Article(id=1322960992237400863, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322960856543273127, articleNumber=null, orderNo=null, doi=10.11834/jig.250413, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1757001600000, receivedDateStr=2025-09-05, revisedDate=1766937600000, revisedDateStr=2025-12-29, acceptedDate=null, acceptedDateStr=null, onlineDate=1793348079976, onlineDateStr=2026-10-30, pubDate=1786809600000, pubDateStr=2026-08-16, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793348079976, onlineIssueDateStr=2026-10-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793348079976, creator=13701087609, updateTime=1793348079976, updator=13701087609, issue=Issue{id=1322960856543273127, tenantId=1146029695717560320, journalId=1249024232475115590, year='2026', volume='31', issue='8', pageStart='2687', pageEnd='3074', issueExtLink='null', onlineDate='null', pubDate='1786809600000', pubDateStr='2026-08-16', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793348047624, creator='13701087609', updateTime=1793348605344, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1322963195874378645, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322960856543273127, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1322963195874378646, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322960856543273127, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=3001, endPage=3014, ext={EN=ArticleExt(id=1322960992417755936, articleId=1322960992237400863, tenantId=1146029695717560320, journalId=1249024232475115590, language=EN, title=PerRec: 3D dressed human reconstruction from perspective images via distortion feature decoupling and pseudo multi-view constraints, columnId=1249044008786400014, journalTitle=Journal of Image and Graphics, columnName=Image Understanding and Computer Vision, runingTitle=null, highlight=null, articleAbstract=
Objective Reconstructing clothed human bodies from a single perspective-distorted image is a fundamental yet challenging problem in computer vision,with broad applications in virtual try-on,digital human creation,AR/VR content generation,and human-computer interaction. Although recent advances in monocular human reconstruction have achieved impressive progress,most existing approaches implicitly assume orthographic or weak-perspective projection models. These simplified assumptions neglect the actual imaging geometry of real cameras,reducing depth to a single global scaling factor and failing to capture the inherently nonlinear spatial variations caused by strong perspective distortion. Consequently,the reconstructed geometry often suffers from inaccurate limb proportions,inconsistent body scale,and distortion-dependent artifacts,particularly when the subject is close to the camera or occupies a non-central region of the image. Such limitations significantly undermine the applicability of current methods to real-world scenarios where perspective effects are inevitable.To address these shortcomings,This study proposes PerRec,a novel perspective-aware reconstruction framework specifically designed for recovering high-fidelity clothed human geometry from a single perspective-distorted RGB image.
Method The key idea of PerRec is to explicitly account for perspective-induced depth ambiguity and projection nonlinearity through a combination of distortion decoupling,geometric field representation,and pseudo-multiple-view supervision. Unlike existing models that attempt to implicitly learn perspective from data,PerRec introduces structural priors and tailored network designs that directly target the characteristics of perspective distortion,thereby enabling a more accurate and physically plausible 3D inference.The proposed framework contains four major components. First,a distortion decoupling module is introduced to separate image position from the underlying perspective distortion pattern. The method effectively normalizes spatial variance while preserving layout-dependent cues by uniformly partitioning the input image and generating virtual viewpoint transformations for each region. This mechanism allows the model to effectively capture how projection distortion changes across the field of view,mitigating the tendency of conventional models to collapse depth variations into oversimplified estimates. Second,we design a multi-scale attention hourglass network (MA-HGNet) to robustly extract local and global features under varying degrees of distortion. The network integrates a multi-level hourglass structure with channel attention mechanisms to refine fine-grained patterns,such as clothing folds,body boundaries,and high-curvature regions that are particularly susceptible to distortion. MA-HGNet demonstrates enhanced sensitivity to spatially localized distortions while maintaining stable global shape perception compared with standard convolutional backbones. Third,we convert the SMPL mesh into a Fourier occupancy field (FOF) to effectively capture continuous geometry and enhance high-frequency surface details. This representation encodes occupancy values using Fourier basis functions,enabling the network to model sharp transitions,intricate clothing topology,and subtle geometric variations that are difficult to represent with parametric models alone. The proposed model unifies the advantages of parametric priors and implicit fields,resulting in substantially detailed and expressive reconstructions. Finally,considering that a single image inherently lacks sufficient viewpoint diversity,we introduce a pseudo-multi-view module that synthesizes multiple virtual observations during training. These synthesized views act as implicit geometric constraints,guiding the network to learn distortion-invariant features and improving its ability to reason about occluded or heavily distorted regions. This strategy significantly boosts reconstruction robustness without requiring additional input views or multi-camera setups.
Result Extensive experiments are conducted on the Thuman2.0 and CustomHumans datasets,covering controlled and in-the-wild settings with diverse degrees of perspective distortion. Quantitative evaluations demonstrate that PerRec substantially outperforms state-of-the-art monocular reconstruction methods across multiple metrics,including chamfer distance,normal consistency,and point-to-surface error. Specifically,improvements of approximately 60%–80% are observed on average,highlighting the effectiveness of the proposed design in addressing global and local reconstruction quality. Qualitative comparisons further show that PerRec produces a stable body scale,highly realistic limb proportions,and detailed clothing geometry,particularly in strongly distorted images where competing methods typically fail.
Conclusion The contributions of this study are threefold. First,this study provides a comprehensive analysis of the limitations of existing projection assumptions in monocular reconstruction and establishes perspective distortion as a core challenge in real-world 3D human modeling. Second,this study proposes a unified reconstruction framework that integrates distortion decoupling,implicit field representation,and pseudo-multi-view learning,offering a principled and effective solution for handling perspective effects. Third,this study demonstrates that accurate and high-fidelity clothed human reconstruction from a single perspective-distorted image is achievable without relying on multi-view capture systems or camera calibration. Overall,this study offers a practical and extensible perspective-aware solution for real-world human reconstruction,bridging the gap between theoretical projection modeling and data-driven 3D inference. The proposed approach not only enhances geometric accuracy under challenging perspective conditions but also expands the applicability of monocular reconstruction methods to everyday images captured by mobile devices and consumer cameras. Results indicate that perspective distortion,long regarded as a major obstacle for monocular reconstruction,can be effectively resolved by combining structural modeling cues with carefully designed learning-based strategies.
