{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:19:22Z","timestamp":1782317962907,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":60,"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-nc\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680861","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"10725-10734","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["UVMap-ID: A Controllable and Personalized UV Map Generative Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1168-3527","authenticated-orcid":false,"given":"Weijie","family":"Wang","sequence":"first","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6189-9521","authenticated-orcid":false,"given":"Jichao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4703-2271","authenticated-orcid":false,"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2284-1700","authenticated-orcid":false,"given":"Xia","family":"Li","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7276-5566","authenticated-orcid":false,"given":"Xingqian","family":"Xu","sequence":"additional","affiliation":[{"name":"PicsArt AI Research, Atlanta, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2922-5663","authenticated-orcid":false,"given":"Humphrey","family":"Shi","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6597-7248","authenticated-orcid":false,"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1275-2333","authenticated-orcid":false,"given":"Bruno","family":"Lepri","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00043"},{"key":"e_1_3_2_2_2_1","volume-title":"International Conference on Machine Learning. PMLR, 1692--1717","author":"Bao Fan","year":"2023","unstructured":"Fan Bao, Shen Nie, Kaiwen Xue, Chongxuan Li, Shi Pu, Yaole Wang, Gang Yue, Yue Cao, Hang Su, and Jun Zhu. 2023. One transformer fits all distributions in multi-modal diffusion at scale. In International Conference on Machine Learning. PMLR, 1692--1717."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_3_2_2_4_1","volume-title":"Dreamavatar: Text-and-shape guided 3d human avatar generation via diffusion models. arXiv preprint arXiv:2304.00916","author":"Cao Yukang","year":"2023","unstructured":"Yukang Cao, Yan-Pei Cao, Kai Han, Ying Shan, and Kwan-Yee K Wong. 2023. Dreamavatar: Text-and-shape guided 3d human avatar generation via diffusion models. arXiv preprint arXiv:2304.00916 (2023)."},{"key":"e_1_3_2_2_5_1","volume-title":"Smplitex: A generative model and dataset for 3d human texture estimation from single image. BMVC","author":"Casas Dan","year":"2023","unstructured":"Dan Casas and Marc Comino Trinidad. 2023. Smplitex: A generative model and dataset for 3d human texture estimation from single image. BMVC (2023)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_2_2_7_1","unstructured":"Siying Cui Jiankang Deng Jia Guo Xiang An Yongle Zhao Xinyu Wei and Ziyong Feng. 2024. IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models. https:\/\/api.semanticscholar.org\/CorpusID:268537084"},{"key":"e_1_3_2_2_8_1","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion. ICLR","author":"Gal Rinon","year":"2023","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2023. An image is worth one word: Personalizing text-to-image generation using textual inversion. ICLR (2023)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00125"},{"key":"e_1_3_2_2_10_1","volume-title":"Generative adversarial nets. NeurIPS","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. NeurIPS (2014)."},{"key":"e_1_3_2_2_11_1","unstructured":"Jia Guo Jiankang Deng Alexandros Lattas and Stefanos Zafeiriou. 2021. Sample and Computation Redistribution for Efficient Face Detection. arxiv: 2105.04714 [cs.CV]"},{"key":"e_1_3_2_2_12_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_13_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_2_14_1","volume-title":"Avatarclip: Zero-shot text-driven generation and animation of 3d avatars. arXiv preprint arXiv:2205.08535","author":"Hong Fangzhou","year":"2022","unstructured":"Fangzhou Hong, Mingyuan Zhang, Liang Pan, Zhongang Cai, Lei Yang, and Ziwei Liu. 2022. Avatarclip: Zero-shot text-driven generation and animation of 3d avatars. arXiv preprint arXiv:2205.08535 (2022)."},{"key":"e_1_3_2_2_15_1","volume-title":"ICLR 2022","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. ICLR 2022 (2021)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612022"},{"key":"e_1_3_2_2_17_1","volume-title":"HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation. CVPR","author":"Huang Xin","year":"2024","unstructured":"Xin Huang, Ruizhi Shao, Qi Zhang, Hongwen Zhang, Ying Feng, Yebin Liu, and Qing Wang. 2024. HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation. CVPR (2024)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"e_1_3_2_2_19_1","volume-title":"AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control. ICCV","author":"Jiang Ruixiang","year":"2023","unstructured":"Ruixiang Jiang, Can Wang, Jingbo Zhang, Menglei Chai, Mingming He, Dongdong Chen, and Jing Liao. 2023. AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control. ICCV (2023)."},{"key":"e_1_3_2_2_20_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Jiang Yuming","year":"2024","unstructured":"Yuming Jiang, Tianxing Wu, Shuai Yang, Chenyang Si, Dahua Lin, Yu Qiao, Chen Change Loy, and Ziwei Liu. 2024. VideoBooth: Diffusion-based Video Generation with Image Prompts. CVPR (2024)."},{"key":"e_1_3_2_2_21_1","volume-title":"Progressive growing of gans for improved quality, stability, and variation. ICLR","author":"Karras Tero","year":"2018","unstructured":"Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2018. Progressive growing of gans for improved quality, stability, and variation. ICLR (2018)."},{"key":"e_1_3_2_2_22_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_23_1","volume-title":"Mihai Fieraru, and Cristian Sminchisescu.","author":"Kolotouros Nikos","year":"2023","unstructured":"Nikos Kolotouros, Thiemo Alldieck, Andrei Zanfir, Eduard Gabriel Bazavan, Mihai Fieraru, and Cristian Sminchisescu. 