Article(id=1322961038274069206, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322960856543273127, articleNumber=null, orderNo=null, doi=10.11834/jig.250262, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1750780800000, receivedDateStr=2025-06-25, revisedDate=1766851200000, revisedDateStr=2025-12-28, acceptedDate=null, acceptedDateStr=null, onlineDate=1793348090952, onlineDateStr=2026-10-30, pubDate=1786809600000, pubDateStr=2026-08-16, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793348090952, onlineIssueDateStr=2026-10-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793348090952, creator=13701087609, updateTime=1793348090952, 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=2987, endPage=3000, ext={EN=ArticleExt(id=1322961038672528087, articleId=1322961038274069206, tenantId=1146029695717560320, journalId=1249024232475115590, language=EN, title=SMPL-guided human mesh reconstruction from incomplete point clouds, columnId=1249044008786400014, journalTitle=Journal of Image and Graphics, columnName=Image Understanding and Computer Vision, runingTitle=null, highlight=null, articleAbstract=
Objective Point cloud data has become a fundamental modality for human body modeling and pose estimation because of their explicit and direct representation of 3D geometric structure. In contrast to image-based or volumetric methods,point clouds preserve raw geometric information without discretization or projective distortion,making them especially suitable for capturing detailed surface characteristics. However,in practical acquisition scenarios,such as those using consumer-grade LiDAR sensors or depth cameras,point clouds often suffer from substantial local missing regions caused by sensor viewpoint limitations,object self-occlusions,and environmental obstructions. These incompleteness issues severely degrade the completeness and accuracy of reconstruction,posing substantial challenges for downstream tasks such as animation,virtual try-on,or motion analysis. Moreover,as unstructured data with irregular sampling,point clouds lack explicit connectivity information and exhibit permutation invariance. This inherent nature complicates the learning of continuous surface geometry and topological connectivity of the human body,which is essential for recovering plausible shapes and joint kinematics. Consequently,many existing approaches produce results with structural distortions,loss of fine-grained details,or inaccurate pose predictions,especially around articulated regions such as elbows,knees,and shoulders. Although recent deep learning models have made progress in processing point sets,they still struggle to maintain structural coherence and geometric fidelity when handling highly incomplete inputs under complex articulations. Therefore,methods that can infer missing geometry with strong contextual awareness and robust priors on human body shape and mobility are still needed.
Method To address these issues,we propose a novel method for human body reconstruction and point cloud completion by leveraging the topological prior of the skinned multiperson linear (SMPL) model. Our approach begins with a multiscale feature extraction module that incorporates per-point semantic awareness,enabling the network to capture fine-grained details and broader contextual information. This module employs a combination of local geometric feature learners and hierarchical aggregation layers to enhance the understanding of structural patterns at various scales. By integrating point-wise semantics during the feature learning process,it effectively encodes biological constraints into the representation,thereby generating more discriminative and context-aware point cloud features that better preserve the natural articulation and proportionality of human body shapes. Based on this enriched feature representation,the parametric mesh topology of the SMPL model guides the prediction of an initial deformable human skeleton. This step effectively regularizes the structural reasoning in missing or incomplete regions by introducing strong anatomical constraints,considerably alleviating topological ambiguities caused by severe data incompleteness,such as occlusions or large-scale scanning artifacts. The parametric model acts as a structural template that ensures biomechanically consistent predictions,even when large portions of the input are absent. As a result,the proposed framework maintains robust performance under challenging conditions,producing plausible human body proportions and pose-dependent shape variations that align with realistic anatomical properties. Furthermore,we design a vertex offset-aware refinement module that learns spatial residuals between the input sparse point cloud and the vertices of the predicted mesh through fine-grained alignment. This module operates in a hierarchical manner,progressively correcting geometric discrepancies across multiple resolution levels. It utilizes a cascaded residual learner that first handles large-scale deformations and then gradually focuses on recovering subtle surface details,such as muscle curves,soft-tissue contours,and joint depressions,which are often lost in coarse reconstruction stages. By iteratively aligning the predicted mesh with the observed points,our method achieves precise reconstruction of detailed surface geometry with remarkably improved geometric fidelity. The final output is a high-fidelity and anatomically plausible human body model,even when reconstructed from highly incomplete or noisy input data.
Result Experimental results demonstrate that the proposed method consistently outperforms existing approaches across the SURREAL and AMASS datasets,highlighting its effectiveness and broad applicability. On the SURREAL dataset,the method reduces the vertex-to-vertex reconstruction error by 4.6%,setting a new state-of-the-art with a remarkable pose estimation accuracy of 16.2 mm. This improvement not only reflects enhanced precision in capturing complex human motions but also indicates stronger alignment with ground-truth data. Similarly,on the AMASS dataset,the approach achieves a considerably lower Chamfer distance compared with current point cloud completion techniques,underscoring its ability to generate more geometrically consistent and structurally accurate reconstructions. These outcomes across diverse datasets further validate the strong generalization capacity and robustness of the proposed framework,suggesting its potential for real-world applications where reliability under varying conditions is critical.
