{"id":"https://openalex.org/W4402979558","doi":"https://doi.org/10.1109/icme57554.2024.10688052","title":"LayoutDM: Precision Multi-Scale Diffusion for Layout-to-Image","display_name":"LayoutDM: Precision Multi-Scale Diffusion for Layout-to-Image","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979558","doi":"https://doi.org/10.1109/icme57554.2024.10688052"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688052","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5009433044","display_name":"Mingzhe Yu","orcid":"https://orcid.org/0009-0005-3793-0847"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingzhe Yu","raw_affiliation_strings":["Shandong University,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong University,Jinan,China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101963649","display_name":"Lei Wu","orcid":"https://orcid.org/0009-0007-7363-0002"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wu","raw_affiliation_strings":["Shandong University,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong University,Jinan,China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039327013","display_name":"Changshuo Wang","orcid":"https://orcid.org/0000-0002-9970-191X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changshuo Wang","raw_affiliation_strings":["Shandong University,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong University,Jinan,China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041574770","display_name":"Lei Meng","orcid":"https://orcid.org/0000-0003-2672-8406"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Meng","raw_affiliation_strings":["Shandong University,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong University,Jinan,China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080015931","display_name":"Xiangxu Meng","orcid":"https://orcid.org/0000-0001-9842-4044"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxu Meng","raw_affiliation_strings":["Shandong University,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong University,Jinan,China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009433044"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16472953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.991599977016449,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.991599977016449,"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":0.9879999756813049,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9776999950408936,"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/computer-science","display_name":"Computer science","score":0.6639503240585327},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5640572309494019},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5261411666870117},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5230927467346191},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4315497875213623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4147643446922302},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3360012173652649},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07189026474952698},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0556674599647522},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05270549654960632}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639503240585327},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5640572309494019},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5261411666870117},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5230927467346191},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4315497875213623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4147643446922302},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3360012173652649},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07189026474952698},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0556674599647522},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05270549654960632},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688052","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2775347418","https://openalex.org/W2779427294","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W2069885731","https://openalex.org/W2563206327","https://openalex.org/W2108687567","https://openalex.org/W2789220062"],"abstract_inverted_index":{"In":[0],"recent":[1],"research":[2],"literature,":[3],"the":[4,38,46,59,63,80,94,103],"layout":[5,117],"to":[6,84],"image":[7,49],"domain":[8],"has":[9],"gained":[10],"significant":[11],"traction.":[12],"Research":[13],"based":[14,74],"on":[15,37,75,134],"GANs":[16],"can":[17],"generate":[18],"complete":[19],"images,":[20],"but":[21],"there":[22],"are":[23],"still":[24,42],"issues":[25],"with":[26],"insufficient":[27],"details":[28,50,109],"and":[29,88,110,136,148],"overall":[30,64,149],"quality":[31,47],"not":[32],"being":[33],"high.":[34],"Diffusion":[35],"models,":[36],"other":[39],"hand,":[40],"challenges":[41],"exist":[43],"in":[44,51],"ensuring":[45,58],"of":[48,62],"complex":[52],"scene":[53],"regions,":[54],"as":[55,57],"well":[56],"smooth":[60],"expression":[61],"semantic":[65,91,111],"information.":[66,112],"To":[67],"address":[68],"these":[69],"challenges,":[70],"we":[71],"propose":[72],"LayoutDM":[73],"multi-scale":[76],"diffusion,":[77],"which":[78],"employs":[79],"Parallel":[81],"Sampling":[82],"Module":[83],"enhance":[85],"local":[86],"precision":[87],"ensures":[89],"global":[90],"coherence":[92],"through":[93],"Semantic":[95],"Coherence":[96],"Module.":[97],"Significantly,":[98],"our":[99,114,141],"approach":[100,142],"generates":[101],"within":[102],"visible":[104],"space,":[105],"progressively":[106],"revealing":[107],"more":[108],"Simultaneously,":[113],"method":[115],"enhances":[116],"part":[118],"handling":[119],"via":[120],"parallel":[121],"region-wise":[122],"clip":[123],"guidance,":[124],"achieving":[125],"strong":[126],"zero-shot":[127],"generation":[128,147],"without":[129],"direct":[130],"training":[131],"samples.":[132],"Tests":[133],"COCO-stuff":[135],"VG":[137],"datasets":[138],"confirm":[139],"that":[140],"achieves":[143],"both":[144],"fine-grained":[145],"object":[146],"visual":[150],"effectiveness.":[151]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}