{"id":"https://openalex.org/W4386076403","doi":"https://doi.org/10.1109/cvpr52729.2023.02154","title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation","display_name":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386076403","doi":"https://doi.org/10.1109/cvpr52729.2023.02154"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.02154","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2303.17189","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088316957","display_name":"Guangcong Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangcong Zheng","raw_affiliation_strings":["College of Computer Science & Technology, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science & Technology, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039357854","display_name":"Xianpan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianpan Zhou","raw_affiliation_strings":["Polytechnic Institute, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Polytechnic Institute, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429593","display_name":"Xuewei Li","orcid":"https://orcid.org/0000-0002-3414-8754"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuewei Li","raw_affiliation_strings":["College of Computer Science & Technology, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science & Technology, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101500719","display_name":"Zhongang Qi","orcid":"https://orcid.org/0000-0001-8298-4063"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongang Qi","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100407758","display_name":"Xi Li","orcid":"https://orcid.org/0000-0003-3023-1662"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I4210137766","display_name":"Institute for Advanced Study","ror":"https://ror.org/03xg85719","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210137766"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Xi Li","raw_affiliation_strings":["College of Computer Science & Technology, Zhejiang University","Shanghai AI Lab","Shanghai Institute for Advanced Study of Zhejiang University","Zhejiang-Singapore Innovation and AI Joint Research Lab"],"affiliations":[{"raw_affiliation_string":"College of Computer Science & Technology, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Institute for Advanced Study of Zhejiang University","institution_ids":["https://openalex.org/I4210137766"]},{"raw_affiliation_string":"Zhejiang-Singapore Innovation and AI Joint Research Lab","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.606,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.999956,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"22490","last_page":"22499"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9992,"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":0.9992,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9989,"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":0.9974,"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/fuse","display_name":"Fuse (electrical)","score":0.5309607},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47743282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78513026},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6477503},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5941447},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.59387493},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.55773824},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5309607},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5223842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5111969},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5060298},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47743282},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09370646},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0818125},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.07888135},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.02154","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2303.17189","pdf_url":"https://arxiv.org/pdf/2303.17189","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2303.17189","pdf_url":"https://arxiv.org/pdf/2303.17189","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"U20A20222"},{"funder":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China","award_id":"2020AAA0107400"}],"datasets":[],"versions":[],"referenced_works_count":48,"referenced_works":["https://openalex.org/W2129069237","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2561196672","https://openalex.org/W2763421725","https://openalex.org/W2891802882","https://openalex.org/W2945027741","https://openalex.org/W2959300817","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2962974533","https://openalex.org/W2963073614","https://openalex.org/W2963184176","https://openalex.org/W2963373786","https://openalex.org/W2963684088","https://openalex.org/W2963800363","https://openalex.org/W2964201867","https://openalex.org/W2964216930","https://openalex.org/W2965833116","https://openalex.org/W2983248633","https://openalex.org/W2987919422","https://openalex.org/W2999219213","https://openalex.org/W3018757597","https://openalex.org/W3036167779","https://openalex.org/W3110257065","https://openalex.org/W3155072588","https://openalex.org/W3162926177","https://openalex.org/W3163884521","https://openalex.org/W3168053944","https://openalex.org/W3201409833","https://openalex.org/W3203593958","https://openalex.org/W4221139906","https://openalex.org/W4225759859","https://openalex.org/W4226125322","https://openalex.org/W4281485151","https://openalex.org/W4281661987","https://openalex.org/W4288099666","https://openalex.org/W4293403276","https://openalex.org/W4300838842","https://openalex.org/W4306809142","https://openalex.org/W4309801456","https://openalex.org/W4312497550","https://openalex.org/W4312680947","https://openalex.org/W4312933868","https://openalex.org/W4312995674","https://openalex.org/W4360884927","https://openalex.org/W4387195417"],"related_works":["https://openalex.org/W2561315646","https://openalex.org/W2554790198","https://openalex.org/W2411113819","https://openalex.org/W2391745328","https://openalex.org/W2332386680","https://openalex.org/W2248621902","https://openalex.org/W2140812588","https://openalex.org/W2095903272","https://openalex.org/W2072887367","https://openalex.org/W2036697162"],"abstract_inverted_index":{"Recently,":[0],"diffusion":[1,54],"models":[2],"have":[3],"achieved":[4],"great":[5],"success":[6],"in":[7,107],"image":[8,20,78,87,96],"synthesis.":[9],"However,":[10],"when":[11],"it":[12],"comes":[13],"to":[14,30,83,101,123,132],"the":[15,36,68,73,94,104,125,141,152],"layout-to-image":[16],"generation":[17,62],"where":[18],"an":[19],"often":[21],"has":[22],"a":[23,45,53,85,98,108],"complex":[24],"scene":[25],"of":[26,77],"multiple":[27,128],"objects,":[28],"how":[29],"make":[31],"strong":[32],"control":[33],"over":[34],"both":[35],"global":[37],"layout":[38,100,106],"map":[39],"and":[40,64,79,92,116,130,135,164],"each":[41],"detailed":[42],"object":[43],"remains":[44],"challenging":[46],"task.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,81],"propose":[52,82],"model":[55,124],"named":[56],"LayoutDiffusion":[57,150],"that":[58,148],"can":[59],"obtain":[60],"higher":[61],"quality":[63],"greater":[65],"controllability":[66],"than":[67],"previous":[69,153],"works.":[70],"To":[71],"overcome":[72],"difficult":[74],"multimodal":[75],"fusion":[76],"layout,":[80],"construct":[84],"structural":[86],"patch":[88],"with":[89,103],"region":[90],"information":[91],"transform":[93],"patched":[95],"into":[97],"special":[99],"fuse":[102],"normal":[105],"unified":[109],"form.":[110],"Moreover,":[111],"Layout":[112],"Fusion":[113],"Module":[114],"(LFM)":[115],"Object-aware":[117],"Cross":[118],"Attention":[119],"(OaCA)":[120],"are":[121],"proposed":[122],"relationship":[126],"among":[127],"objects":[129],"designed":[131],"be":[133],"object-aware":[134],"position-sensitive,":[136],"allowing":[137],"for":[138],"precisely":[139],"controlling":[140],"spatial":[142],"related":[143],"information.":[144],"Extensive":[145],"experiments":[146],"show":[147],"our":[149],"out-performs":[151],"SOTA":[154],"methods":[155],"on":[156,162,166],"FID,":[157],"CAS":[158],"by":[159],"relatively":[160],"46.35%,26.70%":[161],"COCO-stuff":[163],"44.29%,41.82%":[165],"VG.":[167],"Code":[168],"is":[169],"available":[170],"at":[171],"https://github.com/ZGCTroy/LayoutDiffusion.":[172]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4386076403","counts_by_year":[{"year":2024,"cited_by_count":43},{"year":2023,"cited_by_count":5}],"updated_date":"2025-01-04T10:00:32.260240","created_date":"2023-08-23"}