Conclusion In conclusion,this work demonstrates that the effective integration of SMPL’s topological prior into the point cloud reconstruction pipeline leads to remarkable improvements in reconstruction quality. This approach proves especially advantageous when dealing with unstructured and highly incomplete input data,where traditional methods often struggle to produce plausible results. By leveraging the strong semantic and structural constraints provided by the SMPL model,our method enhances detail recovery,ensures improved shape consistency,and reduces artifacts in challenging scenarios. These findings highlight the value of incorporating semantic priors in geometric reconstruction tasks and suggest promising directions for future research in robust 3D understanding and generation.
, authors=Min Zhou, Ping An
*, Xinpeng Huang, Chao Yang, authorsList=Min Zhou, Ping An, Xinpeng Huang, Chao Yang, authorCompany=null, correspAuthors=Ping An, 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=1322961044133511914, articleId=1322961038274069206, tenantId=1146029695717560320, journalId=1249024232475115590, language=CN, title=SMPL引导的残缺点云人体重建, 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 点云在人体建模和姿态估计中应用广泛,但常因传感器视角和遮挡而局部缺失,影响重建完整性和精度。点云非结构化特性使模型难以准确建模几何结构和拓扑关系,导致失真、模糊或偏差。现有方法在处理严重缺失和复杂姿态时,仍面临结构完整性和几何精度不足的挑战。
方法 为此,本文提出一种基于蒙皮多人线性(skinned multi-person linear,SMPL)模型拓扑先验的人体重建与点云补全方法。通过引入逐点语义感知的多尺度特征提取机制,增强对局部几何结构的理解能力;在此基础上,利用SMPL的参数化网格先验构建初始人体形变骨架,有效引导缺失区域的结构推理,缓解因信息缺失带来的拓扑歧义;进一步设计顶点偏移感知优化模块,通过学习输入点云与预测网格间的空间残差,实现对人体表面细节的精细化修正。
结果 实验结果表明,所提方法在SURREAL(synthetic humans for real tasks)和AMASS(archive of motion capture as surface shapes)数据集上均优于现有方法。在SURREAL数据集上,顶点回归误差降低4.6%,姿态估计精度达当前最优的16.2 mm;在AMASS数据集上的倒角距离指标也显著优于现有点云补全算法,进一步验证了所提出框架的良好泛化性与鲁棒性。
结论 综上所述,将SMPL的拓扑先验有效融入点云重建流程,可显著提升重建质量,尤其在处理非结构化与不完整点云时展现出更强优势。
, authors=周敏, 安平
*, 黄新彭, 杨超, authorsList=周敏, 安平, 黄新彭, 杨超, authorCompany=null, correspAuthors=安平, authorNote=
, correspAuthorsNote=
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=2EJv8qHXzSZRI2fP3TPrCA==, magXml=BN2PpSrVTlVz8bcMoVmR7g==, pdfUrl=null, pdf=h0MdWKQ8qYccXxI8V1Yosg==, pdfFileSize=3369272, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=uRzZ/CJt+yo++ZIja63G3g==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=VRNDYygIIiJKLv/3YJkZog==, mapNumber=null, fund=null)}, authors=[Author(id=1322961044565525231, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=mzhou@shu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961044649411313, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, authorId=1322961044565525231, language=EN, stringName=Min Zhou, firstName=Min, middleName=null, lastName=Zhou, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961046280995570, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, authorId=1322961044565525231, language=CN, stringName=周敏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=上海大学通信与信息工程学院,上海 200444, bio={"content":"
周敏,女,硕士研究生,主要研究方向为人体重建和点云补全。E-mail:mzhou@shu.edu.cn
"}, bioImg=null, bioContent=
周敏,女,硕士研究生,主要研究方向为人体重建和点云补全。E-mail:mzhou@shu.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961044368392939, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, xref=null, ext=[AuthorCompanyExt(id=1322961044376781548, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, companyId=1322961044368392939, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China), AuthorCompanyExt(id=1322961044385170157, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, companyId=1322961044368392939, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=上海大学通信与信息工程学院,上海 200444)])]), Author(id=1322961046356493044, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=anping@shu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322961046444573430, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, authorId=1322961046356493044, language=EN, stringName=Ping An, firstName=Ping, middleName=null, lastName=An, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
*, address=School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961046515876599, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, authorId=1322961046356493044, language=CN, stringName=安平, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
*, address=上海大学通信与信息工程学院,上海 200444, bio={"content":"
安平,通信作者,女,教授,主要研究方向为图像处理、视频编码和视觉计算。E-mail:anping@shu.edu.cn
"}, bioImg=null, bioContent=
安平,通信作者,女,教授,主要研究方向为图像处理、视频编码和视觉计算。E-mail:anping@shu.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961044368392939, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, xref=null, ext=[AuthorCompanyExt(id=1322961044376781548, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, companyId=1322961044368392939, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China), AuthorCompanyExt(id=1322961044385170157, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, companyId=1322961044368392939, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=上海大学通信与信息工程学院,上海 200444)])]), Author(id=1322961046612345593, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=huangxinpeng@shu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961046704620283, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, authorId=1322961046612345593, language=EN, stringName=Xinpeng Huang, firstName=Xinpeng, middleName=null, lastName=Huang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961046775923452, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, authorId=1322961046612345593, language=CN, stringName=黄新彭, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=上海大学通信与信息工程学院,上海 200444, bio={"content":"
