{"id":"https://openalex.org/W4415344107","doi":"https://doi.org/10.1109/iccv51701.2025.01677","title":"Laconic: A 3D Layout Adapter for Controllable Image Creation","display_name":"Laconic: A 3D Layout Adapter for Controllable Image Creation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415344107","doi":"https://doi.org/10.1109/iccv51701.2025.01677"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01677","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.03257","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"L\u00e9opold Maillard","orcid":null},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"L\u00e9opold Maillard","raw_affiliation_strings":["Ecole Polytechnique, IP Paris,LIX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique, IP Paris,LIX","institution_ids":["https://openalex.org/I4210139461","https://openalex.org/I142476485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040870391","display_name":"Tom Durand","orcid":"https://orcid.org/0000-0001-9219-3185"},"institutions":[{"id":"https://openalex.org/I47431100","display_name":"Dassault Syst\u00e8mes (France)","ror":"https://ror.org/038sc5x72","country_code":"FR","type":"company","lineage":["https://openalex.org/I47431100"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Tom Durand","raw_affiliation_strings":["Dassault Systemes"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dassault Systemes","institution_ids":["https://openalex.org/I47431100"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120060935","display_name":"Adrien Ramanana Rahary","orcid":null},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Adrien Ramanana Rahary","raw_affiliation_strings":["Ecole Polytechnique, IP Paris,LIX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique, IP Paris,LIX","institution_ids":["https://openalex.org/I4210139461","https://openalex.org/I142476485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108914317","display_name":"Maks Ovsjanikov","orcid":null},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maks Ovsjanikov","raw_affiliation_strings":["Ecole Polytechnique, IP Paris,LIX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique, IP Paris,LIX","institution_ids":["https://openalex.org/I4210139461","https://openalex.org/I142476485"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.26195574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18046","last_page":"18057"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9919999837875366,"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":0.9919999837875366,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.984499990940094,"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/adapter","display_name":"Adapter (computing)","score":0.6013000011444092},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5742999911308289},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5309000015258789},{"id":"https://openalex.org/keywords/tweaking","display_name":"Tweaking","score":0.48590001463890076},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48019999265670776},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47940000891685486},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4708999991416931},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.47049999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6247000098228455},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.6013000011444092},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5785999894142151},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5742999911308289},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C2780200862","wikidata":"https://www.wikidata.org/wiki/Q4453309","display_name":"Tweaking","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48019999265670776},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.47049999237060547},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4634000062942505},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.30140000581741333},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2637999951839447},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2612999975681305},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25540000200271606}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.01677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01677","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:2507.03257","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.03257","pdf_url":"https://arxiv.org/pdf/2507.03257","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":"pmh:oai:HAL:hal-05434054v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05434054","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICCV 2025 - International Conference on Computer Vision, Oct 2025, Honolulu, United States. ⟨10.48550/arXiv.2507.03257⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2507.03257","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.03257","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:2507.03257","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.03257","pdf_url":"https://arxiv.org/pdf/2507.03257","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":[],"abstract_inverted_index":{"Existing":[0],"generative":[1],"approaches":[2],"for":[3,89,94,128,140],"guided":[4],"image":[5,17,144,165],"synthesis":[6],"of":[7,98,126,173],"multi-object":[8],"scenes":[9],"typically":[10],"rely":[11],"on":[12,84,103],"2D":[13],"controls":[14],"in":[15,156],"the":[16,36,90,95],"or":[18,152],"text":[19],"space.":[20],"As":[21],"a":[22,43,64,99,123,157,170],"result,":[23],"these":[24],"methods":[25,139],"struggle":[26],"to":[27,66,107,176],"maintain":[28],"and":[29,49,104,110,131,142,146,168],"respect":[30],"consistent":[31,143],"three-dimensional":[32],"geometric":[33],"structure,":[34],"underlying":[35],"scene.":[37,158],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"novel":[44],"conditioning":[45,83],"approach,":[46],"training":[47],"method":[48,79,160],"adapter":[50],"network":[51],"that":[52],"can":[53],"be":[54],"plugged":[55],"into":[56],"pretrained":[57],"text-to-image":[58],"diffusion":[59],"models.":[60],"Our":[61,78,159],"approach":[62],"provides":[63],"way":[65],"endow":[67],"such":[68],"models":[69],"with":[70],"3D-awareness,":[71],"while":[72],"leveraging":[73],"their":[74],"rich":[75,112],"prior":[76],"knowledge.":[77],"supports":[80],"camera":[81],"control,":[82],"explicit":[85],"3D":[86],"geometries":[87],"and,":[88],"first":[91],"time,":[92],"accounts":[93],"entire":[96],"context":[97],"scene,":[100],"i.e.,":[101],"both":[102],"off-screen":[105],"items,":[106],"synthesize":[108],"plausible":[109],"semantically":[111],"images.":[113],"Despite":[114],"its":[115],"multi-modal":[116],"nature,":[117],"our":[118],"model":[119],"is":[120],"lightweight,":[121],"requires":[122],"reasonable":[124],"number":[125],"data":[127],"supervised":[129],"learning":[130],"shows":[132],"remarkable":[133],"generalization":[134],"power.":[135],"We":[136],"also":[137],"introduce":[138],"intuitive":[141],"editing":[145],"restyling,":[147],"e.g.,":[148],"by":[149],"positioning,":[150],"rotating":[151],"resizing":[153],"individual":[154],"objects":[155],"integrates":[161],"well":[162],"within":[163],"various":[164],"creation":[166],"workflows":[167],"enables":[169],"richer":[171],"set":[172],"applications":[174],"compared":[175],"previous":[177],"approaches.":[178]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-20T00:00:00"}