wang and Xinbo Gao. 2022. Semi-parametric Makeup Transfer via Semantic-aware Correspondence. ArXiv abs\/2203.02286 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247244926"}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730702","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:52:57Z","timestamp":1774018377000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730702"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":52,"alternative-id":["10.1145\/3721238.3730702","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730702","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}