黄新彭,男,副教授,主要研究方向为光场数据压缩与处理。E-mail:huangxinpeng@shu.edu.cn
"}, bioImg=null, bioContent=
黄新彭,男,副教授,主要研究方向为光场数据压缩与处理。E-mail:huangxinpeng@shu.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961044368392939, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, xref=null, ext=[AuthorCompanyExt(id=1322961044376781548, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, companyId=1322961044368392939, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China), AuthorCompanyExt(id=1322961044385170157, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, companyId=1322961044368392939, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=上海大学通信与信息工程学院,上海 200444)])]), Author(id=1322961046868198142, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yangchaoie@shu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961047027581696, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, authorId=1322961046868198142, language=EN, stringName=Chao Yang, firstName=Chao, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961047090496257, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, authorId=1322961046868198142, language=CN, stringName=杨超, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=上海大学通信与信息工程学院,上海 200444, bio={"content":"
杨超,男,副教授,主要研究方向为视频编码与质量评价。E-mail:yangchaoie@shu.edu.cn
"}, bioImg=null, bioContent=
杨超,男,副教授,主要研究方向为视频编码与质量评价。E-mail:yangchaoie@shu.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961044368392939, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, xref=null, ext=[AuthorCompanyExt(id=1322961044376781548, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, companyId=1322961044368392939, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China), AuthorCompanyExt(id=1322961044385170157, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, companyId=1322961044368392939, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=上海大学通信与信息工程学院,上海 200444)])])], keywords=[Keyword(id=1322961047212131074, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, orderNo=1, keyword=point clouds reconstruction), Keyword(id=1322961047279239939, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, orderNo=2, keyword=shape completion), Keyword(id=1322961047518315268, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, orderNo=3, keyword=pose estimation), Keyword(id=1322961047589618437, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, orderNo=4, keyword=multi-scale feature), Keyword(id=1322961047660921606, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, orderNo=5, keyword=SMPL topological prior), Keyword(id=1322961047753196295, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, orderNo=1, keyword=点云重建), Keyword(id=1322961047883219720, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, orderNo=2, keyword=形状补全), Keyword(id=1322961047992271625, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, orderNo=3, keyword=姿态估计), Keyword(id=1322961048302650122, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, orderNo=4, keyword=多尺度特征), Keyword(id=1322961048369758987, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, orderNo=5, keyword=SMPL拓扑先验)], refs=[Reference(id=1322961052585034531, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2308.14492.pdf, language=null, rfNumber=null, rfOrder=0, authorNames=Cai Z G, Pan L, Wei C, Yin W Q, Hong F Z, Zhang M Y, journalName=null, refType=null, unstructuredReference=
Cai Z G,
Pan L,
Wei C,
Yin W Q,
Hong F Z,
Zhang M Y,
et al.
2023. PointHPS: cascaded 3D human pose and shape estimation from point clouds [EB/OL]. [2025-06-25]., articleTitle=PointHPS: cascaded 3D human pose and shape estimation from point clouds, refAbstract=null), Reference(id=1322961052647949092, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=235, pageEnd=251, url=null, language=null, rfNumber=null, rfOrder=1, authorNames=Groueix T, Fisher M, Kim V G, Russell B C, Aubry M, journalName=null, refType=null, unstructuredReference=
Groueix T,
Fisher M,
Kim V G,
Russell B C and
Aubry M.
2018. 3D-CODED: 3D correspondences by deep deformation//Proceedings of the 15th European Conference on Computer Vision Munich. Munich,Germany: Springer: 235-251 [DOI:
10.1007/978-3-030-01216-8_15], articleTitle=3D-CODED: 3D correspondences by deep deformation, refAbstract=null), Reference(id=1322961052736029477, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=5430, pageEnd=5440, url=null, language=null, rfNumber=null, rfOrder=2, authorNames=Jiang H Y, Cai J F, Zheng J M, journalName=null, refType=null, unstructuredReference=
Jiang H Y,
Cai J F and
Zheng J M.
2019. Skeleton-aware 3D human shape reconstruction from point clouds//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul,Korea (South): IEEE: 5430-5440 [DOI:
10.1109/ICCV.2019.00553], articleTitle=Skeleton-aware 3D human shape reconstruction from point clouds, refAbstract=null), Reference(id=1322961052907995942, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=12880, pageEnd=12889, url=null, language=null, rfNumber=null, rfOrder=3, authorNames=Kim J, Gwon M G, Park H, Kwon H, Um G M, Kim W, journalName=null, refType=null, unstructuredReference=
Kim J,
Gwon M G,
Park H,
Kwon H,
Um G M and
Kim W.
