{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T22:10:07Z","timestamp":1760652607409,"version":"build-2065373602"},"reference-count":24,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:00:00Z","timestamp":1760140800000},"content-version":"vor","delay-in-days":10,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102125"],"award-info":[{"award-number":["62102125"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Fast and highly realistic multi\u2010view hair transfer plays a crucial role in evaluating the effectiveness of virtual hair try\u2010on systems. However, GAN\u2010based generation and editing methods face persistent challenges in feature disentanglement. Achieving pixel\u2010level, attribute\u2010specific modifications\u2014such as changing hairstyle or hair color without affecting other facial features\u2014remains a long\u2010standing problem. To address this limitation, we propose a novel multi\u2010view hair transfer framework that leverages a hair\u2010only intermediate facial representation and a 3D\u2010guided masking mechanism. Our approach disentangles tri\u2010plane facial features into spatial geometric components and global style descriptors, enabling independent and precise control over hairstyle and hair color. By introducing a dedicated intermediate representation focused solely on hair and incorporating a two\u2010stage feature fusion strategy guided by the generated 3D mask, our framework achieves fine\u2010grained local editing across multiple viewpoints while preserving facial integrity and improving background consistency. Extensive experiments demonstrate that our method produces visually compelling and natural results in side\u2010to\u2010front view hair transfer tasks, offering a robust and flexible solution for high\u2010fidelity hair reconstruction and manipulation.<\/jats:p>","DOI":"10.1111\/cgf.70245","type":"journal-article","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:18:08Z","timestamp":1760185088000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Feature Disentanglement in GANs for Photorealistic Multi\u2010view Hair Transfer"],"prefix":"10.1111","volume":"44","author":[{"given":"Jiayi","family":"Xu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University"}]},{"given":"Zhengyang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University"}]},{"given":"Chenming","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University"}]},{"given":"Xiaogang","family":"Jin","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University"}]},{"given":"Yaohua","family":"Ji","sequence":"additional","affiliation":[{"name":"Hangzhou Chicheng Digital Technology Co., Ltd"}]}],"member":"311","published-online":{"date-parts":[[2025,10,11]]},"reference":[{"key":"e_1_2_7_2_2","unstructured":"BilecenB. B. YalinY. YuN. DundarA.: Reference-based 3d-aware image editing with triplanes.arXiv preprint arXiv:2404.03632(2024). 1 3 11"},{"key":"e_1_2_7_3_2","doi-asserted-by":"crossref","unstructured":"ChangS. KimG. KimH.: Hairnerf: Geometry-aware image synthesis for hairstyle transfer. In2023 IEEE\/CVF International Conference on Computer Vision (ICCV)(2023) pp.2448\u20132458. 1","DOI":"10.1109\/ICCV51070.2023.00232"},{"key":"e_1_2_7_4_2","unstructured":"ChanE. R. LinC. Z. ChanM. A. NaganoK. PanB. De MelloS. GalloO. GuibasL. J. TremblayJ. KhamisS. et al.: Efficient geometry-aware 3d generative adversarial networks. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2022) pp.16123\u201316133. 3 4 8"},{"key":"e_1_2_7_5_2","doi-asserted-by":"crossref","unstructured":"DengJ. GuoJ. XueN. ZafeiriouS.: Arcface: Additive angular margin loss for deep face recognition. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2019) pp.4690\u20134699. 11","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_2_7_6_2","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow I. J.","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_7_7_2","doi-asserted-by":"crossref","unstructured":"HuangX. BelongieS.: Arbitrary style transfer in real-time with adaptive instance normalization. InProceedings of the IEEE International Conference on Computer Vision(2017) pp.1501\u20131510. 5","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_2_7_8_2","doi-asserted-by":"crossref","unstructured":"HyungJ. HwangS. KimD. LeeH. ChooJ.: Local 3d editing via 3d distillation of clip knowledge. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2023) pp.12674\u201312684. 2 3 11","DOI":"10.1109\/CVPR52729.2023.01219"},{"key":"e_1_2_7_9_2","unstructured":"JiangK. ChenS.-Y. LiuF.-L. FuH. GaoL.: Towards high-quality and disentangled face editing in a 3d gan.IEEE Transactions on Pattern Analysis and Machine Intelligence(2025). 1 2 3 11"},{"key":"e_1_2_7_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3347299"},{"key":"e_1_2_7_11_2","first-page":"188","volume-title":"European Conference on Computer Vision","author":"Kim T.","year":"2022"},{"key":"e_1_2_7_12_2","doi-asserted-by":"crossref","unstructured":"KarrasT. LaineS. AilaT.: A style-based generator architecture for generative adversarial networks. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2019) pp.4401\u20134410. 2 8","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_2_7_13_2","unstructured":"KarrasT. LaineS. AittalaM. HellstenJ. LehtinenJ. AilaT.: Analyzing and improving the image quality of style-gan. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2020) pp.8110\u20138119. 4"},{"key":"e_1_2_7_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78172-8_7"},{"key":"e_1_2_7_15_2","unstructured":"RadfordA. KimJ. W. HallacyC. RameshA. GohG. AgarwalS. SastryG. AskellA. MishkinP. ClarkJ. et al.: Learning transferable visual models from natural language supervision. InInternational Conference on Machine Learning(2021) PmLR pp.8748\u20138763. 2"},{"key":"e_1_2_7_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544777"},{"key":"e_1_2_7_17_2","doi-asserted-by":"publisher","DOI":"10.1137\/S0036144598347059"},{"key":"e_1_2_7_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555506"},{"key":"e_1_2_7_19_2","doi-asserted-by":"crossref","unstructured":"SunJ. WangX. ZhangY. LiX. ZhangQ. LiuY. WangJ.: Fenerf: Face editing in neural radiance fields. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2022) pp.7672\u20137682. 2","DOI":"10.1109\/CVPR52688.2022.00752"},{"key":"e_1_2_7_20_2","unstructured":"WangC. ChaiM. HeM. ChenD. LiaoJ.: Clip-nerf: Text-and-image driven manipulation of neural radiance fields. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2022) pp.3835\u20133844. 2 3"},{"key":"e_1_2_7_21_2","doi-asserted-by":"crossref","unstructured":"WeiT. ChenD. ZhouW. LiaoJ. ZhangW. HuaG. YuN.: Hairclipv2: Unifying hair editing via proxy feature blending. InProceedings of the IEEE\/CVF International Conference on Computer Vision(2023) pp.23589\u201323599. 2 9","DOI":"10.1109\/ICCV51070.2023.02156"},{"key":"e_1_2_7_22_2","unstructured":"WuY. YangY.-L. JinX.: Hairmapper: Removing hair from portraits using gans. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2022) pp.4227\u20134236. 3 6 8"},{"key":"e_1_2_7_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01515-2"},{"key":"e_1_2_7_24_2","unstructured":"ZhuP. AbdalR. FemianiJ. WonkaP.: Barbershop: Gan-based image compositing using segmentation masks.arXiv preprint arXiv:2106.01505(2021). 2 9"},{"key":"e_1_2_7_25_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33123"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T21:33:32Z","timestamp":1760650412000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70245"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":24,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1111\/cgf.70245"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70245","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"type":"print","value":"0167-7055"},{"type":"electronic","value":"1467-8659"}],"subject":[],"published":{"date-parts":[[2025,10]]},"assertion":[{"value":"2025-10-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70245"}}