, authors=Yuanwang Yang, Jian Ma
*, Yuan Meng, Kun Li
*, authorsList=Yuanwang Yang, Jian Ma, Yuan Meng, Kun Li, authorCompany=null, correspAuthors=Jian Ma, Kun Li, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1322960994225500971, articleId=1322960992237400863, tenantId=1146029695717560320, journalId=1249024232475115590, language=CN, title=畸变特征解耦与伪多视角约束的透视图像穿衣人体三维重建, columnId=1249044009054835474, journalTitle=中国图象图形学报, columnName=图像理解和计算机视觉, runingTitle=null, highlight=null, articleAbstract=
目的 单幅透视畸变图像的穿衣人体重建在虚拟试衣、数字人制作等应用中具有重要意义。然而,现有方法多采用正交或弱透视投影,忽略真实相机的成像规律,将深度简化为单一缩放因子,难以恢复透视畸变条件下真实的人体三维结构。为解决这一问题,提出一种面向透视图像的三维穿衣人体重建方法PerRec,通过畸变特征解耦与伪多视角约束缓解深度歧义与投影失真。
方法 首先利用均匀分块与虚拟视角变换解耦图像位置与透视畸变;随后设计多尺度注意力增强网络以强化局部细节表达;并将SMPL网格(skinned multi-person linear model)转化为傅里叶占有率场以提升高频几何重建能力;最后通过伪多视角模块模拟多视角特征以增强对畸变的鲁棒性。
结果 实验结果表明,PerRec在Thuman2.0和CustomHumans 数据集上均取得显著提升,在倒角距离、法线一致性和点到表面距离等指标上相较现有方法平均提升60%~80%。
结论 本文方法能够有效解决单幅透视图像下的结构失真问题,为真实场景中的高精度穿衣人体重建提供了可扩展的技术途径。
, authors=杨源旺, 马健
*, 孟源, 李坤
*, authorsList=杨源旺, 马健, 孟源, 李坤, authorCompany=null, correspAuthors=马健, 李坤, authorNote=
, correspAuthorsNote=
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=OHgSAHggQx0RTOMOBAAR0Q==, magXml=4i6Si4wjWb9RVq1s7rqJTA==, pdfUrl=null, pdf=aQOHlFlWuPTKmmHeCGnmZw==, pdfFileSize=3531985, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=clmz1O3vSAxpBuUWb0YkuA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=rZh07dXKbDIVyO+W0kSboA==, mapNumber=null, fund=null)}, authors=[Author(id=1322960994548462384, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yyw@tju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322960994623959858, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, authorId=1322960994548462384, language=EN, stringName=Yuanwang Yang, firstName=Yuanwang, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Intellgence and Computing,Tianjin University,Tianjin 300354,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322960994712040243, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, authorId=1322960994548462384, language=CN, stringName=杨源旺, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=天津大学智能与计算学部,天津 300354, bio={"content":"
杨源旺,男,硕士研究生,主要研究方向为计算机视觉和计算机图形学。E-mail: yyw@tju.edu.cn
"}, bioImg=null, bioContent=
杨源旺,男,硕士研究生,主要研究方向为计算机视觉和计算机图形学。E-mail: yyw@tju.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322960994464576300, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, xref=null, ext=[AuthorCompanyExt(id=1322960994472964909, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, companyId=1322960994464576300, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Intellgence and Computing,Tianjin University,Tianjin 300354,China), AuthorCompanyExt(id=1322960994481353518, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, companyId=1322960994464576300, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=天津大学智能与计算学部,天津 300354)])]), Author(id=1322960994791732021, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=jianma@tju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322960994858840887, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, authorId=1322960994791732021, language=EN, stringName=Jian Ma, firstName=Jian, middleName=null, lastName=Ma, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
*, address=College of Intellgence and Computing,Tianjin University,Tianjin 300354,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322960994913366840, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, authorId=1322960994791732021, language=CN, stringName=马健, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
*, address=天津大学智能与计算学部,天津 300354, bio={"content":"
马健,通信作者,男,助理研究员,硕士生导师,主要研究方向为三维视觉。E-mail:jianma@tju.edu.cn
"}, bioImg=null, bioContent=
马健,通信作者,男,助理研究员,硕士生导师,主要研究方向为三维视觉。E-mail:jianma@tju.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322960994464576300, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, xref=null, ext=[AuthorCompanyExt(id=1322960994472964909, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, companyId=1322960994464576300, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Intellgence and Computing,Tianjin University,Tianjin 300354,China), AuthorCompanyExt(id=1322960994481353518, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, companyId=1322960994464576300, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=天津大学智能与计算学部,天津 300354)])]), Author(id=1322960994984670010, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=ghqb480736_@tju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322960995055973180, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, authorId=1322960994984670010, language=EN, stringName=Yuan Meng, firstName=Yuan, middleName=null, lastName=Meng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Intellgence and Computing,Tianjin University,Tianjin 300354,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322960995127276349, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, authorId=1322960994984670010, language=CN, stringName=孟源, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=天津大学智能与计算学部,天津 300354, bio={"content":"
孟源,女,硕士研究生,主要研究方向为计算机视觉和计算机图形学。E-mail: ghqb480736_@tju.edu.cn
"}, bioImg=null, bioContent=
孟源,女,硕士研究生,主要研究方向为计算机视觉和计算机图形学。E-mail: ghqb480736_@tju.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322960994464576300, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, xref=null, ext=[AuthorCompanyExt(id=1322960994472964909, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, companyId=1322960994464576300, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Intellgence and Computing,Tianjin University,Tianjin 300354,China), AuthorCompanyExt(id=1322960994481353518, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, companyId=1322960994464576300, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=天津大学智能与计算学部,天津 300354)])]), Author(id=1322960995190190911, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lik@tju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322960995274076993, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, authorId=1322960995190190911, language=EN, stringName=Kun Li, firstName=Kun, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