2023. Sampling is matter: point-guided 3D human mesh reconstruction//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver,Canada: IEEE: 12880-12889 [DOI:
10.1109/CVPR52729.2023.01238], articleTitle=Sampling is matter: point-guided 3D human mesh reconstruction, refAbstract=null), Reference(id=1322961052975104807, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=20470, pageEnd=20480, url=null, language=null, rfNumber=null, rfOrder=4, authorNames=Li J L, Zhang J Y, Wang Z Y, Shen S Q, Wen C L, Ma Y X, journalName=null, refType=null, unstructuredReference=
Li J L,
Zhang J Y,
Wang Z Y,
Shen S Q,
Wen C L,
Ma Y X,
et al.
2022. LiDARCap: long-range markerless 3D human motion capture with lidar point clouds//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans,USA: IEEE: 20470-20480 [DOI:
10.1109/CVPR52688.2022.01985], articleTitle=LiDARCap: long-range markerless 3D human motion capture with lidar point clouds, refAbstract=null), Reference(id=1322961053046407976, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=5, authorNames=Li Z Q, journalName=Research on 3D Human Body Reconstruction Algorithm Based on Parametric Model, refType=null, unstructuredReference=
Li Z Q.
2024.
Research on 3D Human Body Reconstruction Algorithm Based on Parametric Model. Shanghai: East China Normal University, articleTitle=null, refAbstract=null), Reference(id=1322961053109322537, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=6, authorNames=李子清, journalName=基于参数化模型的三维人体重建算法研究, refType=null, unstructuredReference=李子清.
2024.
基于参数化模型的三维人体重建算法研究. 上海: 华东师范大学 [DOI:
10.27149/d.cnki.ghdsu.2024.003820], articleTitle=null, refAbstract=null), Reference(id=1322961053172237098, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1954, pageEnd=1963, url=null, language=null, rfNumber=null, rfOrder=7, authorNames=Lin K, Wang L J, Liu Z C, journalName=null, refType=null, unstructuredReference=
Lin K,
Wang L J and
Liu Z C.
2021. End-to-end human pose and mesh reconstruction with transformers//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville,USA: IEEE: 1954-1963 [DOI:
10.1109/CVPR46437.2021.00199], articleTitle=End-to-end human pose and mesh reconstruction with transformers, refAbstract=null), Reference(id=1322961053226763051, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=955, pageEnd=964, url=null, language=null, rfNumber=null, rfOrder=8, authorNames=Liu G Z, Rong Y, Sheng L, journalName=null, refType=null, unstructuredReference=
Liu G Z,
Rong Y and
Sheng L.
2021. VoteHMR: occlusion-aware voting network for robust 3D human mesh recovery from partial point clouds//Proceedings of the 29th ACM International Conference on Multimedia. Chengdu,China: ACM: 955-964 [DOI:
10.1145/3474085.3475309], articleTitle=VoteHMR: occlusion-aware voting network for robust 3D human mesh recovery from partial point clouds, refAbstract=null), Reference(id=1322961053298066220, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2015, volume=34, issue=6, pageStart=null, pageEnd=248, url=null, language=null, rfNumber=null, rfOrder=9, authorNames=Loper M, Mahmood N, Romero J, Pons-Moll G, Black M J, journalName=ACM Transactions on Graphics (TOG), 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 (TOG),
34(6): #248 [DOI:
10.1145/2816795.2818013], articleTitle=SMPL: a skinned multi-person linear model, refAbstract=null), Reference(id=1322961053386146605, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=5105, pageEnd=5114, url=null, language=null, rfNumber=null, rfOrder=10, authorNames=Qi C R, Yi L, Su H, Guibas L J, journalName=null, refType=null, unstructuredReference=
Qi C R,
Yi L,
Su H and
Guibas L J.
2017. PointNet++: deep hierarchical feature learning on point sets in a metric space//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach,USA: Curran Associates Inc.: 5105-5114, articleTitle=PointNet++: deep hierarchical feature learning on point sets in a metric space, refAbstract=null), Reference(id=1322961053461644078, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=725, pageEnd=741, url=null, language=null, rfNumber=null, rfOrder=11, authorNames=Ranjan A, Bolkart T, Sanyal S, Black M J, journalName=null, refType=null, unstructuredReference=
Ranjan A,
Bolkart T,
Sanyal S and
Black M J.