2023. DreamHuman: Animatable 3D Avatars from Text. NeuIPS (2023)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00076"},{"key":"e_1_3_2_2_25_1","volume-title":"Styleuv: Diverse and high-fidelity uv map generative model. arXiv preprint arXiv:2011.12893","author":"Lee Myunggi","year":"2020","unstructured":"Myunggi Lee, Wonwoong Cho, Moonheum Kim, David Inouye, and Nojun Kwak. 2020. Styleuv: Diverse and high-fidelity uv map generative model. arXiv preprint arXiv:2011.12893 (2020)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3048039"},{"key":"e_1_3_2_2_27_1","volume-title":"SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D. ICLR","author":"Li Weiyu","year":"2024","unstructured":"Weiyu Li, Rui Chen, Xuelin Chen, and Ping Tan. 2024. SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D. ICLR (2024)."},{"key":"e_1_3_2_2_28_1","volume-title":"Humangaussian: Text-driven 3d human generation with gaussian splatting. CVPR","author":"Liu Xian","year":"2024","unstructured":"Xian Liu, Xiaohang Zhan, Jiaxiang Tang, Ying Shan, Gang Zeng, Dahua Lin, Xihui Liu, and Ziwei Liu. 2024. Humangaussian: Text-driven 3d human generation with gaussian splatting. CVPR (2024)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul P. Srinivasan Matthew Tancik Jonathan T. Barron Ravi Ramamoorthi and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555392"},{"key":"e_1_3_2_2_32_1","volume-title":"ICLR 2023","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T. Barron, and Ben Mildenhall. 2022. DreamFusion: Text-to-3D using 2D Diffusion. ICLR 2023 (2022)."},{"key":"e_1_3_2_2_33_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","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 International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_34_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint 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 preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.3.010344"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_2_38_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","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.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_39_1","volume-title":"Improved techniques for training gans. Advances in neural information processing systems","author":"Salimans Tim","year":"2016","unstructured":"Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved techniques for training gans. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASYU50717.2020.9259802"},{"key":"e_1_3_2_2_42_1","volume-title":"Mvdream: Multi-view diffusion for 3d generation. arXiv preprint arXiv:2308.16512","author":"Shi Yichun","year":"2023","unstructured":"Yichun Shi, Peng Wang, Jianglong Ye, Mai Long, Kejie Li, and Xiao Yang. 2023. Mvdream: Multi-view diffusion for 3d generation. arXiv preprint arXiv:2308.16512 (2023)."},{"key":"e_1_3_2_2_43_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_2_44_1","volume-title":"Diffusers: State-of-the-art diffusion models.","author":"Platen Patrick Von","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."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01212"},{"key":"e_1_3_2_2_46_1","unstructured":"Qixun Wang Xu Bai Haofan Wang Zekui Qin and Anthony Chen. 2024. InstantID: Zero-shot Identity-Preserving Generation in Seconds. arXiv preprint arXiv:2401.07519 (2024)."},{"key":"e_1_3_2_2_47_1","volume-title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. NeurIPS","author":"Wang Zhengyi","year":"2023","unstructured":"Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. 2023. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. NeurIPS (2023)."},{"key":"e_1_3_2_2_48_1","volume-title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation. ICCV","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. ICCV (2023)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Yi Wu Ziqiang Li Heliang Zheng Chaoyue Wang and Bin Li. 2024. Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm. https:\/\/api.semanticscholar.org\/CorpusID:268531420","DOI":"10.1007\/978-3-031-73242-3_16"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"e_1_3_2_2_51_1","volume-title":"Prompt-Free Diffusion: Taking\" Text\" out of Text-to-Image Diffusion Models. arXiv preprint arXiv:2305.16223","author":"Xu Xingqian","year":"2023","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:2305.16223 (2023)."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01359"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612363"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00068"},{"key":"e_1_3_2_2_56_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. (2023)."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"crossref","unstructured":"Yuxuan Zhang Yiren Song Jiaming Liu Rui Wang Jinpeng Yu Hao Tang Huaxia Li Xu Tang Yao Hu Han Pan and Zhongliang Jing. 2024. SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation.","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"e_1_3_2_2_59_1","first-page":"14326","article-title":"Human parsing based texture transfer from single image to 3D human via cross-view consistency","volume":"33","author":"Zhao Fang","year":"2020","unstructured":"Fang Zhao, Shengcai Liao, Kaihao Zhang, and Ling Shao. 2020. Human parsing based texture transfer from single image to 3D human via cross-view consistency. Advances in Neural Information Processing Systems, Vol. 33 (2020), 14326--14337.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"}],"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\/3664647.3680861","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680861","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\/3664647.3680861"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":60,"alternative-id":["10.1145\/3664647.3680861","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680861","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"}}]}}