*, address=College of Intellgence and Computing,Tianjin University,Tianjin 300354,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322960995345380162, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, authorId=1322960995190190911, language=CN, stringName=李坤, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
*, address=天津大学智能与计算学部,天津 300354, bio={"content":"
李坤,通信作者,女,教授,博士生导师,主要研究方向为计算机视觉与图形学、人工智能和多媒体处理。E-mail: lik@tju.edu.cn
"}, bioImg=null, bioContent=
李坤,通信作者,女,教授,博士生导师,主要研究方向为计算机视觉与图形学、人工智能和多媒体处理。E-mail: lik@tju.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322960994464576300, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, xref=null, ext=[AuthorCompanyExt(id=1322960994472964909, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, companyId=1322960994464576300, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Intellgence and Computing,Tianjin University,Tianjin 300354,China), AuthorCompanyExt(id=1322960994481353518, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, companyId=1322960994464576300, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=天津大学智能与计算学部,天津 300354)])])], keywords=[Keyword(id=1322960995471209283, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, orderNo=1, keyword=3D human reconstruction), Keyword(id=1322960995538318148, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, orderNo=2, keyword=perspective-distorted image), Keyword(id=1322960995588649797, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, orderNo=3, keyword=monocular camera), Keyword(id=1322960995647370054, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, orderNo=4, keyword=pseudo multi-perspective), Keyword(id=1322960995802559303, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, orderNo=5, keyword=RGB image), Keyword(id=1322960995890639688, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, orderNo=1, keyword=三维人体重建), Keyword(id=1322960995953554249, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, orderNo=2, keyword=透视畸变图像), Keyword(id=1322960996012274506, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, orderNo=3, keyword=单目相机), Keyword(id=1322960996075189067, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, orderNo=4, keyword=伪多视角), Keyword(id=1322960996159075148, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, orderNo=5, keyword=RGB图像)], refs=[Reference(id=1322960997895517023, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=7397, pageEnd=7409, url=null, language=null, rfNumber=null, rfOrder=0, authorNames=Feng Q, Liu Y B, Lai Y K, Yang J Y, Li K, journalName=null, refType=null, unstructuredReference=
Feng Q,
Liu Y B,
Lai Y K,
Yang J Y and
Li K.
2022. FOF: learning fourier occupancy field for monocular real-time human reconstruction//Proceedings of 2022 Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022. New Orleans,USA: [s.n.]: 7397-7409, articleTitle=FOF: learning fourier occupancy field for monocular real-time human reconstruction, refAbstract=null), Reference(id=1322960997983597408, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2412.05961.pdf, language=null, rfNumber=null, rfOrder=1, authorNames=Feng Q, Yang Y W, Liu Y B, Lai Y K, Yang J Y, Li K, journalName=null, refType=null, unstructuredReference=
Feng Q,
Yang Y W,
Liu Y B,
Lai Y K,
Yang J Y and
Li K.
2024. FOF-X: towards real-time detailed human reconstruction from a single image [EB/OL]. [2025-09-05]., articleTitle=FOF-X: towards real-time detailed human reconstruction from a single image, refAbstract=null), Reference(id=1322960998063289185, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=1997, volume=null, issue=null, pageStart=1106, pageEnd=1112, url=null, language=null, rfNumber=null, rfOrder=2, authorNames=Heikkila J, Silven O, journalName=null, refType=null, unstructuredReference=
Heikkila J and
Silven O.
1997. A four-step camera calibration procedure with implicit image correction//Proceedings of 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Juan,USA: IEEE: 1106-1112 [DOI:
10.1109/cvpr.1997.609468], articleTitle=A four-step camera calibration procedure with implicit image correction, refAbstract=null), Reference(id=1322960998126203746, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=538, pageEnd=549, url=null, language=null, rfNumber=null, rfOrder=3, authorNames=Ho H I, Song J, Hilliges O, journalName=null, refType=null, unstructuredReference=
Ho H I,
Song J and
Hilliges O.
2024. SiTH: single-view textured human reconstruction with image-conditioned diffusion//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle,USA: IEEE: 538-549 [DOI:
10.1109/cvpr52733.2024.00058], articleTitle=SiTH: single-view textured human reconstruction with image-conditioned diffusion, refAbstract=null), Reference(id=1322960998201701219, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=21024, pageEnd=21035, url=null, language=null, rfNumber=null, rfOrder=4, authorNames=Ho H I, Xue L X, Song J, Hilliges O, journalName=null, refType=null, unstructuredReference=
Ho H I,
Xue L X,
Song J and
Hilliges O.
2023. Learning locally editable virtual humans//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver,USA: IEEE: 21024-21035 [DOI:
10.1109/cvpr52729.2023.02014], articleTitle=Learning locally editable virtual humans, refAbstract=null), Reference(id=1322960998298170212, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=9, pageStart=2610, pageEnd=2624, url=null, language=null, rfNumber=null, rfOrder=5, authorNames=Huang Q P, Liu L, Fu X D, Liu L J, Peng W, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=
Huang Q P,
Liu L,
Fu X D,
Liu L J and
Peng W.
