{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T07:22:11Z","timestamp":1783063331888,"version":"3.54.6"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation","award":["No.RS-2024-00439499"],"award-info":[{"award-number":["No.RS-2024-00439499"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2026,7,3]]},"abstract":"<jats:p>Creative face stylization aims to render portraits in diverse visual idioms such as cartoons, sketches, and paintings while retaining recognizable identity. However, current identity encoders, which are typically trained and calibrated on natural photographs, exhibit severe brittleness under stylization. They often mistake changes in texture or color palette for identity drift or fail to detect geometric exaggerations. This reveals the lack of a style-agnostic framework to evaluate and supervise identity consistency across varying styles and strengths. To address this gap, we introduce StyleID, a human perception-aware dataset and evaluation framework for facial identity under stylization. StyleID comprises two datasets: (i) StyleBench-H, a benchmark that captures human same-different verification judgments across diffusion- and flow-matching-based stylization at multiple style strengths, and (ii) StyleBench-S, a supervision set derived from psychometric recognition-strength curves obtained through controlled two-alternative forced-choice (2AFC) experiments. Leveraging StyleBench-S, we fine-tune existing semantic encoders to align their similarity orderings with human perception across styles and strengths. Experiments demonstrate that our calibrated models yield significantly higher correlation with human judgments and enhanced robustness for out-of-domain, artist drawn portraits. All of our datasets, code, and pretrained models will be publicly available.<\/jats:p>","DOI":"10.1145\/3811360","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T07:05:51Z","timestamp":1783062351000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition"],"prefix":"10.1145","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0205-5203","authenticated-orcid":false,"given":"Kwan","family":"Yun","sequence":"first","affiliation":[{"name":"Visual Media Lab, KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6605-262X","authenticated-orcid":false,"given":"Changmin","family":"Lee","sequence":"additional","affiliation":[{"name":"Visual Media Lab, KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9258-1323","authenticated-orcid":false,"given":"AYeong","family":"Jeong","sequence":"additional","affiliation":[{"name":"Visual Media Lab, KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9019-2135","authenticated-orcid":false,"given":"Youngseo","family":"Kim","sequence":"additional","affiliation":[{"name":"Visual Media Lab, KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4897-6271","authenticated-orcid":false,"given":"Seungmi","family":"Lee","sequence":"additional","affiliation":[{"name":"Visual Media Lab, KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1925-3326","authenticated-orcid":false,"given":"Junyong","family":"Noh","sequence":"additional","affiliation":[{"name":"Visual Media Lab, KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,3]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00166"},{"key":"e_1_2_1_2_1","volume-title":"Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space. arXiv e-prints","author":"Batifol Stephen","year":"2025","unstructured":"Stephen Batifol, Andreas Blattmann, Frederic Boesel, Saksham Consul, Cyril Diagne, Tim Dockhorn, Jack English, Zion English, Patrick Esser, Sumith Kulal, et al. 2025. FLUX. 1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space. arXiv e-prints (2025), arXiv-2506."},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 1578\u20131587","author":"Boutros Fadi","year":"2022","unstructured":"Fadi Boutros, Naser Damer, Florian Kirchbuchner, and Arjan Kuijper. 2022. Elastic-face: Elastic margin loss for deep face recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 1578\u20131587."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_8"},{"key":"e_1_2_1_7_1","volume-title":"Arcface: Additive angular margin loss for deep face recognition. In CVPR.","author":"Deng Jiankang","year":"2019","unstructured":"Jiankang Deng, Jia Guo, Niannan Xue, and Stefanos Zafeiriou. 2019. Arcface: Additive angular margin loss for deep face recognition. In CVPR."},{"key":"e_1_2_1_8_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412193"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_2_1_12_1","unstructured":"Google. 2025. Gemini. https:\/\/gemini.google.com\/."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"e_1_2_1_14_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_2_1_15_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. Lora: Low-rank adaptation of large language models. ICLR 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_2_1_16_1","volume-title":"Workshop on faces in'Real-Life'Images: detection, alignment, and recognition.","author":"Huang Gary B","year":"2008","unstructured":"Gary B Huang, Marwan Mattar, Tamara Berg, and Eric Learned-Miller. 2008. Labeled faces in the wild: A database forstudying face recognition in unconstrained environments. In Workshop on faces in'Real-Life'Images: detection, alignment, and recognition."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_2_1_18_1","volume-title":"Efros","author":"Isola Phillip","year":"2017","unstructured":"Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros. 2017b. Image-To-Image Translation With Conditional Adversarial Networks. In CVPR."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459860"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657480"},{"key":"e_1_2_1_21_1","volume-title":"InfiniteYou: Flexible photo recrafting while preserving your identity. arXiv preprint arXiv:2503.16418","author":"Jiang Liming","year":"2025","unstructured":"Liming Jiang, Qing Yan, Yumin Jia, Zichuan Liu, Hao Kang, and Xin Lu. 2025. InfiniteYou: Flexible photo recrafting while preserving your identity. arXiv preprint arXiv:2503.16418 (2025)."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_2_1_23_1","unstructured":"Tero Karras Miika Aittala Janne Hellsten Samuli Laine Jaakko Lehtinen and Timo Aila. 2020. Training Generative Adversarial Networks with Limited Data. In NIPS."