{"id":"https://openalex.org/W7204958718","doi":"https://doi.org/10.48550/arxiv.2608.30307","title":"ScenePilot: Grow-and-Repair Policy for Text-Driven 3D Indoor Scene Generation","display_name":"ScenePilot: Grow-and-Repair Policy for Text-Driven 3D Indoor Scene Generation","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204958718","doi":"https://doi.org/10.48550/arxiv.2608.30307"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.30307","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30307","pdf_url":"https://arxiv.org/pdf/2608.30307","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":null,"license_id":null,"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/2608.30307","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148869887","display_name":"Jiawei Zhang","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":"Zhang, Jiawei","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":"https://openalex.org/A5148918803","display_name":"Hongsong Wang","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":"Wang, Hongsong","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125658272","display_name":"Pan Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhou, Pan","raw_affiliation_strings":["Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.926800012588501,"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":0.926800012588501,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0284000001847744,"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":0.02199999988079071,"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.7390000224113464},{"id":"https://openalex.org/keywords/hierarchical-retrieval","display_name":"hierarchical retrieval","score":0.5519999861717224},{"id":"https://openalex.org/keywords/object-insertion","display_name":"object insertion","score":0.4309999942779541},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247999906539917},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5354999899864197},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5120000243186951},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5077999830245972},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.49050000309944153},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.45980000495910645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4480000138282776},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38589999079704285},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.3091999888420105},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C2779606619","wikidata":"https://www.wikidata.org/wiki/Q17092524","display_name":"Interchangeability","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2718000113964081}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.30307","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30307","pdf_url":"https://arxiv.org/pdf/2608.30307","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.30307","doi":"https://doi.org/10.48550/arxiv.2608.30307","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.30307","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.30307","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30307","pdf_url":"https://arxiv.org/pdf/2608.30307","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204958718.pdf","grobid_xml":"https://content.openalex.org/works/W7204958718.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2593864460","https://openalex.org/W4387967982","https://openalex.org/W4391631327","https://openalex.org/W4391673134","https://openalex.org/W4404330874","https://openalex.org/W4413147469","https://openalex.org/W4414787395","https://openalex.org/W4415338436","https://openalex.org/W4416139076","https://openalex.org/W4416975539","https://openalex.org/W4417144611","https://openalex.org/W4417252869","https://openalex.org/W6929169196","https://openalex.org/W7119523234","https://openalex.org/W7128647072","https://openalex.org/W7133190492"],"related_works":["https://openalex.org/W4407422848","https://openalex.org/W7137874744","https://openalex.org/W4406121792","https://openalex.org/W4401880002","https://openalex.org/W7155059621","https://openalex.org/W7168657364","https://openalex.org/W4415796584","https://openalex.org/W6979356379","https://openalex.org/W4415338436","https://openalex.org/W7212314627"],"abstract_inverted_index":{"Text-driven":[0],"3D":[1,135],"indoor":[2],"scene":[3,61,159],"generation":[4,62,178],"has":[5],"advanced":[6],"from":[7,156],"dataset-bound":[8],"layout":[9,44,84],"modeling":[10],"to":[11,86,176],"open-vocabulary":[12],"synthesis":[13],"with":[14,67,169],"large":[15],"language":[16],"and":[17,37,39,49,82,114,140,163,179,188],"vision-language":[18],"models.":[19],"Yet":[20],"existing":[21],"methods":[22],"remain":[23],"limited:":[24],"one-pass":[25],"generators":[26],"often":[27],"yield":[28],"geometrically":[29],"invalid":[30],"layouts,":[31],"heavy":[32,180],"post-hoc":[33],"optimization":[34],"is":[35],"costly":[36],"unstable,":[38],"prompt-only":[40],"planners":[41],"lack":[42],"reusable":[43],"priors":[45,85],"for":[46],"functional":[47,88,186],"grouping":[48],"object":[50,97],"relations.":[51],"We":[52],"propose":[53],"\\textbf{ScenePilot},":[54],"a":[55,71,115,128],"retrieval-augmented":[56],"\\textbf{Grow-and-Repair}":[57],"framework":[58],"that":[59],"formulates":[60],"as":[63,146],"prior-guided":[64],"incremental":[65],"growth":[66],"learned":[68],"rectification.":[69],"Given":[70],"prompt,":[72],"the":[73,101],"Hierarchical":[74],"Retrieval-Augmented":[75],"Planning":[76],"(HRAP)":[77],"module":[78,106],"retrieves":[79],"room-,":[80],"group-,":[81],"anchor-level":[83],"support":[87],"group":[89],"planning.":[90],"A":[91],"text-driven":[92],"base":[93],"generator":[94],"then":[95,142],"inserts":[96],"groups":[98],"sequentially,":[99],"while":[100,190],"Reinforcement":[102],"Multimodal":[103],"Repair":[104],"(RMR)":[105],"performs":[107],"lightweight":[108],"local":[109],"correction":[110],"after":[111,119],"each":[112],"insertion":[113],"final":[116],"global":[117],"repair":[118],"completion.":[120],"To":[121],"train":[122],"this":[123],"policy,":[124],"we":[125],"construct":[126],"\\textbf{SceneReverse-17k},":[127],"repair-trajectory":[129],"dataset":[130],"built":[131],"by":[132],"perturbing":[133],"high-quality":[134],"scenes":[136],"in":[137],"position,":[138],"rotation,":[139],"scale,":[141],"using":[143],"inverse":[144],"operations":[145],"executable":[147],"rectification":[148],"targets.":[149],"The":[150],"policy":[151],"predicts":[152],"structured":[153],"\\emph{move--rotate--scale}":[154],"actions":[155],"rendered":[157],"views,":[158],"state,":[160],"retrieved":[161],"priors,":[162],"edit":[164],"history.":[165],"By":[166],"combining":[167],"HRAP":[168],"RMR,":[170],"ScenePilot":[171],"offers":[172],"an":[173],"efficient":[174],"alternative":[175],"one-shot":[177],"full-scene":[181],"optimization,":[182],"improving":[183],"physical":[184],"plausibility,":[185],"coherence,":[187],"controllability":[189],"preserving":[191],"diversity.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-02T00:00:00"}