2024. Clothed feature learning for single-view 3D human reconstruction.
Journal of Image and Graphics,
29(9): 2610-2624, articleTitle=Clothed feature learning for single-view 3D human reconstruction, refAbstract=null), Reference(id=1322960998365279077, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=9, pageStart=2610, pageEnd=2624, url=null, language=null, rfNumber=null, rfOrder=6, authorNames=黄千芃, 刘骊, 付晓东, 刘利军, 彭玮, journalName=中国图象图形学报, refType=null, unstructuredReference=黄千芃,刘骊,付晓东,刘利军,彭玮.
2024. 单视角三维人体重建的着装特征学习.
中国图象图形学报,
29(9): 2610-2624 [DOI:
10.11834/jig.230623], articleTitle=单视角三维人体重建的着装特征学习, refAbstract=null), Reference(id=1322960998444970854, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=3090, pageEnd=3099, url=null, language=null, rfNumber=null, rfOrder=7, authorNames=Huang Z, Xu Y L, Lassner C, Li H, Tung T, journalName=null, refType=null, unstructuredReference=
Huang Z,
Xu Y L,
Lassner C,
Li H and
Tung T.
2020. Arch: animatable reconstruction of clothed humans//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle,USA: IEEE: 3090-3099 [DOI:
10.1109/cvpr42600.2020.00316], articleTitle=Arch: animatable reconstruction of clothed humans, refAbstract=null), Reference(id=1322960998507885415, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=402, pageEnd=418, url=null, language=null, rfNumber=null, rfOrder=8, authorNames=Jiang W, Yi K M, Samei G, Tuzel O, Ranjan A, journalName=null, refType=null, unstructuredReference=
Jiang W,
Yi K M,
Samei G,
Tuzel O and
Ranjan A.
2022. NeuMan: neural human radiance field from a single video//Proceedings of the 17th European Conference on Computer Vision (ECCV). Tel Aviv,Israel: Springer: 402-418 [DOI:
10.1007/978-3-031-19824-3_24], articleTitle=NeuMan: neural human radiance field from a single video, refAbstract=null), Reference(id=1322960998608548712, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=590, pageEnd=606, url=null, language=null, rfNumber=null, rfOrder=9, authorNames=Li Z H, Liu J Z, Zhang Z S, Xu S C, Yan Y L, journalName=null, refType=null, unstructuredReference=
Li Z H,
Liu J Z,
Zhang Z S,
Xu S C and
Yan Y L.
2022. CLIFF: carrying location information in full frames into human pose and shape estimation//Proceedings of the 17th European Conference on Computer Vision. Tel Aviv,Israel: Springer: 590-606 [DOI:
10.1007/978-3-031-20065-6_34], articleTitle=CLIFF: carrying location information in full frames into human pose and shape estimation, refAbstract=null), Reference(id=1322960998684046185, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=5, pageStart=98, pageEnd=122, url=null, language=null, rfNumber=null, rfOrder=10, authorNames=Liu L Y, Sun J C, Gao Y Q, Gao C X, Chen J Y, journalName=Journal of Huazhong University of Science and Technology (Natural Science Edition), refType=null, unstructuredReference=
Liu L Y,
Sun J C,
Gao Y Q,
Gao C X and
Chen J Y.
2024. Review of single-image 3D human reconstruction based on deep learning.
Journal of Huazhong University of Science and Technology (Natural Science Edition),
52(5): 98-122, articleTitle=Review of single-image 3D human reconstruction based on deep learning, refAbstract=null), Reference(id=1322960998751155050, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=5, pageStart=98, pageEnd=122, url=null, language=null, rfNumber=null, rfOrder=11, authorNames=刘乐元, 孙见弛, 高韵琪, 高常鑫, 陈靓影, journalName=华中科技大学学报 (自然科学版), refType=null, unstructuredReference=刘乐元,孙见弛,高韵琪,高常鑫,陈靓影.
2024. 基于深度学习的单图像三维人体重建研究综述.
华中科技大学学报 (自然科学版),
52(5): 98-122 [DOI:
10.13245/j.hust.240614], articleTitle=基于深度学习的单图像三维人体重建研究综述, refAbstract=null), Reference(id=1322960998814069611, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2015, volume=34, issue=6, pageStart=null, pageEnd=248, url=null, language=null, rfNumber=null, rfOrder=12, authorNames=Loper M, Mahmood N, Romero J, Pons-Moll G, Black M J, journalName=ACM Transactions on Graphics, refType=null, unstructuredReference=
Loper M,
Mahmood N,
Romero J,
Pons-Moll G and
Black M J.
2015. SMPL: a skinned multi-person linear model.
ACM Transactions on Graphics,
34(6): #248 [DOI:
10.1145/2816795.2818013], articleTitle=SMPL: a skinned multi-person linear model, refAbstract=null), Reference(id=1322960998872789868, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=598, pageEnd=613, url=null, language=null, rfNumber=null, rfOrder=13, authorNames=Osman A A A, Bolkart T, Black M J, journalName=null, refType=null, unstructuredReference=
Osman A A A,
Bolkart T and
Black M J.
2020. STAR: sparse trained articulated human body regressor//Proceedings of the 16th European Conference on Computer Vision (ECCV). Glasgow,UK: Springer: 598-613 [DOI:
10.1007/978-3-030-58539-6_36], articleTitle=STAR: sparse trained articulated human body regressor, refAbstract=null), Reference(id=1322960998939898733, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=10967, pageEnd=10977, url=null, language=null, rfNumber=null, rfOrder=14, authorNames=Pavlakos G, Choutas V, Ghorbani N, Bolkart T, Osman A A, Tzionas D, journalName=null, refType=null, unstructuredReference=
Pavlakos G,
Choutas V,
Ghorbani N,
Bolkart T,
Osman A A,
Tzionas D,
et al.