2018. Generating 3D faces using convolutional mesh autoencoders//Proceedings of the 15th European Conference on Computer Vision. Munich,Germany: Springer: 725-741 [DOI:
10.1007/978-3-030-01219-9_43], articleTitle=Generating 3D faces using convolutional mesh autoencoders, refAbstract=null), Reference(id=1322961053528752943, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=1281, pageEnd=1291, url=null, language=null, rfNumber=null, rfOrder=12, authorNames=Ren Y M, Han X, Zhao C F, Wang J Y, Xu L, Yu J Y, journalName=null, refType=null, unstructuredReference=
Ren Y M,
Han X,
Zhao C F,
Wang J Y,
Xu L,
Yu J Y,
et al.
2024. LiveHPS: LiDAR-based scene-level human pose and shape estimation in free environment//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle,USA: IEEE: 1281-1291 [DOI:
10.1109/CVPR52733.2024.00128], articleTitle=LiveHPS: LiDAR-based scene-level human pose and shape estimation in free environment, refAbstract=null), Reference(id=1322961055097422640, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2023, volume=29, issue=5, pageStart=2337, pageEnd=2347, url=null, language=null, rfNumber=null, rfOrder=13, authorNames=Ren Y M, Zhao C F, He Y N, Cong P S, Liang H, Yu J Y, journalName=IEEE Transactions on Visualization and Computer Graphics, refType=null, unstructuredReference=
Ren Y M,
Zhao C F,
He Y N,
Cong P S,
Liang H,
Yu J Y,
et al.
2023. LiDAR-aid inertial poser: large-scale human motion capture by sparse inertial and LiDAR sensors.
IEEE Transactions on Visualization and Computer Graphics,
29(5): 2337-2347 [DOI:
10.1109/TVCG.2023.3247088], articleTitle=LiDAR-aid inertial poser: large-scale human motion capture by sparse inertial and LiDAR sensors, refAbstract=null), Reference(id=1322961055168725809, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=4676, pageEnd=4685, url=null, language=null, rfNumber=null, rfOrder=14, authorNames=Rong Y, Zhou H R, Yuan L X, Mei C, Wang J H, Lu T, journalName=null, refType=null, unstructuredReference=
Rong Y,
Zhou H R,
Yuan L X,
Mei C,
Wang J H and
Lu T.
2024. CRA-PCN: point cloud completion with intra-and inter-level cross-resolution transformers//Proceedings of the 38th AAAI Conference on Artificial Intelligence. Vancouver,Canada: AAAI Press: 4676-4685 [DOI:
10.1609/aaai.v38i5.28268], articleTitle=CRA-PCN: point cloud completion with intra-and inter-level cross-resolution transformers, refAbstract=null), Reference(id=1322961055235834674, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=15, authorNames=Shao M Z, journalName=Implicit Function Based Human Surface Reconstructionwith Single Images, refType=null, unstructuredReference=
Shao M Z.
2023.
Implicit Function Based Human Surface Reconstructionwith Single Images. Hefei: Anhui University, articleTitle=null, refAbstract=null), Reference(id=1322961055307137843, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=16, authorNames=邵明正, journalName=基于隐式函数的单幅图像人体表面重建技术研究, refType=null, unstructuredReference=邵明正.
2023.
基于隐式函数的单幅图像人体表面重建技术研究. 合肥: 安徽大学 [DOI:
10.26917/d.cnki.ganhu.2023.001442], articleTitle=null, refAbstract=null), Reference(id=1322961055424578356, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2410.04889.pdf, language=null, rfNumber=null, rfOrder=17, authorNames=Vasilikopoulos N, Drosakis D, Argyros A, journalName=null, refType=null, unstructuredReference=
Vasilikopoulos N,
Drosakis D and
Argyros A.
2024. D-PoSE: depth as an intermediate representation for 3D human pose and shape estimation [EB/OL]. [2025-06-25]., articleTitle=D-PoSE: depth as an intermediate representation for 3D human pose and shape estimation, refAbstract=null), Reference(id=1322961055491687221, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=7273, pageEnd=7282, url=null, language=null, rfNumber=null, rfOrder=18, authorNames=Wang K K, Xie J, Zhang G F, Liu L, Yang J, journalName=null, refType=null, unstructuredReference=
Wang K K,
Xie J,
Zhang G F,
Liu L and
Yang J.
2020. Sequential 3D human pose and shape estimation from point clouds//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle,USA: IEEE: 7273-7282 [DOI:
10.1109/CVPR42600.2020.00730], articleTitle=Sequential 3D human pose and shape estimation from point clouds, refAbstract=null), Reference(id=1322961055562990390, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=1, pageStart=852, pageEnd=867, url=null, language=null, rfNumber=null, rfOrder=19, authorNames=Wen X, Xiang P, Han Z Z, Cao Y P, Wan P F, Zheng W, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=
Wen X,
Xiang P,
Han Z Z,
Cao Y P,
Wan P F,
Zheng W,
et al.
