{"id":"https://openalex.org/W4415310631","doi":"https://doi.org/10.1109/iccv51701.2025.01028","title":"Diffuman4D: 4D Consistent Human View Synthesis From Sparse-View Videos With Spatio-Temporal Diffusion Models","display_name":"Diffuman4D: 4D Consistent Human View Synthesis From Sparse-View Videos With Spatio-Temporal Diffusion Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415310631","doi":"https://doi.org/10.1109/iccv51701.2025.01028"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.13344","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yudong Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudong Jin","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073087748","display_name":"Sida Peng","orcid":"https://orcid.org/0000-0001-6546-4525"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sida Peng","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641599","display_name":"Xuan Wang","orcid":"https://orcid.org/0000-0001-9084-532X"},"institutions":[{"id":"https://openalex.org/I4210121321","display_name":"ANT Foundation Italy Onlus","ror":"https://ror.org/02zf60s91","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210121321"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Xuan Wang","raw_affiliation_strings":["Ant Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Research","institution_ids":["https://openalex.org/I4210121321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012942103","display_name":"Tao Xie","orcid":"https://orcid.org/0000-0002-7489-6861"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Xie","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112435934","display_name":"Zhen Xu","orcid":"https://orcid.org/0000-0003-0692-3749"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Xu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104479074","display_name":"Yifan Yang","orcid":"https://orcid.org/0009-0002-6868-1220"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103003762","display_name":"Yujun Shen","orcid":"https://orcid.org/0000-0003-3801-6705"},"institutions":[{"id":"https://openalex.org/I4210121321","display_name":"ANT Foundation Italy Onlus","ror":"https://ror.org/02zf60s91","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210121321"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Yujun Shen","raw_affiliation_strings":["Ant Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Research","institution_ids":["https://openalex.org/I4210121321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111954079","display_name":"Hujun Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hujun Bao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101814482","display_name":"Xiaowei Zhou","orcid":"https://orcid.org/0000-0003-1926-5597"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Zhou","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11047","last_page":"11057"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9969000220298767,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9969000220298767,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9907000064849854,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9817000031471252,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6814000010490417},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.6771000027656555},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6340000033378601},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5127000212669373},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5012999773025513},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.47940000891685486},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47620001435279846},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4731999933719635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781499981880188},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6814000010490417},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.6771000027656555},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6340000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050999760627747},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5593000054359436},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5012999773025513},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4731999933719635},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.26989999413490295},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.13344","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.13344","pdf_url":"https://arxiv.org/pdf/2507.13344","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.13344","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.13344","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.13344","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.13344","pdf_url":"https://arxiv.org/pdf/2507.13344","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2480055265","display_name":null,"funder_award_id":"U24B20154,62172364","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7435075526","display_name":null,"funder_award_id":"2024YFB2809105","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,19,36,64,68,83,99,114,120,125,132,136,148,152,156,164,185],"challenge":[4],"of":[5,9,21,67,151],"high-fidelity":[6],"view":[7,48],"synthesis":[8,49],"humans":[10],"with":[11,107],"sparse-view":[12],"videos":[13,31,38,115,181],"as":[14],"input.":[15],"Previous":[16],"methods":[17],"solve":[18],"issue":[20],"insufficient":[22],"observation":[23],"by":[24],"leveraging":[25],"4D":[26,69,149],"diffusion":[27,70,137],"models":[28,41],"to":[29,62,139,175],"generate":[30],"at":[32,116],"novel":[33,57],"viewpoints.":[34],"However,":[35],"generated":[37],"from":[39,119],"these":[40],"often":[42],"lack":[43],"spatio-temporal":[44,65],"consistency,":[45],"thus":[46,146],"degrading":[47],"quality.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,73],"propose":[55],"a":[56,75,91,108,141],"sliding":[58,109],"iterative":[59,126],"denoising":[60,98],"process":[61],"enhance":[63,147],"consistency":[66,150],"model.":[71],"Specifically,":[72],"define":[74],"latent":[76,81,100,133],"grid":[77,101],"in":[78],"which":[79],"each":[80],"encodes":[82],"image,":[84],"camera":[85],"pose,":[86],"and":[87,94,104,111,145,166,178,182,195],"human":[88],"pose":[89],"for":[90,192],"certain":[92],"viewpoint":[93],"timestamp,":[95],"then":[96],"alternately":[97],"along":[102],"spatial":[103],"temporal":[105],"dimensions":[106],"window,":[110],"finally":[112],"decode":[113],"target":[117],"viewpoints":[118],"corresponding":[121],"denoised":[122],"latents.":[123],"Through":[124],"sliding,":[127],"information":[128],"flows":[129],"sufficiently":[130],"across":[131],"grid,":[134],"allowing":[135],"model":[138],"obtain":[140],"large":[142],"receptive":[143],"field":[144],"output,":[153],"while":[154],"making":[155],"GPU":[157],"memory":[158],"consumption":[159],"affordable.":[160],"The":[161],"experiments":[162],"on":[163],"DNA-Rendering":[165],"ActorsHQ":[167],"datasets":[168],"demonstrate":[169],"that":[170],"our":[171,189],"method":[172],"is":[173],"able":[174],"synthesize":[176],"high-quality":[177],"consistent":[179],"novel-view":[180],"significantly":[183],"outperforms":[184],"existing":[186],"approaches.":[187],"See":[188],"project":[190],"page":[191],"interactive":[193],"demos":[194],"video":[196],"results:":[197],"https://diffuman4d.github.io/":[198],".":[199]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-18T00:00:00"}