2019. Expressive body capture: 3D hands,face,and body from a single image//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach,USA: IEEE: 10967-10977 [DOI:
10.1109/cvpr.2019.01123], articleTitle=Expressive body capture: 3D hands,face,and body from a single image, refAbstract=null), Reference(id=1322960999011201902, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2022, volume=34, issue=3, pageStart=352, pageEnd=363, url=null, language=null, rfNumber=null, rfOrder=15, authorNames=Pu J C, Liu L, Fu X D, Liu L J, Huang Q S, journalName=Journal of Computer-Aided Design and Computer Graphics, refType=null, unstructuredReference=
Pu J C,
Liu L,
Fu X D,
Liu L J and
Huang Q S.
2022. Clothing visual representation for 3D human reconstruction.
Journal of Computer-Aided Design and Computer Graphics,
34(3): 352-363, articleTitle=Clothing visual representation for 3D human reconstruction, refAbstract=null), Reference(id=1322960999090893679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2022, volume=34, issue=3, pageStart=352, pageEnd=363, url=null, language=null, rfNumber=null, rfOrder=16, authorNames=普骏程, 刘骊, 付晓东, 刘利军, 黄青松, journalName=计算机辅助设计与图形学学报, refType=null, unstructuredReference=普骏程,刘骊,付晓东,刘利军,黄青松.
2022. 三维人体重建中的服装视觉信息表示.
计算机辅助设计与图形学学报,
34(3): 352-363 [DOI:
10.3724/SP.J.1089.2022.18921], articleTitle=三维人体重建中的服装视觉信息表示, refAbstract=null), Reference(id=1322960999149613936, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=2304, pageEnd=2314, url=null, language=null, rfNumber=null, rfOrder=17, authorNames=Saito S, Huang Z, Natsume R, Morishima S, Li H, Kanazawa A, journalName=null, refType=null, unstructuredReference=
Saito S,
Huang Z,
Natsume R,
Morishima S,
Li H and
Kanazawa A.
2019. PIFu: pixel-aligned implicit function for high-resolution clothed human digitization//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul,Korea(South): IEEE: 2304-2314 [DOI:
10.1109/iccv.2019.00239], articleTitle=PIFu: pixel-aligned implicit function for high-resolution clothed human digitization, refAbstract=null), Reference(id=1322960999216722801, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=81, pageEnd=90, url=null, language=null, rfNumber=null, rfOrder=18, authorNames=Saito S, Simon T, Saragih J, Joo H, journalName=null, refType=null, unstructuredReference=
Saito S,
Simon T,
Saragih J and
Joo H.
2020. PIFuHD: multi-level pixel-aligned implicit function for high-resolution 3D human digitization//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle,USA: IEEE: 81-90 [DOI:
10.1109/cvpr42600.2020.00016], articleTitle=PIFuHD: multi-level pixel-aligned implicit function for high-resolution 3D human digitization, refAbstract=null), Reference(id=1322960999288025970, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=2885, pageEnd=2896, url=null, language=null, rfNumber=null, rfOrder=19, authorNames=Saito S, Yang J L, Ma Q L, Black M J, journalName=null, refType=null, unstructuredReference=
Saito S,
Yang J L,
Ma Q L and
Black M J.
2021. SCANimate: weakly supervised learning of skinned clothed avatar networks//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville,USA: IEEE: 2885-2896 [DOI:
10.1109/cvpr46437.2021.00291], articleTitle=SCANimate: weakly supervised learning of skinned clothed avatar networks, refAbstract=null), Reference(id=1322960999355134835, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2026, volume=32, issue=2, pageStart=2061, pageEnd=2074, url=null, language=null, rfNumber=null, rfOrder=20, authorNames=Tang Y Z, Zhang Q J, Hou J H, journalName=IEEE Transactions on Visualization and Computer Graphics, refType=null, unstructuredReference=
Tang Y Z,
Zhang Q J and
Hou J H.
2026. HuGDiffusion: generalizable single-image human rendering via 3D Gaussian diffusion.
IEEE Transactions on Visualization and Computer Graphics,
32(2): 2061-2074 [DOI:
10.1109/TVCG.2025.3625230], articleTitle=HuGDiffusion: generalizable single-image human rendering via 3D Gaussian diffusion, refAbstract=null), Reference(id=1322960999426438004, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=3902, pageEnd=3912, url=null, language=null, rfNumber=null, rfOrder=21, authorNames=Wang W J, Ge Y T, Mei H Y, Cai Z G, Sun Q P, Wang Y J, journalName=null, refType=null, unstructuredReference=
Wang W J,
Ge Y T,
Mei H Y,
Cai Z G,
Sun Q P,
Wang Y J,
et al.
2023. Zolly: zoom focal length correctly for perspective-distorted human mesh reconstruction//Proceedings of 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris,France: IEEE: 3902-3912 [DOI:
10.1109/iccv51070.2023.00363], articleTitle=Zolly: zoom focal length correctly for perspective-distorted human mesh reconstruction, refAbstract=null), Reference(id=1322960999493546869, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=512, pageEnd=523, url=null, language=null, rfNumber=null, rfOrder=22, authorNames=Xiu Y L, Yang J L, Cao X, Tzionas D, Black M J, journalName=null, refType=null, unstructuredReference=
Xiu Y L,
Yang J L,
Cao X,
Tzionas D and
Black M J.
2023. ECON: explicit clothed humans optimized via normal integration//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver,Canada: IEEE: 512-523 [DOI:
10.1109/cvpr52729.2023.00057], articleTitle=ECON: explicit clothed humans optimized via normal integration, refAbstract=null), Reference(id=1322960999560655734, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=13286, pageEnd=13296, url=null, language=null, rfNumber=null, rfOrder=23, authorNames=Xiu Y L, Yang J L, Tzionas D, Black M J, journalName=null, refType=null, unstructuredReference=
Xiu Y L,
Yang J L,
Tzionas D and
Black M J.
