{"id":"https://openalex.org/W7204078993","doi":"https://doi.org/10.48550/arxiv.2608.20932","title":"OccluRank: Controllable Occlusion-Aware Layout-to-Image Generation by Adding Just an Ordinal Rank","display_name":"OccluRank: Controllable Occlusion-Aware Layout-to-Image Generation by Adding Just an Ordinal Rank","publication_year":2026,"publication_date":"2026-08-21","ids":{"openalex":"https://openalex.org/W7204078993","doi":"https://doi.org/10.48550/arxiv.2608.20932"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.20932","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20932","pdf_url":"https://arxiv.org/pdf/2608.20932","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.20932","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147974963","display_name":"Wenyang Hong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong, Wenyang","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148173634","display_name":"Yuan Wang","orcid":null,"observed_orcids":[]},"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":"Wang, Yuan","raw_affiliation_strings":["School of Cyber Science and Technology , University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology , University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138476365","display_name":"Yanbin Hao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao, Yanbin","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063593572","display_name":"Lanqing Xue","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Lanqing","raw_affiliation_strings":["LCFC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LCFC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134803252","display_name":"Ke Wang","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":"Wang, Ke","raw_affiliation_strings":["ByteDance Inc","\u2211 CA CA CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"\u2211 CA CA CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122334324","display_name":"Xiang Wang","orcid":null,"observed_orcids":[]},"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":"Wang, Xiang","raw_affiliation_strings":["School of Artificial Intelligence and Data Science , University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Data Science , University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134198162","display_name":"Kuien Liu","orcid":"https://orcid.org/0000-0003-3674-7555","observed_orcids":["https://orcid.org/0000-0003-3674-7555"]},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Kuien","raw_affiliation_strings":["Hefei University of Technology","Institute of Software , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"Institute of Software , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129676354","display_name":"Richang Hong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong, Richang","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9990000128746033,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9990000128746033,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0006000000284984708,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00019999999494757503,"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/synthetic-training-data","display_name":"synthetic training data","score":0.8460000157356262},{"id":"https://openalex.org/keywords/spatial-control","display_name":"spatial control","score":0.4320000112056732},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.4269999861717224}],"concepts":[{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058000087738037},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.48260000348091125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4796999990940094},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44339999556541443},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.40230000019073486},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C174478892","wikidata":"https://www.wikidata.org/wiki/Q4747455","display_name":"Amodal perception","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.20932","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20932","pdf_url":"https://arxiv.org/pdf/2608.20932","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.2608.20932","doi":"https://doi.org/10.48550/arxiv.2608.20932","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.20932","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:2608.20932","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20932","pdf_url":"https://arxiv.org/pdf/2608.20932","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204078993.pdf","grobid_xml":"https://content.openalex.org/works/W7204078993.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7162032328","https://openalex.org/W7117449335","https://openalex.org/W4414818585","https://openalex.org/W7140609679","https://openalex.org/W4312691223","https://openalex.org/W7167608034","https://openalex.org/W4415251617","https://openalex.org/W4413147524","https://openalex.org/W3155112754","https://openalex.org/W3174711319"],"abstract_inverted_index":{"Layout-to-image":[0],"generation":[1],"enables":[2],"explicit":[3],"spatial":[4,162],"control":[5],"through":[6,72],"bounding-box":[7],"layouts,":[8,186],"yet":[9],"bounding":[10,59],"boxes":[11],"specify":[12],"only":[13,62],"instance":[14,38,88,160],"locations":[15],"and":[16,51,76,123,165,187,197],"cannot":[17],"represent":[18],"their":[19,43],"occlusion":[20,70,121,166,190],"order.":[21],"Existing":[22],"methods":[23],"may":[24],"rely":[25],"on":[26],"additional":[27,105],"geometric":[28,106],"conditions,":[29],"employ":[30],"complex":[31],"inference":[32],"procedures,":[33],"or":[34,108],"aggregate":[35],"independently":[36],"constructed":[37],"representations":[39,89],"without":[40,104],"explicitly":[41],"modeling":[42],"occlusion-dependent":[44],"interactions.":[45],"We":[46,112],"propose":[47],"OccluRank,":[48],"a":[49,116],"simple":[50],"controllable":[52],"occlusion-aware":[53],"layout-to-image":[54],"framework":[55],"that":[56,177],"augments":[57],"each":[58],"box":[60],"with":[61,169],"one":[63],"ordinal":[64],"rank.":[65],"OccluRank":[66,178],"encodes":[67],"the":[68,94],"user-specified":[69],"order":[71,96,122],"lightweight":[73],"rank-based":[74],"conditioning":[75],"introduces":[77],"an":[78],"Order-aware":[79],"Instance":[80],"Interaction":[81],"(OII)":[82],"module":[83],"to":[84,97,158],"jointly":[85],"update":[86],"rank-conditioned":[87],"before":[90],"aggregation.":[91],"This":[92],"allows":[93],"specified":[95,185],"guide":[98],"information":[99],"exchange":[100],"among":[101],"occluding":[102],"instances":[103],"inputs":[107],"specialized":[109],"inference-time":[110],"optimization.":[111],"further":[113],"construct":[114],"OccluLayout,":[115],"synthetic":[117],"training":[118],"dataset":[119],"whose":[120],"amodal":[124],"annotations":[125],"are":[126],"derived":[127],"directly":[128],"from":[129,136],"known":[130],"scene":[131],"geometry":[132],"rather":[133],"than":[134],"estimated":[135],"partially":[137],"occluded":[138],"images":[139],"using":[140],"auxiliary":[141],"prediction":[142],"models.":[143],"For":[144],"comprehensive":[145],"evaluation,":[146],"we":[147],"introduce":[148],"OccluLayout-Bench,":[149],"which":[150],"uses":[151],"multiple":[152],"multimodal":[153],"large":[154],"language":[155],"model":[156],"evaluators":[157],"assess":[159],"presence,":[161],"layout,":[163],"attributes,":[164],"order,":[167],"together":[168],"FID":[170],"for":[171],"overall":[172,198],"image":[173,199],"quality.":[174,200],"Experiments":[175],"show":[176],"more":[179],"reliably":[180],"preserves":[181],"target":[182],"instances,":[183],"follows":[184],"realizes":[188],"desired":[189],"relationships":[191],"while":[192],"maintaining":[193],"comparable":[194],"attribute":[195],"consistency":[196]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-25T00:00:00"}