{"id":"https://openalex.org/W4416095693","doi":"https://doi.org/10.1109/iccv51701.2025.01664","title":"Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers","display_name":"Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416095693","doi":"https://doi.org/10.1109/iccv51701.2025.01664"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.04718","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007978190","display_name":"Divyansh Srivastava","orcid":"https://orcid.org/0000-0001-5755-7123"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divyansh Srivastava","raw_affiliation_strings":["UC San Diego,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego,USA","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368916","display_name":"Xiang Zhang","orcid":"https://orcid.org/0000-0003-2004-5794"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Zhang","raw_affiliation_strings":["UC San Diego,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego,USA","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112118627","display_name":"Wen He","orcid":"https://orcid.org/0000-0003-0440-8516"},"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":"He Wen","raw_affiliation_strings":["Tsingua University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsingua University,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenru Wen","orcid":null},"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":"Chenru Wen","raw_affiliation_strings":["Tsingua University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsingua University,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001760915","display_name":"Zhuowen Tu","orcid":"https://orcid.org/0000-0002-1900-2124"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuowen Tu","raw_affiliation_strings":["UC San Diego,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego,USA","institution_ids":["https://openalex.org/I2800935791"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17909","last_page":"17919"},"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":0.6827999949455261,"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":0.6827999949455261,"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":0.23100000619888306,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.012400000356137753,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6668999791145325},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6506999731063843},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.641700029373169},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.49559998512268066},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46000000834465027},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4131999909877777},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40849998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878999710083008},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6668999791145325},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6506999731063843},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.641700029373169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5228999853134155},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4359999895095825},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.34779998660087585},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3276999890804291},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2522999942302704},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.25040000677108765}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.04718","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.04718","pdf_url":"https://arxiv.org/pdf/2505.04718","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2505.04718","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.04718","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.04718","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.04718","pdf_url":"https://arxiv.org/pdf/2505.04718","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[{"id":"https://openalex.org/G6310532796","display_name":null,"funder_award_id":"IIS-2127544,IIS-2433768","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1,96,124],"Lay-Your-Scene":[2],"(shorthand":[3],"LayouSyn),":[4],"a":[5,60,125],"novel":[6,61],"text-to-layout":[7],"generation":[8,16],"pipeline":[9,126],"for":[10,27,71,127],"natural":[11],"scenes.":[12],"Prior":[13],"scene":[14,54],"layout":[15,73],"methods":[17,82],"are":[18],"either":[19],"closed-vocabulary":[20],"or":[21],"use":[22,47],"proprietary":[23],"large":[24,108],"language":[25,50,109],"models":[26,51,110],"open-vocabulary":[28,69],"generation,":[29],"limiting":[30],"their":[31],"modeling":[32],"capabilities":[33],"and":[34,59,83,90],"broader":[35],"applicability":[36],"in":[37,67,137],"controllable":[38],"image":[39,138],"generation.":[40,74],"In":[41],"this":[42],"work,":[43],"we":[44,95,102,123],"propose":[45],"to":[46,52,118,130],"lightweight":[48],"open-source":[49],"obtain":[53],"elements":[55],"from":[56,107],"text":[57],"prompts":[58],"aspect-aware":[62],"diffusion":[63],"Transformer":[64],"architecture":[65],"trained":[66],"an":[68],"manner":[70],"conditional":[72],"Extensive":[75],"experiments":[76],"demonstrate":[77],"that":[78,104],"LayouSyn":[79,136],"outperforms":[80],"existing":[81],"achieves":[84],"state-of-the-art":[85],"performance":[86],"on":[87],"challenging":[88],"spatial":[89],"numerical":[91],"reasoning":[92],"benchmarks.":[93],"Additionally,":[94],"two":[97],"applications":[98],"of":[99,135],"LayouSyn.":[100],"First,":[101],"show":[103],"coarse":[105],"initialization":[106],"can":[111],"be":[112],"seamlessly":[113],"combined":[114],"with":[115],"our":[116],"method":[117],"achieve":[119],"better":[120],"results.":[121],"Second,":[122],"adding":[128],"objects":[129],"images,":[131],"demonstrating":[132],"the":[133],"potential":[134],"editing":[139],"applications.":[140]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}