{"id":"https://openalex.org/W4415540676","doi":"https://doi.org/10.1145/3746027.3755241","title":"PLATO: Generating Objects from Part Lists via Synthesized Layouts","display_name":"PLATO: Generating Objects from Part Lists via Synthesized Layouts","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540676","doi":"https://doi.org/10.1145/3746027.3755241"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5120132450","display_name":"Amruta Muthal","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amruta Muthal","raw_affiliation_strings":["CVIT, International Institute of Information Technology, Hyderabad, India"],"raw_orcid":"https://orcid.org/0009-0002-4234-9780","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085982333","display_name":"Varghese P Kuruvilla","orcid":"https://orcid.org/0009-0006-1327-0036"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Varghese P Kuruvilla","raw_affiliation_strings":["CVIT, International Institute of Information Technology, Hyderabad, India"],"raw_orcid":"https://orcid.org/0009-0006-1327-0036","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038936106","display_name":"Ravi Kiran Sarvadevabhatla","orcid":"https://orcid.org/0000-0003-4134-1154"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ravi Kiran Sarvadevabhatla","raw_affiliation_strings":["CVIT, International Institute of Information Technology, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0003-4134-1154","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"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":0.26207189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9940","last_page":"9949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9975000023841858,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9975000023841858,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9965000152587891,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9761999845504761,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/hallucinating","display_name":"Hallucinating","score":0.7504000067710876},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.7325999736785889},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.725600004196167},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5871000289916992},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5090000033378601},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3853999972343445},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.3765999972820282}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.7504000067710876},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.7325999736785889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278000116348267},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.725600004196167},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5871000289916992},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5090000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45239999890327454},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3853999972343445},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.3765999972820282},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3463999927043915},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C2779606619","wikidata":"https://www.wikidata.org/wiki/Q17092524","display_name":"Interchangeability","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.289000004529953},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.28839999437332153},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25600001215934753},{"id":"https://openalex.org/C76178495","wikidata":"https://www.wikidata.org/wiki/Q4808784","display_name":"Asset (computer security)","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":14,"referenced_works":["https://openalex.org/W2104408738","https://openalex.org/W2507296351","https://openalex.org/W2962766617","https://openalex.org/W3190835409","https://openalex.org/W3217157240","https://openalex.org/W4283803959","https://openalex.org/W4312497550","https://openalex.org/W4312824283","https://openalex.org/W4312933868","https://openalex.org/W4386076027","https://openalex.org/W4386076211","https://openalex.org/W4386076403","https://openalex.org/W4390873054","https://openalex.org/W4402976947"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"generative":[1,137],"models":[2,138],"often":[3],"struggle":[4],"to":[5,72,91,122,126],"synthesize":[6],"structured":[7],"objects":[8,143],"from":[9],"detailed":[10],"part":[11,46,65,127],"specifications.":[12,128],"They":[13],"frequently":[14],"produce":[15],"anatomically":[16,105],"implausible":[17],"outputs":[18],"or":[19],"hallucinated":[20],"components.":[21],"We":[22,115],"introduce":[23,77],"PLATO,":[24],"a":[25,51,93,145,150],"novel":[26,45,78],"two-stage":[27],"framework":[28],"that":[29,132],"bridges":[30],"this":[31],"gap":[32],"by":[33],"enabling":[34],"precise,":[35],"part-controlled":[36],"object":[37,56,108],"generation.":[38,157],"The":[39],"first":[40],"stage":[41],"is":[42,89],"PLayGen,":[43],"our":[44],"layout":[47,88],"generator":[48],"which":[49],"takes":[50],"list":[52],"of":[53,64],"parts":[54],"and":[55,60,99,139],"category":[57],"as":[58],"input":[59],"synthesizes":[61],"high-fidelity":[62,107],"layouts":[63],"bounding":[66],"boxes.":[67],"To":[68],"enhance":[69],"PLayGen's":[70,86],"ability":[71],"learn":[73],"inter-part":[74],"relationships,":[75],"we":[76],"structure-based":[79],"loss":[80],"functions.":[81],"In":[82],"the":[83,112],"second":[84],"stage,":[85],"synthesized":[87],"used":[90],"condition":[92],"custom-tuned":[94],"ControlNet-style":[95],"adapter,":[96],"enforcing":[97],"spatial":[98],"connectivity":[100],"constraints.":[101],"This":[102],"results":[103],"in":[104,144,153],"consistent,":[106],"generations":[109],"containing":[110],"precisely":[111],"user-specified":[113],"parts.":[114],"further":[116],"propose":[117],"new":[118],"part-level":[119],"evaluation":[120],"metrics":[121],"rigorously":[123],"quantify":[124],"adherence":[125],"Extensive":[129],"experiments":[130],"show":[131],"PLATO":[133],"significantly":[134],"outperforms":[135],"state-of-the-art":[136],"produces":[140],"structurally":[141],"coherent":[142],"controllable":[146],"manner":[147],"-":[148],"marking":[149],"step":[151],"forward":[152],"modular,":[154],"part-driven":[155],"asset":[156]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}