{"id":"https://openalex.org/W7131151245","doi":"https://doi.org/10.1109/iccvw69036.2025.00201","title":"DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors","display_name":"DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131151245","doi":"https://doi.org/10.1109/iccvw69036.2025.00201"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00201","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 Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5126593112","display_name":"Hanwen Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hanwen Zhu","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126653697","display_name":"Ruining Li","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruining Li","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126582828","display_name":"Tomas Jakab","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tomas Jakab","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1916","last_page":"1926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.210999995470047,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.210999995470047,"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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.15039999783039093,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.11810000240802765,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/leverage","display_name":"Leverage (statistics)","score":0.6898000240325928},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5993000268936157},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5526000261306763},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4453999996185303},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.38609999418258667},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.38519999384880066},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3463999927043915},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.3312999904155731}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7468000054359436},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6898000240325928},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5993000268936157},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5526000261306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5085999965667725},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3961000144481659},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3312999904155731},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00201","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 Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2045863238","https://openalex.org/W2555859288","https://openalex.org/W2559085405","https://openalex.org/W2768683308","https://openalex.org/W2962778872","https://openalex.org/W2963488642","https://openalex.org/W2964304707","https://openalex.org/W2978956737","https://openalex.org/W3034487425","https://openalex.org/W3035523051","https://openalex.org/W3035724791","https://openalex.org/W3053462477","https://openalex.org/W3081268564","https://openalex.org/W3109585842","https://openalex.org/W3153469116","https://openalex.org/W3175788243","https://openalex.org/W3176368002","https://openalex.org/W4246818198","https://openalex.org/W4312783246","https://openalex.org/W4312824283","https://openalex.org/W4312933868","https://openalex.org/W4313072274","https://openalex.org/W4313182738","https://openalex.org/W4380790484","https://openalex.org/W4386065887","https://openalex.org/W4386075859","https://openalex.org/W4386076018","https://openalex.org/W4386076574","https://openalex.org/W4386076579","https://openalex.org/W4389339329","https://openalex.org/W4390873331","https://openalex.org/W4390874786","https://openalex.org/W4399563597","https://openalex.org/W4399563697","https://openalex.org/W4402667893","https://openalex.org/W4402716015","https://openalex.org/W4402727821","https://openalex.org/W4402753909","https://openalex.org/W4402772414","https://openalex.org/W4402781583","https://openalex.org/W4402951568","https://openalex.org/W4403562353","https://openalex.org/W4403947180","https://openalex.org/W4403998223","https://openalex.org/W4414197407"],"related_works":[],"abstract_inverted_index":{"We":[0,78,162],"present":[1],"DreamHOI,":[2],"a":[3,14,27,55,83,125,130],"novel":[4],"method":[5],"for":[6,64],"zero-shot":[7],"synthesis":[8],"of":[9,32,42,51,58,75,82,117,129],"human-object":[10],"interactions":[11],"(HOIs),":[12],"enabling":[13],"3D":[15],"human":[16,85],"model":[17],"to":[18,113],"realistically":[19],"interact":[20],"with":[21,139],"any":[22],"given":[23],"object":[24],"based":[25],"on":[26,73],"textual":[28],"description.":[29],"The":[30],"complexity":[31],"this":[33],"task":[34],"arises":[35],"from":[36,94],"the":[37,48,62,80,114,154,159],"diverse":[38],"categories":[39],"and":[40,150],"geometries":[41],"real-world":[43],"objects,":[44],"as":[45,47],"well":[46],"limited":[49],"availability":[50],"datasets":[52],"that":[53],"cover":[54],"wide":[56],"range":[57],"HOIs.":[59,175],"To":[60,120],"circumvent":[61],"need":[63],"extensive":[65,167],"data,":[66],"we":[67,123,146],"leverage":[68],"text-to-image":[69],"diffusion":[70],"models":[71],"trained":[72],"billions":[74],"image-caption":[76],"pairs.":[77],"optimize":[79],"articulation":[81,108],"skinned":[84,131],"mesh":[86,142,160],"using":[87],"Score":[88],"Distillation":[89],"Sampling":[90],"(SDS)":[91],"gradients":[92,105],"obtained":[93],"these":[95],"models,":[96],"which":[97],"predict":[98],"image-space":[99,104],"edits.":[100],"However,":[101],"directly":[102],"backpropagating":[103],"into":[106],"complex":[107],"parameters":[109],"is":[110],"ineffective":[111],"due":[112],"local":[115],"nature":[116],"such":[118],"gradients.":[119],"overcome":[121],"this,":[122],"introduce":[124],"dual":[126],"implicit-explicit":[127],"representation":[128],"mesh,":[132],"combining":[133],"(implicit)":[134],"neural":[135],"radiance":[136],"fields":[137],"(NeRFs)":[138],"(explicit)":[140],"skeleton-driven":[141],"articulation.":[143,161],"During":[144],"optimization,":[145],"transition":[147],"between":[148],"implicit":[149],"explicit":[151],"forms,":[152],"grounding":[153],"NeRF":[155],"generation":[156],"while":[157],"refining":[158],"validate":[163],"our":[164],"approach":[165],"through":[166],"experiments,":[168],"demonstrating":[169],"its":[170],"effectiveness":[171],"in":[172],"generating":[173],"realistic":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-24T00:00:00"}