2023. PMP-Net++: point cloud completion by transformer-enhanced multi-step point moving paths.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
45(1): 852-867 [DOI:
10.1109/TPAMI.2022.3159003], articleTitle=PMP-Net++: point cloud completion by transformer-enhanced multi-step point moving paths, refAbstract=null), Reference(id=1322961055634293559, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=4746, pageEnd=4756, url=null, language=null, rfNumber=null, rfOrder=20, authorNames=Yang W D, Jiang Z H, Zhao S, Zhou S K, journalName=null, refType=null, unstructuredReference=
Yang W D,
Jiang Z H,
Zhao S and
Zhou S K.
2025. PostoMETRO: pose token enhanced mesh transformer for robust 3D human mesh recovery//Proceedings of 2025 IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson,USA: IEEE: 4746-4756 [DOI:
10.1109/WACV61041.2025.00465], articleTitle=PostoMETRO: pose token enhanced mesh transformer for robust 3D human mesh recovery, refAbstract=null), Reference(id=1322961055718179640, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=206, pageEnd=215, url=null, language=null, rfNumber=null, rfOrder=21, authorNames=Yang Y Q, Feng C, Shen Y R, Tian D, journalName=null, refType=null, unstructuredReference=
Yang Y Q,
Feng C,
Shen Y R and
Tian D.
2018. FoldingNet: point cloud auto-encoder via deep grid deformation//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City,USA: IEEE: 206-215 [DOI:
10.1109/CVPR.2018.00029], articleTitle=FoldingNet: point cloud auto-encoder via deep grid deformation, refAbstract=null), Reference(id=1322961055781094202, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2021, volume=26, issue=12, pageStart=2918, pageEnd=2930, url=null, language=null, rfNumber=null, rfOrder=22, authorNames=Yao L, Zhang Y A, Zhang M X, Wan Y, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=
Yao L,
Zhang Y A,
Zhang M X and
Wan Y.
2021. The impact of joint axis angle prior on the results of 3D human body reconstruction.
Journal of Image and Graphics,
26(12): 2918-2930, articleTitle=The impact of joint axis angle prior on the results of 3D human body reconstruction, refAbstract=null), Reference(id=1322961055860785979, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2021, volume=26, issue=12, pageStart=2918, pageEnd=2930, url=null, language=null, rfNumber=null, rfOrder=23, authorNames=姚砺, 张幼安, 张梦雪, 万燕, journalName=中国图象图形学报, refType=null, unstructuredReference=姚砺,张幼安,张梦雪,万燕.
2021. 关节轴角先验对3维人体重建结果的影响.
中国图象图形学报,
26(12): 2918-2930 [DOI:
10.11834/jig.200348], articleTitle=关节轴角先验对3维人体重建结果的影响, refAbstract=null), Reference(id=1322961055927894844, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=12478, pageEnd=12487, url=null, language=null, rfNumber=null, rfOrder=24, authorNames=Yu X M, Rao Y M, Wang Z Y, Liu Z Y, Lu J W, Zhou J, journalName=null, refType=null, unstructuredReference=
Yu X M,
Rao Y M,
Wang Z Y,
Liu Z Y,
Lu J W and
Zhou J.
2021. PoinTr: diverse point cloud completion with geometry-aware transformers//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision. Montreal,Canada: IEEE: 12478-12487 [DOI:
10.1109/ICCV48922.2021.01227], articleTitle=PoinTr: diverse point cloud completion with geometry-aware transformers, refAbstract=null), Reference(id=1322961055999198013, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=728, pageEnd=737, url=null, language=null, rfNumber=null, rfOrder=25, authorNames=Yuan W T, Khot T, Held D, Mertz C, Hebert M, journalName=null, refType=null, unstructuredReference=
Yuan W T,
Khot T,
Held D,
Mertz C and
Hebert M.
2018. PCN: point completion network//Proceedings of 2018 International Conference on 3D Vision. Verona,Italy: IEEE: 728-737 [DOI:
10.1109/3DV.2018.00088], articleTitle=PCN: point completion network, refAbstract=null), Reference(id=1322961056200524606, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=416, pageEnd=432, url=null, language=null, rfNumber=null, rfOrder=26, authorNames=Zhou H R, Cao Y, Chu W Q, Zhu J W, Lu T, Tai Y, journalName=null, refType=null, unstructuredReference=
Zhou H R,
Cao Y,
Chu W Q,
Zhu J W,
Lu T,
Tai Y,
et al.
