{"id":"https://openalex.org/W7106691647","doi":"https://doi.org/10.48550/arxiv.2511.18734","title":"Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion","display_name":"Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W7106691647","doi":"https://doi.org/10.48550/arxiv.2511.18734"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2511.18734","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.18734","pdf_url":"https://arxiv.org/pdf/2511.18734","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.18734","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lu, Keyang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu, Keyang","raw_affiliation_strings":["Beihang University","School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou, Sifan","orcid":null,"observed_orcids":[]},"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":"Zhou, Sifan","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu, Hongbin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Hongbin","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu, Gang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405260597","display_name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen)","ror":"https://ror.org/040g1y854","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405260597"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Gang","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)","institution_ids":["https://openalex.org/I4405260597"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang, Zhifei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Zhifei","raw_affiliation_strings":["School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Yikai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yikai","raw_affiliation_strings":["Beijing Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao, Zhen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao, Zhen","raw_affiliation_strings":["School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Long, Jieyi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Jieyi","raw_affiliation_strings":["Theta Labs ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Theta Labs (","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Li, Ming","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.6894999742507935,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.6894999742507935,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1526000052690506,"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":0.11540000140666962,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.550000011920929},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7860000133514404},{"id":"https://openalex.org/keywords/agentic-framework","display_name":"agentic framework","score":0.7059999704360962},{"id":"https://openalex.org/keywords/top-down-planning","display_name":"top-down planning","score":0.5770000219345093},{"id":"https://openalex.org/keywords/image-to-3d-generation","display_name":"image-to-3D generation","score":0.9700000286102295},{"id":"https://openalex.org/keywords/scene-graph","display_name":"scene graph","score":0.703000009059906},{"id":"https://openalex.org/keywords/layout-optimization","display_name":"layout optimization","score":0.7590000033378601},{"id":"https://openalex.org/keywords/digital-twin","display_name":"digital twin","score":0.6100000143051147},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"virtual reality","score":0.8399999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6963000297546387},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6841999888420105},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.6302000284194946},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5640000104904175},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4860999882221222},{"id":"https://openalex.org/C170477896","wikidata":"https://www.wikidata.org/wiki/Q17039022","display_name":"Ideation","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C181672929","wikidata":"https://www.wikidata.org/wiki/Q4115141","display_name":"Digital mapping","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.267300009727478},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25450000166893005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.18734","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.18734","pdf_url":"https://arxiv.org/pdf/2511.18734","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.18734","doi":"https://doi.org/10.48550/arxiv.2511.18734","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.18734","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.18734","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.18734","pdf_url":"https://arxiv.org/pdf/2511.18734","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.8787999749183655}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7106691647.pdf","grobid_xml":"https://content.openalex.org/works/W7106691647.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W4322718191","https://openalex.org/W4327810158","https://openalex.org/W4377121468","https://openalex.org/W4384812233","https://openalex.org/W4399511096","https://openalex.org/W4402671013","https://openalex.org/W4414585765","https://openalex.org/W4414588510","https://openalex.org/W4414747960","https://openalex.org/W4415032550","https://openalex.org/W4415191902","https://openalex.org/W4415289293","https://openalex.org/W4415886207","https://openalex.org/W4416373957","https://openalex.org/W4416780398","https://openalex.org/W4416872478","https://openalex.org/W4416917105","https://openalex.org/W4417538703","https://openalex.org/W6891851223","https://openalex.org/W6929169196","https://openalex.org/W6948184552","https://openalex.org/W7119523234","https://openalex.org/W7201998646"],"related_works":["https://openalex.org/W7106842101","https://openalex.org/W4402703008","https://openalex.org/W4399511096","https://openalex.org/W7128064407","https://openalex.org/W4399554456","https://openalex.org/W4408353343","https://openalex.org/W7167578630","https://openalex.org/W4401200999","https://openalex.org/W4394736858","https://openalex.org/W4415289336"],"abstract_inverted_index":{"Realistic":[0],"3D":[1,56,113],"city":[2,57,75,131,153],"generation":[3,58,114,173],"is":[4,115],"fundamental":[5],"to":[6,33],"a":[7,25,46,77,83,118,136,162],"wide":[8],"range":[9],"of":[10,66,178],"applications,":[11],"including":[12],"virtual":[13],"reality":[14],"and":[15,36,53,63,94,146,166,182],"digital":[16],"twins.":[17],"However,":[18],"most":[19],"existing":[20,191],"methods":[21,193],"rely":[22],"on":[23],"training":[24],"single":[26],"diffusion":[27],"model,":[28],"which":[29,141],"limits":[30],"their":[31],"ability":[32],"generate":[34],"personalized":[35],"boundless":[37],"city-scale":[38],"scenes.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,160],"present":[44],"Yo'City,":[45],"novel":[47],"agentic":[48],"framework":[49],"that":[50,81,171,187],"enables":[51],"user-customized":[52],"infinitely":[54],"expandable":[55],"by":[59,125],"leveraging":[60],"the":[61,74,91,99,111,176],"reasoning":[62],"compositional":[64],"capabilities":[65],"off-the-shelf":[67],"large":[68],"models.":[69],"Specifically,":[70],"Yo'City":[71,133,188],"first":[72],"conceptualizes":[73],"through":[76,117],"top-down":[78],"planning":[79],"strategy":[80],"defines":[82],"hierarchical":[84],"\"City-District-Grid\"":[85],"structure.":[86],"The":[87],"Global":[88],"Planner":[89],"determines":[90],"overall":[92],"layout":[93,148],"potential":[95],"functional":[96],"districts,":[97],"while":[98],"Local":[100],"Designer":[101],"further":[102,134],"refines":[103],"each":[104],"district":[105],"with":[106],"detailed":[107],"grid-level":[108,112],"descriptions.":[109],"Subsequently,":[110],"achieved":[116],"\"produce-refine-evaluate\"":[119],"isometric":[120],"image":[121],"synthesis":[122],"loop,":[123],"followed":[124],"image-to-3D":[126],"generation.":[127],"To":[128,155],"simulate":[129],"continuous":[130],"evolution,":[132],"introduces":[135],"user-interactive,":[137],"relationship-guided":[138],"expansion":[139],"mechanism,":[140],"performs":[142],"scene":[143],"graph-based":[144],"distance-":[145],"semantics-aware":[147],"optimization,":[149],"ensuring":[150],"spatially":[151],"coherent":[152],"growth.":[154],"comprehensively":[156],"evaluate":[157],"our":[158],"method,":[159],"construct":[161],"diverse":[163],"benchmark":[164],"dataset":[165],"design":[167],"six":[168],"multi-dimensional":[169],"metrics":[170],"assess":[172],"quality":[174],"from":[175],"perspectives":[177],"semantics,":[179],"geometry,":[180],"texture,":[181],"layout.":[183],"Extensive":[184],"experiments":[185],"demonstrate":[186],"consistently":[189],"outperforms":[190],"state-of-the-art":[192],"across":[194],"all":[195],"evaluation":[196],"aspects.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-11-27T00:00:00"}