{"id":"https://openalex.org/W4414684812","doi":"https://doi.org/10.1109/wacv61042.2026.00022","title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","display_name":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4414684812","doi":"https://doi.org/10.1109/wacv61042.2026.00022"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.19840","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100607162","display_name":"Zekun Li","orcid":"https://orcid.org/0000-0002-0590-8873"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zekun Li","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101621542","display_name":"Rui Zhou","orcid":"https://orcid.org/0000-0001-9687-0825"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Zhou","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030173417","display_name":"Rahul Sajnani","orcid":"https://orcid.org/0000-0001-7714-5855"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Sajnani","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065242641","display_name":"Xiaoyan Cong","orcid":"https://orcid.org/0000-0003-3940-3336"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyan Cong","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059267221","display_name":"Daniel Ritchie","orcid":"https://orcid.org/0000-0002-1854-0502"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Ritchie","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014973945","display_name":"Srinath Sridhar","orcid":"https://orcid.org/0000-0003-4663-3324"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinath Sridhar","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100607162"],"corresponding_institution_ids":["https://openalex.org/I175594653"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0043415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"138","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"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":0.9991999864578247,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9961000084877014,"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/T12290","display_name":"Human Motion and Animation","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6365000009536743},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5760999917984009},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5479999780654907},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5455999970436096},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.49410000443458557},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.47200000286102295},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3677000105381012},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3490000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840499997138977},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5978999733924866},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5943999886512756},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5760999917984009},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5455999970436096},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.47200000286102295},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C166142869","wikidata":"https://www.wikidata.org/wiki/Q60061622","display_name":"Video production","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.29760000109672546},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.19840","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.19840","pdf_url":"https://arxiv.org/pdf/2506.19840","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.2506.19840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.19840","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:2506.19840","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.19840","pdf_url":"https://arxiv.org/pdf/2506.19840","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"pre-trained":[1,154],"video":[2,11,71,205,231],"diffusion":[3,157,206],"models":[4,158,207],"have":[5],"exhibited":[6],"remarkable":[7],"capabilities":[8],"in":[9,19,135,149,176,219],"diverse":[10],"generation.":[12],"However,":[13],"existing":[14],"solutions":[15],"face":[16],"several":[17],"challenges":[18],"generating":[20],"long":[21,57,104,212,230],"videos":[22,59,105,213,259],"with":[23,60,93,214,233,268],"rich":[24,112],"human\u2013scene":[25],"interactions":[26,164,183],"(HSI),":[27],"including":[28],"unrealistic":[29],"dynamics":[30,216],"and":[31,38,81,90,110,113,194,217,249,265],"affordance,":[32],"lack":[33],"of":[34,56,87,126,236,246],"subject":[35],"identity":[36,109,267],"preservation,":[37],"the":[39,70,136,171,203,225,243,247],"need":[40,172],"for":[41,53,173],"expensive":[42],"training.":[43],"To":[44,143],"this":[45],"end,":[46],"we":[47,68,97,152],"propose":[48],"GenHSI,":[49],"a":[50,88,91,94,119,124,220,229,234,273],"training-free":[51],"method":[52,255],"controllable":[54],"generation":[55],"HSI":[58,127,237,258],"3D":[61,141,150,185,201],"awareness.":[62],"Taking":[63],"inspiration":[64],"from":[65,196,272],"movie":[66],"animation,":[67],"subdivide":[69],"synthesis":[72],"into":[73,128],"three":[74,100],"stages:":[75],"(1)":[76],"script":[77],"writing,":[78],"(2)":[79],"pre-visualization,":[80],"(3)":[82],"animation.":[83],"Given":[84],"an":[85],"image":[86,244,275],"scene":[89,248,263],"character":[92,266],"user":[95],"description,":[96],"use":[98],"these":[99,182,200],"stages":[101],"to":[102,139,159,184,227],"generate":[103,140,160,210,257],"that":[106,132,253,260],"preserve":[107,262],"human":[108,146,163],"provide":[111],"plausible":[114,145,161,215,269],"HSI.":[115],"Script":[116],"writing":[117],"converts":[118],"complex":[120],"text":[121],"prompt":[122],"involving":[123],"chain":[125,235],"simple":[129],"atomic":[130],"actions":[131,238],"are":[133,224],"used":[134],"pre-visualization":[137],"stage":[138],"keyframes.":[142],"synthesize":[144,228],"interaction":[147,271],"poses":[148],"keyframes,":[151,202],"utilize":[153],"2D":[155,162],"inpainting":[156],"based":[165,241],"on":[166,242],"view":[167],"canonicalization,":[168],"which":[169],"eliminates":[170],"multi-view":[174],"fitting":[175],"previous":[177],"works.":[178],"We":[179,223],"then":[180],"extend":[181],"using":[186],"robust":[187],"iterative":[188],"optimization,":[189],"informed":[190],"by":[191,199],"contact":[192],"cues":[193],"reasoning":[195],"VLMs.":[197],"Prompted":[198],"pretrained":[204],"can":[208,256],"better":[209],"consistent":[211],"affordance":[218],"3D-aware":[221],"manner.":[222],"first":[226],"sequence":[232],"without":[239],"training":[240],"references":[245],"character.":[250],"Experiments":[251],"demonstrate":[252],"our":[254],"effectively":[261],"content":[264],"humanscene":[270],"single":[274],"scene.":[276]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-10-10T00:00:00"}