2022. ICON: implicit clothed humans obtained from normals//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans,USA: IEEE: 13286-13296 [DOI:
10.1109/cvpr52688.2022.01294], articleTitle=ICON: implicit clothed humans obtained from normals, refAbstract=null), Reference(id=1322960999636153207, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=5742, pageEnd=5752, url=null, language=null, rfNumber=null, rfOrder=24, authorNames=Yu T, Zheng Z R, Guo K W, Liu P P, Dai Q H, Liu Y B, journalName=null, refType=null, unstructuredReference=
Yu T,
Zheng Z R,
Guo K W,
Liu P P,
Dai Q H and
Liu Y B.
2021. Function4D: real-time human volumetric capture from very sparse consumer RGBD sensors//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville,USA: IEEE: 5742-5752 [DOI:
10.1109/cvpr46437.2021.00569], articleTitle=Function4D: real-time human volumetric capture from very sparse consumer RGBD sensors, refAbstract=null), Reference(id=1322960999715844984, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2025, volume=42, issue=1, pageStart=300, pageEnd=306, url=null, language=null, rfNumber=null, rfOrder=25, authorNames=Zhang J, Ren Z P, Zhang R H, Yuan C, Zhai Y J, Yu Z Q, journalName=Application Research of Computers, refType=null, unstructuredReference=
Zhang J,
Ren Z P,
Zhang R H,
Yuan C,
Zhai Y J and
Yu Z Q.
2025. Hand-focused reconstruction of monocular RGB clothed humans.
Application Research of Computers,
42(1): 300-306, articleTitle=Hand-focused reconstruction of monocular RGB clothed humans, refAbstract=null), Reference(id=1322960999795536761, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2025, volume=42, issue=1, pageStart=300, pageEnd=306, url=null, language=null, rfNumber=null, rfOrder=26, authorNames=张冀, 任志鹏, 张荣华, 苑朝, 翟永杰, 余正秦, journalName=计算机应用研究, refType=null, unstructuredReference=张冀,任志鹏,张荣华,苑朝,翟永杰,余正秦.
2025. 单目RGB穿衣人体的手部精细化重建.
计算机应用研究,
42(1): 300-306 [DOI:
10.19734/j.issn.1001-3695.2024.02.0112], articleTitle=单目RGB穿衣人体的手部精细化重建, refAbstract=null), Reference(id=1322960999871034234, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2000, volume=22, issue=11, pageStart=1330, pageEnd=1334, url=null, language=null, rfNumber=null, rfOrder=27, authorNames=Zhang Z, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=
Zhang Z.
2000. A flexible new technique for camera calibration.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
22(11): 1330-1334 [DOI:
10.1109/34.888718], articleTitle=A flexible new technique for camera calibration, refAbstract=null), Reference(id=1322961001523590011, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=6, pageStart=3170, pageEnd=3184, url=null, language=null, rfNumber=null, rfOrder=28, authorNames=Zheng Z R, Yu T, Liu Y B, Dai Q H, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=
Zheng Z R,
Yu T,
Liu Y B and
Dai Q H.
2022. PaMIR: parametric model-conditioned implicit representation for image-based human reconstruction.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
44(6): 3170-3184 [DOI:
10.1109/tpami.2021.3050505], articleTitle=PaMIR: parametric model-conditioned implicit representation for image-based human reconstruction, refAbstract=null)], funds=[Fund(id=1322960997677413213, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, awardId=null, language=EN, fundingSource=National Key R&D Program of China(2023YFC3082100);National Natural Science Foundation of China (62501416);Science Fund for Distinguished Young Scholars of Tianjin,China (22JCJQJC00040);Tianjin Municipal Natural Science Foundation(24JCYBJC01300), fundOrder=null, country=null), Fund(id=1322960997748716382, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, awardId=null, language=CN, fundingSource=国家重点研发计划资助(2023YFC3082100);国家自然科学基金项目(62501416);天津市杰出青年科学基金项目(22JCJQJC00040);天津市自然科学基金项目(24JCYBJC01300), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322960994464576300, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, xref=null, ext=[AuthorCompanyExt(id=1322960994472964909, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, companyId=1322960994464576300, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Intellgence and Computing,Tianjin University,Tianjin 300354,China), AuthorCompanyExt(id=1322960994481353518, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, companyId=1322960994464576300, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=天津大学智能与计算学部,天津 300354)])], figs=[ArticleFig(id=1322960996343624525, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, label=Fig.1, caption=
Comparison of 3D human body reconstruction results from distorted images, figureFileSmall=i34MQxGuo3nFv2CKwkOkoQ==, figureFileBig=clmz1O3vSAxpBuUWb0YkuA==, tableContent=null), ArticleFig(id=1322960996427510606, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, label=图1, caption=
畸变图像的三维人体重建结果对比, figureFileSmall=i34MQxGuo3nFv2CKwkOkoQ==, figureFileBig=clmz1O3vSAxpBuUWb0YkuA==, tableContent=null), ArticleFig(id=1322960996616254287, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, label=Fig.2, caption=
Pipeline of the PerRec, figureFileSmall=glKad84/u1PC6j25edTfxQ==, figureFileBig=tRvIi0G2UFQP3TdgIONbow==, tableContent=null), ArticleFig(id=1322960996687557456, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, label=图2, caption=
PerRec方法框架示意图, figureFileSmall=glKad84/u1PC6j25edTfxQ==, figureFileBig=tRvIi0G2UFQP3TdgIONbow==, tableContent=null), ArticleFig(id=1322960996754666321, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, label=Fig.3, caption=
Qualitative results on the THuman2.0 and CustomHumans datasets, figureFileSmall=hZLpPJCC+qg0g0hTDIgZeg==, figureFileBig=GNkj6CXc68mOhi3vbkYXYg==, tableContent=null), ArticleFig(id=1322960996821775186, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, label=图3, caption=
