{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T16:50:33Z","timestamp":1774284633501,"version":"3.50.1"},"reference-count":54,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62262036, 62362043"],"award-info":[{"award-number":["62262036, 62362043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Xingdian Talent","award":["KKXY202203008"],"award-info":[{"award-number":["KKXY202203008"]}]},{"name":"Yunnan Science and Technology Program","award":["202502AD080003, 202503AA080013"],"award-info":[{"award-number":["202502AD080003, 202503AA080013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>High-quality garment representation is both a challenge and a key factor in constructing generalized 3D humans from a single-view image. Existing techniques often perform poorly when handling complex garments, primarily due to two critical challenges: (1) Single-view images lack complete information about the garments, limiting the completeness and realism of the reconstruction results. (2) The model\u2019s generalization ability is insufficient, resulting in significant inconsistencies in garment texture and structure when rendered from different viewpoints, which severely impacts the quality of novel view images. To improve the quality of novel view images, we propose a three-stage garment-aware Neural Radiance Field (NeRF) method for generalizable 3D human digitization. To supplement the missing garment information in single-view images, the first garment prior awareness stage focuses on extracting prior knowledge of the garment\u2019s shape, pose deformations, and style. To comprehensively eliminate ambiguities in rendered images across different viewpoints, we then introduce a set of prior-aware feature learning in the second stage to represent garment\u2019s global texture, geometry, and fine details. Additionally, a garment-aware NeRF module with fusion and decoder is designed in the third stage to effectively fuse these prior features, and thus our model can render novel view clothed human and generate high-quality results. Experimental results on RenderPeople, Thuman, and HuMMan datasets demonstrate that our method achieves superior performance and robust generalization in garment representation over the existing methods, especially for synthesizing novel view images of garments without the human body.<\/jats:p>","DOI":"10.1145\/3798043","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T06:35:55Z","timestamp":1772174155000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Garment-Aware Neural Radiance Fields for Generalizable 3D Human Digitization"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0399-3260","authenticated-orcid":false,"given":"Wei","family":"Yin","sequence":"first","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9685-6599","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1354-2293","authenticated-orcid":false,"given":"Xiaodong","family":"Fu","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4543-0111","authenticated-orcid":false,"given":"Lijun","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9572-951X","authenticated-orcid":false,"given":"Wei","family":"Peng","sequence":"additional","affiliation":[{"name":"Computer Technology Application Key Lab of Yunnan Province, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,23]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"1","volume-title":"Proceedings of the SIGGRAPH Asia 2023 Conference Papers","author":"AlBahar Badour","year":"2023","unstructured":"Badour AlBahar, Shunsuke Saito, Hung-Yu Tseng, Changil Kim, Johannes Kopf, and Jia-Bin Huang. 2023. Single-image 3D human digitization with shape-guided diffusion. In Proceedings of the SIGGRAPH Asia 2023 Conference Papers, 1\u201311."},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"e_1_3_1_5_2","unstructured":"Jianchuan Chen Ying Zhang Di Kang Xuefei Zhe Linchao Bao Xu Jia and Huchuan Lu. 2021. Animatable neural radiance fields from monocular RGB videos. arXiv:2106.13629. Retrieved from https:\/\/arxiv.org\/abs\/2106.13629"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3380059"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00700"},{"key":"e_1_3_1_8_2","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1109\/3DV57658.2022.00036","volume-title":"Proceedings of the 2022 International Conference on 3D Vision (3DV)","author":"Choi Hongsuk","year":"2022","unstructured":"Hongsuk Choi, Gyeongsik Moon, Matthieu Armando, Vincent Leroy, Kyoung Mu Lee, and Gr\u00e9gory Rogez. 2022. MonoNHR: Monocular neural human renderer. In Proceedings of the 2022 International Conference on 3D Vision (3DV). IEEE, 242\u2013251."