{"id":"https://openalex.org/W4417000471","doi":"https://doi.org/10.1145/3763353","title":"Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation","display_name":"Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W4417000471","doi":"https://doi.org/10.1145/3763353"},"language":"en","primary_location":{"id":"doi:10.1145/3763353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3763353","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","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/A5103196761","display_name":"X. Zhu","orcid":"https://orcid.org/0009-0002-3695-7288"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoming Zhu","raw_affiliation_strings":["Tsinghua University, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, ShenZhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104333008","display_name":"Xu Huang","orcid":"https://orcid.org/0009-0006-2655-2251"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Huang","raw_affiliation_strings":["Tencent, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, ShenZhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042845780","display_name":"Qihu Xie","orcid":"https://orcid.org/0009-0000-9590-638X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghongbing Xie","raw_affiliation_strings":["Tsinghua University, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, ShenZhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109343486","display_name":"Zhi Deng","orcid":"https://orcid.org/0000-0003-4582-4874"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Deng","raw_affiliation_strings":["Tencent, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, ShenZhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036986559","display_name":"Junsheng Yu","orcid":"https://orcid.org/0009-0001-8719-1289"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junsheng Yu","raw_affiliation_strings":["Southeast University, NanJing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University, NanJing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108520170","display_name":"Y. Guan","orcid":"https://orcid.org/0009-0006-0603-748X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yirui Guan","raw_affiliation_strings":["Tencent, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, ShenZhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019686446","display_name":"Z. Liu","orcid":"https://orcid.org/0000-0003-1601-0038"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyuan Liu","raw_affiliation_strings":["Tencent, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, ShenZhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051952253","display_name":"Lin Zhu","orcid":"https://orcid.org/0009-0001-9044-9922"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Zhu","raw_affiliation_strings":["Tencent, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, ShenZhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024477687","display_name":"Qijun Zhao","orcid":"https://orcid.org/0009-0007-4797-9155"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qijun Zhao","raw_affiliation_strings":["Tencent, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, ShenZhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635702","display_name":"Ligang Liu","orcid":"https://orcid.org/0000-0003-4352-1431"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ligang Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035988413","display_name":"Long Zeng","orcid":"https://orcid.org/0000-0002-3090-6319"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Zeng","raw_affiliation_strings":["Tsinghua University, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, ShenZhen, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5103196761"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3944327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":"6","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.44130000472068787,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.44130000472068787,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3903000056743622,"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":0.03799999877810478,"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/parsing","display_name":"Parsing","score":0.6151000261306763},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6140999794006348},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4918000102043152},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.48489999771118164},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.459199994802475},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.397599995136261},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3939000070095062},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.374099999666214},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3723999857902527},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.34369999170303345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8179000020027161},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6151000261306763},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6140999794006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5552999973297119},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.48489999771118164},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43810001015663147},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.397599995136261},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3939000070095062},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C76178495","wikidata":"https://www.wikidata.org/wiki/Q4808784","display_name":"Asset (computer security)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C181095308","wikidata":"https://www.wikidata.org/wiki/Q1541599","display_name":"Geometric primitive","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C2778597888","wikidata":"https://www.wikidata.org/wiki/Q172169","display_name":"3D city models","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2985909886","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Spatial coherence","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C188985296","wikidata":"https://www.wikidata.org/wiki/Q868954","display_name":"Page layout","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C2776509796","wikidata":"https://www.wikidata.org/wiki/Q5276056","display_name":"Content creation","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3763353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3763353","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1989476314","https://openalex.org/W2060268527","https://openalex.org/W2085261163","https://openalex.org/W2119618626","https://openalex.org/W2130634053","https://openalex.org/W2161168419","https://openalex.org/W2162559028","https://openalex.org/W2552930185","https://openalex.org/W2770875015","https://openalex.org/W2795999188","https://openalex.org/W2798622261","https://openalex.org/W2808775391","https://openalex.org/W2810181048","https://openalex.org/W2963892972","https://openalex.org/W2964334375","https://openalex.org/W3035154952","https://openalex.org/W3095066959","https://openalex.org/W3183092879","https://openalex.org/W4205481600","https://openalex.org/W4221162309","https://openalex.org/W4226020718","https://openalex.org/W4253426066","https://openalex.org/W4386072096","https://openalex.org/W4386630189","https://openalex.org/W4390874575","https://openalex.org/W4400818973","https://openalex.org/W4402660086","https://openalex.org/W4402727742","https://openalex.org/W4402733576","https://openalex.org/W4402753875","https://openalex.org/W4403842181","https://openalex.org/W4415798564"],"related_works":[],"abstract_inverted_index":{"Generating":[0],"artistic":[1],"and":[2,34,46,79,124,136,144,165,169],"coherent":[3],"3D":[4,64,81,116],"scene":[5,77,82,131,134],"layouts":[6],"is":[7],"crucial":[8],"in":[9,29,160],"digital":[10],"content":[11,31],"creation.":[12],"Traditional":[13],"optimization-based":[14],"methods":[15,159],"are":[16],"often":[17],"constrained":[18],"by":[19],"cumbersome":[20],"manual":[21],"rules,":[22],"while":[23],"deep":[24],"generative":[25],"models":[26,42],"face":[27],"challenges":[28],"producing":[30],"with":[32,101,146],"richness":[33,164],"diversity.":[35],"Furthermore,":[36],"approaches":[37],"that":[38,153],"utilize":[39],"large":[40],"language":[41],"frequently":[43],"lack":[44],"robustness":[45],"fail":[47],"to":[48,91,99,113,140],"accurately":[49],"capture":[50],"complex":[51],"spatial":[52],"relationships.":[53],"To":[54],"address":[55],"these":[56],"challenges,":[57],"this":[58],"paper":[59],"presents":[60],"a":[61,71,108],"novel":[62],"vision-guided":[63],"layout":[65,117,132,163],"generation":[66,89],"system.":[67],"We":[68,105],"first":[69],"construct":[70],"high-quality":[72],"asset":[73,103],"library":[74],"containing":[75],"2,037":[76],"assets":[78],"147":[80],"layouts.":[83],"Subsequently,":[84],"we":[85,128],"employ":[86],"an":[87],"image":[88,110],"model":[90],"expand":[92],"prompt":[93],"representations":[94],"into":[95],"images,":[96],"fine-tuning":[97],"it":[98],"align":[100],"our":[102,154],"library.":[104],"then":[106],"develop":[107],"robust":[109],"parsing":[111],"module":[112],"recover":[114],"the":[115,130,147],"of":[118,162],"scenes":[119],"based":[120],"on":[121],"visual":[122,138],"semantics":[123,139],"geometric":[125],"information.":[126],"Finally,":[127],"optimize":[129],"using":[133],"graphs":[135],"overall":[137],"ensure":[141],"logical":[142],"coherence":[143],"alignment":[145],"images.":[148],"Extensive":[149],"user":[150],"testing":[151],"demonstrates":[152],"algorithm":[155],"significantly":[156],"outperforms":[157],"existing":[158],"terms":[161],"quality.":[166],"The":[167],"code":[168],"dataset":[170],"will":[171],"be":[172],"available":[173],"at":[174],"https://github.com/HiHiAllen/Imaginarium.":[175]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-04T00:00:00"}