在THuman2.0和CustomHumans数据集的定性结果, figureFileSmall=hZLpPJCC+qg0g0hTDIgZeg==, figureFileBig=GNkj6CXc68mOhi3vbkYXYg==, tableContent=null), ArticleFig(id=1322960996893078355, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, label=Fig.4, caption=
Comparative results of ablation experiments, figureFileSmall=C2s3zvoOmwyd+R0/r0FcCg==, figureFileBig=9JNALQRUkB+EW7GY+9RMLQ==, tableContent=null), ArticleFig(id=1322960996976964436, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, label=图4, caption=
消融实验对比结果, figureFileSmall=C2s3zvoOmwyd+R0/r0FcCg==, figureFileBig=9JNALQRUkB+EW7GY+9RMLQ==, tableContent=null), ArticleFig(id=1322960997048267605, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, label=Fig.5, caption=
Validation of hand region sampling strategy, figureFileSmall=u8HV6tnzwS2bnWAsuWW/Bw==, figureFileBig=mprEJd2IehHsMyOZ2BWNcw==, tableContent=null), ArticleFig(id=1322960997106987862, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, label=图5, caption=
手部区域采样策略有效性验证, figureFileSmall=u8HV6tnzwS2bnWAsuWW/Bw==, figureFileBig=mprEJd2IehHsMyOZ2BWNcw==, tableContent=null), ArticleFig(id=1322960997169902423, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, label=Table 1, caption=
Comparison on the THuman2.0 dataset, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 年份 | 倒角距离 /cm↓ | 法线 一致性↑ | 点到表面距离/cm↓ |
|---|
| PIFu | 2019 | 13.287 | 36.960 | 4.950 |
| PIFuhd | 2020 | 14.091 | 35.266 | 5.710 |
| PaMIR | 2022 | 28.885 | 31.203 | 5.612 |
| ICON | 2022 | 17.184 | 32.527 | 7.653 |
| ECON | 2023 | 17.963 | 30.295 | 7.855 |
| SITH | 2024 | 13.413 | 34.778 | 4.771 |
| FOFX | 2024 | 11.445 | 41.163 | 4.123 |
| PerRec | 2025 | 1.957 | 66.700 | 0.983 |
), ArticleFig(id=1322960997241205592, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, label=表1, caption=
在 THuman2.0 数据集上的比较
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 年份 | 倒角距离 /cm↓ | 法线 一致性↑ | 点到表面距离/cm↓ |
|---|
| PIFu | 2019 | 13.287 | 36.960 | 4.950 |
| PIFuhd | 2020 | 14.091 | 35.266 | 5.710 |
| PaMIR | 2022 | 28.885 | 31.203 | 5.612 |
| ICON | 2022 | 17.184 | 32.527 | 7.653 |
| ECON | 2023 | 17.963 | 30.295 | 7.855 |
| SITH | 2024 | 13.413 | 34.778 | 4.771 |
| FOFX | 2024 | 11.445 | 41.163 | 4.123 |
| PerRec | 2025 | 1.957 | 66.700 | 0.983 |
), ArticleFig(id=1322960997341868889, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, label=Table 2, caption=
Comparison on the CustomHumans dataset, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 年份 | 倒角距离 /cm↓ | 法线 一致性↑ | 点到表面距离/cm↓ |
|---|
| PIFu | 2019 | 13.888 | 36.982 | 4.903 |
| PIFuhd | 2020 | 12.803 | 37.178 | 5.579 |
| PaMIR | 2022 | 30.404 | 29.994 | 4.857 |
| ICON | 2022 | 14.856 | 34.546 | 6.934 |
| ECON | 2023 | 20.039 | 29.912 | 9.472 |
| SITH | 2024 | 13.912 | 34.524 | 4.653 |
| FOFX | 2024 | 8.433 | 39.300 | 6.103 |
| PerRec | 2025 | 2.336 | 72.603 | 0.919 |
), ArticleFig(id=1322960997421560666, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, label=表2, caption=
在 CustomHumans数据集上的比较
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 年份 | 倒角距离 /cm↓ | 法线 一致性↑ | 点到表面距离/cm↓ |
|---|
| PIFu | 2019 | 13.888 | 36.982 | 4.903 |
| PIFuhd | 2020 | 12.803 | 37.178 | 5.579 |
| PaMIR | 2022 | 30.404 | 29.994 | 4.857 |
| ICON | 2022 | 14.856 | 34.546 | 6.934 |
| ECON | 2023 | 20.039 | 29.912 | 9.472 |
| SITH | 2024 | 13.912 | 34.524 | 4.653 |
| FOFX | 2024 | 8.433 | 39.300 | 6.103 |
| PerRec | 2025 | 2.336 | 72.603 | 0.919 |
), ArticleFig(id=1322960997501252443, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=EN, label=Table 3, caption=
Ablation experiment quantitative results, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | Thuman2.0 | CustomHumans |
|---|
| 透视图像特征自适应 | 三维几何表征 | 伪多视角 | 倒角距离↓ | 法线一致性↑ | P-to-S↓ | 倒角距离↓ | 法线一致性↑ | P-to-S↓ |
|---|
| - | - | - | 12.837 | 46.312 | 4.864 | 12.058 | 45.874 | 4.518 |
| √ | - | - | 4.862 | 58.958 | 2.522 | 6.201 | 58.832 | 3.348 |
| - | √ | - | 3.316 | 65.264 | 2.038 | 4.308 | 68.331 | 1.902 |
| √ | √ | - | 2.221 | 66.700 | 1.030 | 2.360 | 71.635 | 0.946 |
| √ | √ | √ | 1.957 | 66.700 | 0.983 | 2.336 | 72.603 | 0.919 |
), ArticleFig(id=1322960997564167004, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322960992237400863, language=CN, label=表3, caption=
消融实验定量结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | Thuman2.0 | CustomHumans |
|---|
| 透视图像特征自适应 | 三维几何表征 | 伪多视角 | 倒角距离↓ | 法线一致性↑ | P-to-S↓ | 倒角距离↓ | 法线一致性↑ | P-to-S↓ |
|---|
| - | - | - | 12.837 | 46.312 | 4.864 | 12.058 | 45.874 | 4.518 |
| √ | - | - | 4.862 | 58.958 | 2.522 | 6.201 | 58.832 | 3.348 |
| - | √ | - | 3.316 | 65.264 | 2.038 | 4.308 | 68.331 | 1.902 |
| √ | √ | - | 2.221 | 66.700 | 1.030 | 2.360 | 71.635 | 0.946 |
| √ | √ | √ | 1.957 | 66.700 | 0.983 | 2.336 | 72.603 | 0.919 |
)], attaches=null, journal=Journal(id=1249023527618129992, delFlag=0, nameCn=中国图象图形学报, nameEn=Journal of Image and Graphics, nameHistory1=null, nameHistory2=null, issn=1006-8961, eissn=null, cn=11-3758, coden=CODEN ZTTXFZ, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=uirXtX858YS3zEpFXZttJA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Image and Graphics, journalRemark=null, publicationField=null, createdTime=1775720014721, updatedTime=1788951488513, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=Z, firstLetterEn=Z, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=uirXtX858YS3zEpFXZttJA==, picEn=bud7qaxfvWHeFsbyBTAiKQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1304520351199814396, language=CN, name=中国图象图形学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951488542, updatedTime=1788951488542, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=e6369def-2842-41d8, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-editor&redirect_uri=https%3A%2F%2Fcjigeditor.