},{"key":"e_1_3_1_9_2","first-page":"5159","article-title":"UniParser: Multi-human parsing with unified correlation representation learning","author":"Chu Jiaming","year":"2024","unstructured":"Jiaming Chu, Lei Jin, Yinglei Teng, Jianshu Li, Yunchao Wei, Zheng Wang, Junliang Xing, Shuicheng Yan, and Jian Zhao. 2024. UniParser: Multi-human parsing with unified correlation representation learning. IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing 33 (2024), 5159\u20135171.","journal-title":"IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01170"},{"key":"e_1_3_1_11_2","volume-title":"Proceedings of the Conference on Computer Vision and Pattern Recognition","volume":"1","author":"DeLuigi Luca","year":"2023","unstructured":"Luca DeLuigi, Ren Li, Beno\u00eet Guillard, Mathieu Salzmann, and Pascal Fua. 2023. DrapeNet: Generating garments and draping them with self-supervision. In Proceedings of the Conference on Computer Vision and Pattern Recognition, Vol. 1, 4."},{"issue":"8","key":"e_1_3_1_12_2","first-page":"6110","article-title":"MPS-","volume":"47","author":"Gao Xiangjun","year":"2025","unstructured":"Xiangjun Gao, Jiaolong Yang, Jongyoo Kim, Sida Peng, Zicheng Liu, and Xin Tong. 2025. MPS-NeRF: Generalizable 3D human rendering from multiview images. IEEE Transactions on Pattern Analysis and Machine Intelligence 47, 8 (2025), 6110\u20136121.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_13_2","first-page":"634","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu Liangxiao","year":"2024","unstructured":"Liangxiao Hu, Hongwen Zhang, Yuxiang Zhang, Boyao Zhou, Boning Liu, Shengping Zhang, and Liqiang Nie. 2024. GaussianAvatar: Towards realistic human avatar modeling from a single video via animatable 3D Gaussians. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 634\u2013644."},{"key":"e_1_3_1_14_2","first-page":"9352","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Hu Shoukang","year":"2023","unstructured":"Shoukang Hu, Fangzhou Hong, Liang Pan, Haiyi Mei, Lei Yang, and Ziwei Liu. 2023. Sherf: Generalizable human NeRF from a single image. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9352\u20139364."},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00152"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00316"},{"key":"e_1_3_1_17_2","first-page":"12949","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Jang Wonbong","year":"2021","unstructured":"Wonbong Jang and Lourdes Agapito. 2021. CodeNeRF: Disentangled neural radiance fields for object categories. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 12949\u201312958."},{"key":"e_1_3_1_18_2","first-page":"402","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Jiang Wei","year":"2022","unstructured":"Wei Jiang, Kwang Moo Yi, Golnoosh Samei, Oncel Tuzel, and Anurag Ranjan. 2022. Neuman: Neural human radiance field from a single video. In Proceedings of the European Conference on Computer Vision. Springer, 402\u2013418."},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00744"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_1_22_2","first-page":"24741","article-title":"Neural human performer: Learning generalizable radiance fields for human performance rendering","volume":"34","author":"Kwon Youngjoong","year":"2021","unstructured":"Youngjoong Kwon, Dahun Kim, Duygu Ceylan, and Henry Fuchs. 2021. Neural human performer: Learning generalizable radiance fields for human performance rendering. In Advances in Neural Information Processing Systems, Vol. 34, 24741\u201324752.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_23_2","unstructured":"Mengtian Li Shengxiang Yao Zhifeng Xie and Keyu Chen. 2024. Gaussianbody: Clothed human reconstruction via 3D Gaussian splatting. arXiv:2401.09720. Retrieved from https:\/\/arxiv.org\/abs\/2401.09720"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/280811.281026"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00650"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"issue":"1","key":"e_1_3_1_28_2","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/3503250","article-title":"Representing scenes as neural radiance fields for view synthesis","volume":"65","author":"Mildenhall Ben","year":"2021","unstructured":"Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, and Ren Ng. 2021. NeRF: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM 65, 1 (2021), 99\u2013106.","journal-title":"Communications of the ACM"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00356"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00571"},{"key":"e_1_3_1_31_2","first-page":"6011","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Onizuka Hayato","year":"2020","unstructured":"Hayato Onizuka, Zehra Hayirci, Diego Thomas, Akihiro Sugimoto, Hideaki Uchiyama, and Rin-Ichiro Taniguchi. 