{"id":"https://openalex.org/W4405792764","doi":"https://doi.org/10.1109/3dv69130.2026.00080","title":"ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation","display_name":"ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W4405792764","doi":"https://doi.org/10.1109/3dv69130.2026.00080"},"language":"en","primary_location":{"id":"doi:10.1109/3dv69130.2026.00080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.18600","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059881394","display_name":"Hongjie Li","orcid":"https://orcid.org/0000-0001-5534-6533"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongjie Li","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100647862","display_name":"Hong-Xing Yu","orcid":"https://orcid.org/0000-0003-3093-5467"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong-Xing Yu","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009234134","display_name":"Jiaman Li","orcid":"https://orcid.org/0000-0002-1261-3248"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaman Li","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621607","display_name":"Jiajun Wu","orcid":"https://orcid.org/0000-0003-0741-0742"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajun Wu","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00358873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"783","last_page":"794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9983999729156494,"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":0.9980000257492065,"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/shot","display_name":"Shot (pellet)","score":0.7955568432807922},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6764118075370789},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4204178750514984},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41646867990493774},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.414107084274292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33626338839530945},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0686330497264862},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.04448100924491882}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7955568432807922},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6764118075370789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4204178750514984},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41646867990493774},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.414107084274292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33626338839530945},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0686330497264862},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04448100924491882},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/3dv69130.2026.00080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.18600","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.18600","pdf_url":"https://arxiv.org/pdf/2412.18600","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.2412.18600","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.18600","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.18600","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.18600","pdf_url":"https://arxiv.org/pdf/2412.18600","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Human-scene":[0],"interaction":[1,62,145],"(HSI)":[2],"generation":[3,84],"is":[4,76],"crucial":[5],"for":[6,43,48,67],"applications":[7],"in":[8,21,112],"embodied":[9],"AI,":[10],"virtual":[11],"reality,":[12],"and":[13,38,97,116,140,153],"robotics.":[14],"Yet,":[15],"existing":[16],"methods":[17],"cannot":[18],"synthesize":[19,108],"interactions":[20,80],"unseen":[22,49],"environments":[23,117],"such":[24],"as":[25,31],"in-the-wild":[26],"scenes":[27,37,115,142],"or":[28],"reconstructed":[29],"scenes,":[30],"they":[32],"rely":[33],"on":[34,69,90,130],"paired":[35],"3D":[36],"captured":[39],"human":[40,95,110],"motion":[41,125],"data":[42],"training,":[44],"which":[45,86],"are":[46],"unavailable":[47],"environments.":[50],"We":[51,127],"present":[52],"ZeroHSI,":[53],"a":[54,131],"novel":[55],"approach":[56],"that":[57],"enables":[58],"zero-shot":[59],"4D":[60],"human-scene":[61,79,104,156],"synthesis,":[63],"eliminating":[64],"the":[65],"need":[66],"training":[68],"any":[70,123],"MoCap":[71],"data.":[72,126],"Our":[73],"key":[74],"insight":[75],"to":[77,102,150],"distill":[78],"from":[81],"state-of-the-art":[82],"video":[83],"models,":[85],"have":[87],"been":[88],"trained":[89],"vast":[91],"amounts":[92],"of":[93,134,137],"natural":[94],"movements":[96],"interactions,and":[98],"use":[99],"differentiable":[100],"rendering":[101],"reconstruct":[103],"interactions.":[105,157],"ZeroHSI":[106,129],"can":[107],"realistic":[109],"motions":[111],"both":[113],"static":[114],"with":[118,143],"dynamic":[119],"objects,":[120],"without":[121],"requiring":[122],"ground-truth":[124],"evaluate":[128],"curated":[132],"dataset":[133],"different":[135,144],"types":[136],"various":[138],"indoor":[139],"outdoor":[141],"prompts,":[146],"demonstrating":[147],"its":[148],"ability":[149],"generate":[151],"diverse":[152],"contextually":[154],"appropriate":[155],"Project":[158],"page:":[159],"https://awfuact.github.io/zerohsi.":[160]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
