{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T01:35:30Z","timestamp":1772674530465,"version":"3.50.1"},"reference-count":52,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T00:00:00Z","timestamp":1717977600000},"content-version":"vor","delay-in-days":40,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2023C01047"],"award-info":[{"award-number":["2023C01047"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Animation &amp;amp; Virtual"],"published-print":{"date-parts":[[2024,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The rapid development of the online apparel shopping industry demands innovative solutions for high\u2010quality digital apparel sample displays with virtual avatars. However, developing such displays is prohibitively expensive and prone to the well\u2010known \u201cuncanny valley\u201d effect, where a nearly human\u2010looking artifact arouses eeriness and repulsiveness, thus affecting the user experience. To effectively mitigate the \u201cuncanny valley\u201d effect and improve the overall authenticity of digital apparel sample displays, we present a novel photo\u2010realistic portrait generation framework. Our key idea is to employ transfer learning to learn an identity\u2010consistent mapping from the latent space of rendered portraits to that of real portraits. During the inference stage, the input portrait of an avatar can be directly transferred to a realistic portrait by changing its appearance style while maintaining the facial identity. To this end, we collect a new dataset, <jats:bold>D<\/jats:bold>az\u2010<jats:bold>R<\/jats:bold>endered\u2010<jats:bold>F<\/jats:bold>aces\u2010<jats:bold>HQ<\/jats:bold> (<jats:italic>DRFHQ<\/jats:italic>), specifically designed for rendering\u2010style portraits. We leverage this dataset to fine\u2010tune the StyleGAN2\u2010<jats:italic>FFHQ<\/jats:italic> generator, using our carefully crafted framework, which helps to preserve the geometric and color features relevant to facial identity. We evaluate our framework using portraits with diverse gender, age, and race variations. Qualitative and quantitative evaluations, along with ablation studies, highlight our method's advantages over state\u2010of\u2010the\u2010art approaches.<\/jats:p>","DOI":"10.1002\/cav.2278","type":"journal-article","created":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T07:14:18Z","timestamp":1718003658000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Identity\u2010consistent transfer learning of portraits for digital apparel sample display"],"prefix":"10.1002","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5727-5417","authenticated-orcid":false,"given":"Luyuan","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Lab of CAD&amp;CG Zhejiang University  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqian","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG Zhejiang University  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong\u2010Liang","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science University of Bath  Bath UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG Zhejiang University  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7339-2920","authenticated-orcid":false,"given":"Xiaogang","family":"Jin","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG Zhejiang University  Hangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2024,6,10]]},"reference":[{"key":"e_1_2_8_2_1","unstructured":"Browzwear.Browzwear Solutions Pte Ltd. 2000\u20102024.http:\/\/browzwear.com"},{"key":"e_1_2_8_3_1","unstructured":"CLO.CLO Virtual Fashion LLC. 2024.http:\/\/clo3d.com"},{"key":"e_1_2_8_4_1","unstructured":"Optitex.OPTITEX. 1988\u20102022.http:\/\/optitex.com"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392464"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344855"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417821"},{"key":"e_1_2_8_8_1","first-page":"33","article-title":"Bukimi no tani [the uncanny valley]","volume":"7","author":"Mori M","year":"1970","journal-title":"Energy"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep00864"},{"key":"e_1_2_8_10_1","volume-title":"Advances in Neural Information Processing Systems","author":"Goodfellow I","year":"2014"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"e_1_2_8_12_1","first-page":"4401","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"Karras T","year":"2019"},{"key":"e_1_2_8_13_1","first-page":"852","volume-title":"Advances in Neural Information Processing Systems","author":"Karras T","year":"2021"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00971"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591500"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480509"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_14"},{"key":"e_1_2_8_18_1","first-page":"12104","volume-title":"Advances in Neural Information Processing Systems","author":"Karras T","year":"2020"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/pres.16.4.337"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-016-0380-9"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00852"},{"key":"e_1_2_8_23_1","unstructured":"PinkneyJNM AdlerD.Resolution dependent GAN interpolation for controllable image synthesis between domains.CoRRabs\/2010.05334 2020."},{"key":"e_1_2_8_24_1","unstructured":"WuZ NitzanY ShechtmanE LischinskiD.StyleAlign: analysis and applications of aligned StyleGAN models. arXiv preprint arXiv:2110.11323 2021."},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"e_1_2_8_26_1","unstructured":"LiuP SongL ZhangD HuaH TangY TuH et al.Emo\u2010Avatar: efficient monocular video style avatar through texture rendering. arXiv preprint arXiv:2402.00827 2024."},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555402"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00182"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"e_1_2_8_30_1","unstructured":"Daz Productions.Daz Productions Inc. 2024.https:\/\/www.daz3d.com\/gallery"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.241"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00366"},{"key":"e_1_2_8_33_1","first-page":"29710","volume-title":"Advances in Neural Information Processing Systems","author":"Liu M","year":"2021"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0231266"},{"key":"e_1_2_8_35_1","unstructured":"Synthesis AI.Synthesis AI. 2022.https:\/\/opensynthetics.com\/dataset\/diverse\u2010human\u2010faces\u2010dataset\/"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459760"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_2_8_39_1","unstructured":"Flickr.Flickr. 2024.https:\/\/flickr.com"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"e_1_2_8_42_1","first-page":"2287","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"Richardson E","year":"2021"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01796"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00664"},{"issue":"1","key":"e_1_2_8_45_1","first-page":"6:1","article-title":"Pivotal tuning for latent\u2010based editing of real images","volume":"42","author":"Roich D","year":"2022","journal-title":"ACM Trans Graph"},{"key":"e_1_2_8_46_1","unstructured":"MengC HeY SongY SongJ WuJ ZhuJ\u2010Y et al.SDEdit: guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 2022."},{"key":"e_1_2_8_47_1","first-page":"1","volume-title":"10th International Conference on Learning Representations","author":"Zhu P","year":"2022"},{"key":"e_1_2_8_48_1","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang Z","year":"2022"},{"key":"e_1_2_8_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459771"},{"key":"e_1_2_8_50_1","volume-title":"Advances in Neural Information Processing Systems","author":"Heusel M","year":"2017"},{"key":"e_1_2_8_51_1","doi-asserted-by":"crossref","unstructured":"HuangY WangY TaiY LiuX ShenP LiS et al.CurricularFace: adaptive curriculum learning loss for deep face recognition. arXiv preprint arXiv:2004.00288 2020.","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"e_1_2_8_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"e_1_2_8_53_1","unstructured":"Zllrunning.face\u2010parsing.PyTorch. 2019.https:\/\/github.com\/zllrunning\/face\u2010parsing.PyTorch"}],"container-title":["Computer Animation and Virtual Worlds"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cav.2278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T06:35:08Z","timestamp":1720420508000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cav.2278"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":52,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["10.1002\/cav.2278"],"URL":"https:\/\/doi.org\/10.1002\/cav.2278","archive":["Portico"],"relation":{},"ISSN":["1546-4261","1546-427X"],"issn-type":[{"value":"1546-4261","type":"print"},{"value":"1546-427X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]},"assertion":[{"value":"2024-04-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-03","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2278"}}