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=9ccec05b-6bd, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=1e8a31c8-5434-4f78, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304520351250146045, language=EN, name=Journal of Image and Graphics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951488554, updatedTime=1788951488554, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=e6369def-2842-41d8, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-editor&redirect_uri=https%3A%2F%2Fcjigeditor.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=9ccec05b-6bd, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=1e8a31c8-5434-4f78, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1249024232475115590, websiteList=[Website(id=1249025782459334881, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1249024232475115590, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN, language=CN, createTime=1775720552315, createBy=18614031015, updateTime=1775720586268, updateBy=18614031015, name=中国图象图形学报-中文, tplId=1146099689490845704, title=中国图象图形学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1249026166254928133, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=articleTextType, value=kx, createTime=1775720643819, updateTime=1775720643819, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166221373698, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=banner, value=null, createTime=1775720643811, updateTime=1775720643811, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166271705352, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=grayFlag, value=0, createTime=1775720643823, updateTime=1775720643823, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166212985089, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=logo, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/file/pic?fileId=TDRjKTHfgAnvFKZaDA70wA==, createTime=1775720643809, updateTime=1775720643809, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166288482570, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=minRunFlag, value=0, createTime=1775720643827, updateTime=1775720643827, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166246539524, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/file/pic, createTime=1775720643817, updateTime=1775720643817, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166280093961, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=silenceFlag, value=0, createTime=1775720643825, updateTime=1775720643825, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166233956611, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1775720643814, updateTime=1775720643814, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166259122438, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=themeColor, value=null, createTime=1775720643820, updateTime=1775720643820, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166267511047, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=themeStyle, value=null, createTime=1775720643822, updateTime=1775720643822, creator=18614031015, updator=18614031015)]), Website(id=1249025782681633001, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1249024232475115590, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN, language=EN, createTime=1775720552368, createBy=18614031015, updateTime=1775720607118, updateBy=18614031015, name=中国图象图形学报-英文, tplId=1146101810881728533, title=Journal of Image and Graphics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1249026195371786511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=articleTextType, value=kx, createTime=1775720650761, updateTime=1775720650761, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195355009292, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=banner, value=null, createTime=1775720650757, updateTime=1775720650757, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195392758034, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=grayFlag, value=0, createTime=1775720650766, updateTime=1775720650766, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195342426379, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=logo, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/file/pic?fileId=TDRjKTHfgAnvFKZaDA70wA==, createTime=1775720650754, updateTime=1775720650754, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195409535252, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=minRunFlag, value=0, createTime=1775720650770, updateTime=1775720650770, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195367592206, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/file/pic, createTime=1775720650760, updateTime=1775720650760, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195401146643, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=silenceFlag, value=0, createTime=1775720650768, updateTime=1775720650768, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195359203597, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1775720650758, updateTime=1775720650758, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195380175120, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=themeColor, value=null, createTime=1775720650763, updateTime=1775720650763, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195388563729, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=themeStyle, value=null, createTime=1775720650765, updateTime=1775720650765, creator=18614031015, updator=18614031015)])], journalTitle=中国图象图形学报, weixinUrl=null, journalUrl=https://www.cjig.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Image and Graphics, journalPhotoCn=uirXtX858YS3zEpFXZttJA==, journalPhotoEn=bud7qaxfvWHeFsbyBTAiKQ==, journalFirstLetter=Z, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/10.11834/jig.250413, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/10.11834/jig.250413, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/PDF/10.11834/jig.250413, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/PDF/10.11834/jig.250413, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1786809600000, fullTextJson=null, articleText=null, reference=null)