},{"key":"e_1_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Tero Karras Samuli Laine and Timo Aila. 2019. A style-based generator architecture for generative adversarial networks. In CVPR.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_2_1_25_1","volume-title":"Supervised contrastive learning. Advances in neural information processing systems 33","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems 33 (2020), 18661\u201318673."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01819"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555416"},{"key":"e_1_2_1_28_1","unstructured":"Black Forest Labs. 2025. FLUX.2: Frontier Visual Intelligence. https:\/\/bfl.ai\/blog\/flux-2."},{"key":"e_1_2_1_29_1","volume-title":"The measurement of observer agreement for categorical data. biometrics","author":"Richard Landis J","year":"1977","unstructured":"J Richard Landis and Gary G Koch. 1977. The measurement of observer agreement for categorical data. biometrics (1977), 159\u2013174."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.70234"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/0005-2795(75)90109-9"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530159"},{"key":"e_1_2_1_34_1","volume-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073","author":"Meng Chenlin","year":"2021","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2021a. Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01400"},{"key":"e_1_2_1_36_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 6038\u20136047","author":"Mokady Ron","year":"2023","unstructured":"Ron Mokady, Amir Hertz, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2023. Nulltext inversion for editing real images using guided diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 6038\u20136047."},{"key":"e_1_2_1_37_1","unstructured":"OpenAI. 2025. ChatGPT. https:\/\/chat.openai.com\/."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01213"},{"key":"e_1_2_1_40_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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. arXiv preprint arXiv:2103.00020 (2021)."},{"key":"e_1_2_1_41_1","volume-title":"Pivotal tuning for latent-based editing of real images. ACM Transactions on graphics (TOG) 42, 1","author":"Roich Daniel","year":"2022","unstructured":"Daniel Roich, Ron Mokady, Amit H Bermano, and Daniel Cohen-Or. 2022. Pivotal tuning for latent-based editing of real images. ACM Transactions on graphics (TOG) 42, 1 (2022), 1\u201313."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICEET53442.2021.9659697"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01102"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"e_1_2_1_46_1","volume-title":"Designing an encoder for stylegan image manipulation. ACM Transactions on graphics (TOG) 40, 4","author":"Tov Omer","year":"2021","unstructured":"Omer Tov, Yuval Alaluf, Yotam Nitzan, Or Patashnik, and Daniel Cohen-Or. 2021. Designing an encoder for stylegan image manipulation. ACM Transactions on graphics (TOG) 40, 4 (2021), 1\u201314."},{"key":"e_1_2_1_47_1","volume-title":"Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, et al.","author":"Tschannen Michael","year":"2025","unstructured":"Michael Tschannen, Alexey Gritsenko, Xiao Wang, Muhammad Ferjad Naeem, Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, et al. 2025. Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)."},{"key":"e_1_2_1_48_1","volume-title":"Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022","author":"Ulyanov Dmitry","year":"2016","unstructured":"Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. 2016. Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"e_1_2_1_50_1","volume-title":"Instantid: Zero-shot identity-preserving generation in seconds. arXiv preprint arXiv:2401.07519","author":"Wang Qixun","year":"2024","unstructured":"Qixun Wang, Xu Bai, Haofan Wang, Zekui Qin, Anthony Chen, Huaxia Li, Xu Tang, and Yao Hu. 2024. Instantid: Zero-shot identity-preserving generation in seconds. arXiv preprint arXiv:2401.07519 (2024)."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"e_1_2_1_52_1","unstructured":"Chenfei Wu Jiahao Li Jingren Zhou Junyang Lin Kaiyuan Gao Kun Yan Sheng-ming Yin Shuai Bai Xiao Xu Yilei Chen et al. 2025. Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)."},{"key":"e_1_2_1_53_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_2_1_54_1","volume-title":"Learning face representation from scratch. arXiv preprint arXiv:1411.7923","author":"Yi Dong","year":"2014","unstructured":"Dong Yi, Zhen Lei, Shengcai Liao, and Stan Z Li. 2014. Learning face representation from scratch. arXiv preprint arXiv:1411.7923 (2014)."},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00431"},{"key":"e_1_2_1_56_1","volume-title":"Soyeon Yoon, Seongcheol Kim, Soohyun Ji, Amirsaman Ashtari, and Junyong Noh.","author":"Yun Kwan","year":"2024","unstructured":"Kwan Yun, Kwanggyoon Seo, Chang Wook Seo, Soyeon Yoon, Seongcheol Kim, Soohyun Ji, Amirsaman Ashtari, and Junyong Noh. 2024. Stylized face sketch extraction via generative prior with limited data. In Computer Graphics Forum, Vol. 43. Wiley Online Library, e15045."},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01814"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_2_1_60_1","volume-title":"Mind the gap: Domain gap control for single shot domain adaptation for generative adversarial networks. arXiv preprint arXiv:2110.08398","author":"Zhu Peihao","year":"2021","unstructured":"Peihao Zhu, Rameen Abdal, John Femiani, and Peter Wonka. 2021a. Mind the gap: Domain gap control for single shot domain adaptation for generative adversarial networks. arXiv preprint arXiv:2110.08398 (2021)."},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01035"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T07:13:31Z","timestamp":1783062811000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3811360"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,3]]},"references-count":61,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7,3]]}},"alternative-id":["10.1145\/3811360"],"URL":"https:\/\/doi.org\/10.1145\/3811360","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,3]]},"assertion":[{"value":"2026-01-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}