2022. SeedFormer: patch seeds based point cloud completion with upsample transformer//Proceedings of the 17th European Conference on Computer Vision. Tel Aviv,Israel: Springer: 416-432 [DOI:
10.1007/978-3-031-20062-5_24], articleTitle=SeedFormer: patch seeds based point cloud completion with upsample transformer, refAbstract=null)], funds=[Fund(id=1322961052324987681, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, awardId=null, language=EN, fundingSource=National Natural Science Foundation of China(62471284,62020106011,62371278,62371279);Shanghai Municipal Natural Science Foundation(22ZR1424300), fundOrder=null, country=null), Fund(id=1322961052484371234, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, awardId=null, language=CN, fundingSource=国家自然科学基金项目(62471284,62020106011,62371278,62371279);上海自然科学基金项目(22ZR1424300), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322961044368392939, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, xref=null, ext=[AuthorCompanyExt(id=1322961044376781548, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, companyId=1322961044368392939, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China), AuthorCompanyExt(id=1322961044385170157, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, companyId=1322961044368392939, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=上海大学通信与信息工程学院,上海 200444)])], figs=[ArticleFig(id=1322961048747246348, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, label=Fig.1, caption=
Flowchart of point clouds human reconstruction algorithm with SMPL topology-prior, figureFileSmall=GOK6lFQElAoW+5nG7OO/4w==, figureFileBig=uRzZ/CJt+yo++ZIja63G3g==, tableContent=null), ArticleFig(id=1322961048822743821, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, label=图1, caption=
基于SMPL拓扑先验的点云人体重建算法流程图, figureFileSmall=GOK6lFQElAoW+5nG7OO/4w==, figureFileBig=uRzZ/CJt+yo++ZIja63G3g==, tableContent=null), ArticleFig(id=1322961050747929358, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, label=Fig.2, caption=
Diagram of multi-scale encoder module, figureFileSmall=C8klzdFbiR0eMvH/GIb4wg==, figureFileBig=sHCgM5HI0lCoGiFCxK56XA==, tableContent=null), ArticleFig(id=1322961050810843919, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, label=图2, caption=
多尺度编码模块结构图, figureFileSmall=C8klzdFbiR0eMvH/GIb4wg==, figureFileBig=sHCgM5HI0lCoGiFCxK56XA==, tableContent=null), ArticleFig(id=1322961050877952784, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, label=Fig.3, caption=
Diagram of feature enhance module, figureFileSmall=q9iGCfv+JjYq/z59dpdPdA==, figureFileBig=I9CNFua9Mqg/ykXIBGIJdg==, tableContent=null), ArticleFig(id=1322961050945061649, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, label=图3, caption=
特征增强模块结构图, figureFileSmall=q9iGCfv+JjYq/z59dpdPdA==, figureFileBig=I9CNFua9Mqg/ykXIBGIJdg==, tableContent=null), ArticleFig(id=1322961051012170514, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, label=Fig.4, caption=
Diagram of topology-prior vertices regression module ((a) Transformer block; (b) Transformer-encoder layer ), figureFileSmall=WbBT16IAcx5vC8Ja0hwVow==, figureFileBig=55/MVsSu5C/6yDEri5bGwQ==, tableContent=null), ArticleFig(id=1322961051242857235, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, label=图4, caption=
拓扑先验顶点回归模块结构图, figureFileSmall=WbBT16IAcx5vC8Ja0hwVow==, figureFileBig=55/MVsSu5C/6yDEri5bGwQ==, tableContent=null), ArticleFig(id=1322961051305771796, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, label=Fig.5, caption=
Diagram of offset-aware refine module ((a) offset-aware refine module; (b) center point cloud;, figureFileSmall=FvMJTjzcdZFsAPILZiIwvA==, figureFileBig=U+L2oIftrgxs03ibiwoCyw==, tableContent=null), ArticleFig(id=1322961051385463573, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, label=图5, caption=
偏移感知优化模块结构图(c) coarse regression point cloud; (d) refined point cloud; (e) visual overlay comparison point cloud)
, figureFileSmall=FvMJTjzcdZFsAPILZiIwvA==, figureFileBig=U+L2oIftrgxs03ibiwoCyw==, tableContent=null), ArticleFig(id=1322961051452572438, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, label=Fig.6, caption=
SMPL mesh reconstruction results on SURREAL test set, figureFileSmall=HkoP0yWjXC2s+MbaNXuEUA==, figureFileBig=zp91SqMI19GrOlK+jSovfg==, tableContent=null), ArticleFig(id=1322961051523875608, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, label=图6, caption=
在SURREAL测试集SMPL网格重建结果((a) partial point cloud;(b) reconstruction result;
