{"id":"https://openalex.org/W4415743516","doi":"https://doi.org/10.1109/tvcg.2025.3626741","title":"Consistent 3D Human Reconstruction From Monocular Video: Learning Correctable Appearance and Temporal Motion Priors","display_name":"Consistent 3D Human Reconstruction From Monocular Video: Learning Correctable Appearance and Temporal Motion Priors","publication_year":2025,"publication_date":"2025-10-31","ids":{"openalex":"https://openalex.org/W4415743516","doi":"https://doi.org/10.1109/tvcg.2025.3626741","pmid":"https://pubmed.ncbi.nlm.nih.gov/41171674"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2025.3626741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3626741","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100955523","display_name":"Shang Cheng","orcid":"https://orcid.org/0009-0005-5280-5788"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Shang","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","School of Software, Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0009-0005-5280-5788","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Software, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019986","display_name":"Liang An","orcid":"https://orcid.org/0000-0002-1028-3759"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang An","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1028-3759","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101835832","display_name":"Tingting Li","orcid":"https://orcid.org/0000-0001-7788-2003"},"institutions":[{"id":"https://openalex.org/I182722699","display_name":"Shenzhen Polytechnic University","ror":"https://ror.org/00d2w9g53","country_code":"CN","type":"education","lineage":["https://openalex.org/I182722699"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Li","raw_affiliation_strings":["School of Digital Media, Shenzhen Polytechnic University, Shenzhen, China","School of Digital Creation and Animation, Shenzhen Polytechnic University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Digital Media, Shenzhen Polytechnic University, Shenzhen, China","institution_ids":["https://openalex.org/I182722699"]},{"raw_affiliation_string":"School of Digital Creation and Animation, Shenzhen Polytechnic University, Shenzhen, China","institution_ids":["https://openalex.org/I182722699"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111205847","display_name":"Jiajun Zhang","orcid":"https://orcid.org/0009-0002-9712-9953"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Zhang","raw_affiliation_strings":["School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-9712-9953","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103102493","display_name":"Yuxiang Zhang","orcid":"https://orcid.org/0000-0002-8807-0825"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Zhang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8807-0825","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110766031","display_name":"Jidong Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Tian","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence AI Institute, Shanghai Jiao Tong University, Shanghai, China","MoE Key Lab of Artificial Intelligence AI Institute, Shanghai Jiao Tong University, ShangHai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence AI Institute, Shanghai Jiao Tong University, ShangHai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032875389","display_name":"Yebin Liu","orcid":"https://orcid.org/0000-0003-3215-0225"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yebin Liu","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3215-0225","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010767009","display_name":"Xubo Yang","orcid":"https://orcid.org/0000-0001-5378-4003"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xubo Yang","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","School of Software, Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0001-5378-4003","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Software, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22085406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"2","first_page":"1895","last_page":"1910"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.36980000138282776,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.36980000138282776,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.27469998598098755,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.0966000035405159,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.8399999737739563},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.7433000206947327},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5004000067710876},{"id":"https://openalex.org/keywords/motion-blur","display_name":"Motion blur","score":0.4627000093460083},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.45809999108314514},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.45750001072883606},{"id":"https://openalex.org/keywords/human-motion","display_name":"Human motion","score":0.39480000734329224},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.36719998717308044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86080002784729},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.8399999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8086000084877014},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7900999784469604},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7433000206947327},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5004000067710876},{"id":"https://openalex.org/C2777708103","wikidata":"https://www.wikidata.org/wiki/Q852589","display_name":"Motion blur","level":3,"score":0.4627000093460083},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.45809999108314514},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.39480000734329224},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.39149999618530273},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C44185422","wikidata":"https://www.wikidata.org/wiki/Q6002064","display_name":"Image-based modeling and rendering","level":3,"score":0.3547999858856201},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C116921373","wikidata":"https://www.wikidata.org/wiki/Q2816483","display_name":"Real-time rendering","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C36816356","wikidata":"https://www.wikidata.org/wiki/Q16911860","display_name":"3D rendering","level":3,"score":0.25119999051094055}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009038","descriptor_name":"Motion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009038","descriptor_name":"Motion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2025.3626741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3626741","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:41171674","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41171674","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8394430395","display_name":null,"funder_award_id":"62272305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8989291188","display_name":null,"funder_award_id":"62125107","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2133665775","https://openalex.org/W2793768642","https://openalex.org/W2962785568","https://openalex.org/W3153220274","https://openalex.org/W3176327543","https://openalex.org/W3202804820","https://openalex.org/W3203570626","https://openalex.org/W3215023725","https://openalex.org/W3215769467","https://openalex.org/W4214731463","https://openalex.org/W4285981761","https://openalex.org/W4295308256","https://openalex.org/W4310380504","https://openalex.org/W4312253380","https://openalex.org/W4312258500","https://openalex.org/W4312341890","https://openalex.org/W4312879788","https://openalex.org/W4312891300","https://openalex.org/W4385275452","https://openalex.org/W4385318467","https://openalex.org/W4386075716","https://openalex.org/W4386076679","https://openalex.org/W4390874306","https://openalex.org/W4390874575","https://openalex.org/W4400573547","https://openalex.org/W4400582194","https://openalex.org/W4402713112","https://openalex.org/W4402716022","https://openalex.org/W4402727151","https://openalex.org/W4402727211","https://openalex.org/W4402727576","https://openalex.org/W4402727915","https://openalex.org/W4402727930","https://openalex.org/W4402733569","https://openalex.org/W4402733571","https://openalex.org/W4402753521","https://openalex.org/W4402952507","https://openalex.org/W4404525447","https://openalex.org/W4404526070"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,29,37,88],"rendering":[3,23,38,62],"dynamic":[4,113],"humans":[5],"using":[6,116],"NeRF":[7],"and":[8,20,40,46,65,120,132],"3D":[9],"Gaussian":[10],"splatting":[11],"have":[12],"made":[13],"significant":[14],"progress,":[15],"leveraging":[16,107],"implicit":[17],"geometry":[18],"learning":[19],"image":[21],"appearance":[22],"to":[24,50,102],"create":[25],"digital":[26],"humans.":[27],"However,":[28],"monocular":[30],"video":[31],"rendering,":[32,115],"there":[33],"are":[34],"still":[35],"challenges":[36],"subtle":[39],"complex":[41],"motion":[42,81,104],"from":[43,63],"different":[44,93],"viewpoints":[45,67],"states,":[47],"primarily":[48],"due":[49],"the":[51,86,89,117],"imbalance":[52],"of":[53],"viewpoints.":[54,94],"Additionally,":[55],"ensuring":[56],"continuity":[57,105],"between":[58,92],"adjacent":[59,108],"frames":[60],"when":[61],"novel":[64],"free":[66],"remains":[68],"a":[69,79,98],"difficult":[70],"task.":[71],"To":[72],"address":[73],"these":[74],"challenges,":[75],"we":[76],"first":[77],"propose":[78],"pixel-level":[80],"correction":[82],"module":[83],"that":[84,124],"adjusts":[85],"errors":[87],"learned":[90],"representation":[91],"We":[95],"also":[96],"introduce":[97],"temporal":[99],"information-based":[100],"model":[101],"improve":[103],"by":[106],"frames.":[109],"Experimental":[110],"results":[111],"on":[112],"human":[114],"NeuMan,":[118],"ZJU-Mocap,":[119],"People-Snapshot":[121],"datasets,":[122],"demonstrate":[123],"our":[125],"method":[126],"outperforms":[127],"state-of-the-art":[128],"techniques":[129],"both":[130],"quantitatively":[131],"qualitatively.":[133]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-31T00:00:00"}