2020. TetraTSDF: 3D human reconstruction from a single image with a tetrahedral outer shell. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6011\u20136020."},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_36"},{"key":"e_1_3_1_33_2","first-page":"74383","article-title":"HumanSplat: Generalizable single-image human Gaussian splatting with structure priors","volume":"37","author":"Pan Panwang","year":"2024","unstructured":"Panwang Pan, Zhuo Su, Chenguo Lin, Zhen Fan, Yongjie Zhang, Zeming Li, Tingting Shen, Yadong Mu, and Yebin Liu. 2024. HumanSplat: Generalizable single-image human Gaussian splatting with structure priors. In Advances in Neural Information Processing Systems, Vol. 37, 74383\u201374410.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_1_36_2","doi-asserted-by":"crossref","first-page":"e14792","DOI":"10.1111\/cgf.14792","article-title":"Feature representation for high-resolution clothed human reconstruction","volume":"42","author":"Pu Juncheng","year":"2023","unstructured":"Juncheng Pu, Li Liu, Xiaodong Fu, Zhuo Su, Lijun Liu, and Wei Peng. 2023. Feature representation for high-resolution clothed human reconstruction. Computer Graphics Forum 42 (2023), e14792.","journal-title":"Computer Graphics Forum"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.4236\/jcc.2019.73002"},{"key":"e_1_3_1_41_2","first-page":"12278","article-title":"A-","volume":"34","author":"Su Shih-Yang","year":"2021","unstructured":"Shih-Yang Su, Frank Yu, Michael Zollh\u00f6fer, and Helge Rhodin. 2021. A-NeRF: Articulated neural radiance fields for learning human shape, appearance, and pose. In Advances in Neural Information Processing Systems, Vol. 34, 12278\u201312291.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00650"},{"key":"e_1_3_1_43_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_1_45_2","unstructured":"Zhenzhen Weng Jingyuan Liu Hao Tan Zhan Xu Yang Zhou Serena Yeung-Levy and Jimei Yang. 2024. Template-free single-view 3D human digitalization with diffusion-guided LRM. arXiv:2401.12175. Retrieved from https:\/\/arxiv.org\/abs\/2401.12175"},{"key":"e_1_3_1_46_2","first-page":"13286","volume-title":"Proceedings of the 2022 IEEE in CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xiu Yuliang","year":"2022","unstructured":"Yuliang Xiu, Jinlong Yang, Dimitrios Tzionas, and Michael J. Black. 2022. Icon: Implicit clothed humans obtained from normals. In Proceedings of the 2022 IEEE in CVF Conference on Computer Vision and Pattern Recognition (CVPR), 13286\u201313296."},{"key":"e_1_3_1_47_2","first-page":"9122","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Yang Xueting","year":"2023","unstructured":"Xueting Yang, Yihao Luo, Yuliang Xiu, Wei Wang, Hao Xu, and Zhaoxin Fan. 2023. D-if: Uncertainty-aware human digitization via implicit distribution field. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9122\u20139132."},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3514248"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_1_50_2","first-page":"7818","article-title":"Global-correlated 3D-decoupling transformer for clothed avatar reconstruction","volume":"36","author":"Zhang Zechuan","year":"2023","unstructured":"Zechuan Zhang, Li Sun, Zongxin Yang, Ling Chen, and Yi Yang. 2023. Global-correlated 3D-decoupling transformer for clothed avatar reconstruction. In Advances in Neural Information Processing Systems, Vol. 36, 7818\u20137830.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00948"},{"key":"e_1_3_1_52_2","unstructured":"Fuqiang Zhao Wei Yang Jiakai Zhang Pei Lin Yingliang Zhang Jingyi Yu and Lan Xu. 2021. HumanNeRF: Generalizable neural human radiance field from sparse inputs. arXiv:2112.02789. Retrieved from https:\/\/arxiv.org\/abs\/2112.02789"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01861"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050505"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00783"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3798043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T15:51:37Z","timestamp":1774281097000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3798043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,23]]},"references-count":54,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3798043"],"URL":"https:\/\/doi.org\/10.1145\/3798043","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,23]]},"assertion":[{"value":"2024-08-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}