(c) SMPL mesh)
, figureFileSmall=HkoP0yWjXC2s+MbaNXuEUA==, figureFileBig=zp91SqMI19GrOlK+jSovfg==, tableContent=null), ArticleFig(id=1322961051611955993, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, label=Fig.7, caption=
Reconstruction results on SURREAL test set, figureFileSmall=S12gjZOoSatgOZsfPYkjCw==, figureFileBig=xIjgHL1p++ecyknbOpWcSQ==, tableContent=null), ArticleFig(id=1322961051695842074, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, label=图7, caption=
在SURREAL测试集的重建结果, figureFileSmall=S12gjZOoSatgOZsfPYkjCw==, figureFileBig=xIjgHL1p++ecyknbOpWcSQ==, tableContent=null), ArticleFig(id=1322961051758756635, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, label=Table 1, caption=
3D human reconstruction experimental results on SURREAL dataset, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | 方法 | MPVE↓ | MPJPE↓ | PA-MPJPE↓ |
|---|
| 深度图点云 | Jiang等人(2019) | 80.5 | - | - |
| 3DCODED(Groueix等,2018) | 41.8 | 38.5 | 33.1 |
| Sequential (Param.)(Wang等,2020) | 24.3 | 21.9 | 18.2 |
| Sequential (Non Param.)(Wang等,2020) | 21.2 | 18.7 | 13.4 |
| VoteHMR(Liu等,2021) | 20.2 | 17.7 | 12.2 |
| PointHPS(Cai等,2023) | 19.6 | - | - |
| 雷达点云 | LiDARCap(Li等,2022) | 42.8 | 54.1 | - |
| LIP(Ren等,2023) | 31.7 | 42.4 | - |
| LiveHPS(Ren等,2024) | 30.8 | 24.0 | - |
| 本文-512 | 27.0 | 20.9 | 15.3 |
| 本文 | 18.7(19.5) | 16.2 | 12.0 |
), ArticleFig(id=1322961051834254108, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, label=表1, caption=
在SURREAL数据集上进行三维人体重建的实验结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | 方法 | MPVE↓ | MPJPE↓ | PA-MPJPE↓ |
|---|
| 深度图点云 | Jiang等人(2019) | 80.5 | - | - |
| 3DCODED(Groueix等,2018) | 41.8 | 38.5 | 33.1 |
| Sequential (Param.)(Wang等,2020) | 24.3 | 21.9 | 18.2 |
| Sequential (Non Param.)(Wang等,2020) | 21.2 | 18.7 | 13.4 |
| VoteHMR(Liu等,2021) | 20.2 | 17.7 | 12.2 |
| PointHPS(Cai等,2023) | 19.6 | - | - |
| 雷达点云 | LiDARCap(Li等,2022) | 42.8 | 54.1 | - |
| LIP(Ren等,2023) | 31.7 | 42.4 | - |
| LiveHPS(Ren等,2024) | 30.8 | 24.0 | - |
| 本文-512 | 27.0 | 20.9 | 15.3 |
| 本文 | 18.7(19.5) | 16.2 | 12.0 |
), ArticleFig(id=1322961051909751581, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, label=Table 2, caption=
3D human point clouds completion experimental results on AMASS dataset, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | CD-L1/×10-3↓ | F1-Score↑ |
|---|
| FoldingNet(Yang等,2018) | 31.16 | 0.11 |
| PCN(Yuan等,2018) | 23.13 | 0.21 |
| PoinTr(Yu等,2021) | 25.12 | 0.28 |
| Pmp-net++(Wen等,2023) | 18.69 | 0.31 |
| Seedformer(Zhou等,2022) | 16.92 | 0.49 |
| CRA-PCN(Rong等,2024) | 10.28 | 0.55 |
| 本文 | 6.27 | 0.61 |
), ArticleFig(id=1322961052064940830, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, label=表2, caption=
在AMASS数据集上进行三维人体点云补全的实验结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | CD-L1/×10-3↓ | F1-Score↑ |
|---|
| FoldingNet(Yang等,2018) | 31.16 | 0.11 |
| PCN(Yuan等,2018) | 23.13 | 0.21 |
| PoinTr(Yu等,2021) | 25.12 | 0.28 |
| Pmp-net++(Wen等,2023) | 18.69 | 0.31 |
| Seedformer(Zhou等,2022) | 16.92 | 0.49 |
| CRA-PCN(Rong等,2024) | 10.28 | 0.55 |
| 本文 | 6.27 | 0.61 |
), ArticleFig(id=1322961052148826911, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=EN, label=Table 3, caption=
Ablation study of the semantic,multi-scale encoder,and offset-aware refine modules, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 残缺 | 语义编码 | 多尺度 | 偏移 感知 | MPVE↓ | MPJPE↓ |
|---|
| A | × | × | × | × | 9.3 | 6.6 |
| B | √ | × | × | × | 32.7 | 24.2 |
| C | √ | √ | × | × | 23.1 | 17.6 |
| D | √ | √ | √ | × | 22.8 | 17.1 |
| E | √ | √ | √ | √ | 19.5 | 16.2 |
), ArticleFig(id=1322961052215935776, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961038274069206, language=CN, label=表3, caption=
语义、多尺度编码和偏移感知优化模块的消融实验
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 残缺 | 语义编码 | 多尺度 | 偏移 感知 | MPVE↓ | MPJPE↓ |
|---|
| A | × | × | × | × | 9.3 | 6.6 |
| B | √ | × | × | × | 32.7 | 24.2 |
| C | √ | √ | × | × | 23.1 | 17.6 |
| D | √ | √ | √ | × | 22.8 | 17.1 |
| E | √ | √ | √ | √ | 19.5 | 16.2 |
)], 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.250262, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/10.11834/jig.250262, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/PDF/10.11834/jig.250262, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/PDF/10.11834/jig.250262, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1786809600000, fullTextJson=null, articleText=null, reference=null)