{"id":"https://openalex.org/W4386071676","doi":"https://doi.org/10.1109/cvpr52729.2023.02152","title":"SceneComposer: Any-Level Semantic Image Synthesis","display_name":"SceneComposer: Any-Level Semantic Image Synthesis","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386071676","doi":"https://doi.org/10.1109/cvpr52729.2023.02152"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.02152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.02152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5105217290","display_name":"Yu Zeng","orcid":"https://orcid.org/0009-0000-0263-2990"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Zeng","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564904","display_name":"Zhe Lin","orcid":"https://orcid.org/0000-0003-1154-9907"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Lin","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036510129","display_name":"Jianming Zhang","orcid":"https://orcid.org/0000-0002-9954-6294"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianming Zhang","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102334908","display_name":"Qing Liu","orcid":"https://orcid.org/0000-0003-0879-7440"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Liu","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024767797","display_name":"John Collomosse","orcid":"https://orcid.org/0000-0003-3580-4685"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Collomosse","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076366439","display_name":"Jason Kuen","orcid":"https://orcid.org/0000-0001-5099-8145"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Kuen","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004716468","display_name":"Vishal M. Patel","orcid":"https://orcid.org/0000-0002-5239-692X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishal M. Patel","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5105217290"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":4.5505,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.96069881,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"22468","last_page":"22478"},"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":0.9991999864578247,"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":0.9991999864578247,"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":0.9976000189781189,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9907000064849854,"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":0.8368409872055054},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6347675323486328},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5577048659324646},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5327252149581909},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5074309706687927},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4969678223133087},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.4659249484539032},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4638870358467102},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45240598917007446},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4370657205581665},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4304952323436737},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42674243450164795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41728609800338745},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.165700763463974},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09253400564193726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368409872055054},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6347675323486328},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5577048659324646},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5327252149581909},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5074309706687927},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4969678223133087},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4659249484539032},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4638870358467102},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45240598917007446},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4370657205581665},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4304952323436737},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42674243450164795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41728609800338745},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.165700763463974},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09253400564193726},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52729.2023.02152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.02152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":75,"referenced_works":["https://openalex.org/W8437397","https://openalex.org/W2423557781","https://openalex.org/W2561196672","https://openalex.org/W2752796333","https://openalex.org/W2952122856","https://openalex.org/W2962770929","https://openalex.org/W2962974533","https://openalex.org/W2963073614","https://openalex.org/W2963150697","https://openalex.org/W2963522749","https://openalex.org/W2963800363","https://openalex.org/W2964024144","https://openalex.org/W2964216930","https://openalex.org/W2965289598","https://openalex.org/W2965833116","https://openalex.org/W2987919422","https://openalex.org/W2990269423","https://openalex.org/W2991044292","https://openalex.org/W2993433871","https://openalex.org/W3005755659","https://openalex.org/W3034667262","https://openalex.org/W3035083401","https://openalex.org/W3035574324","https://openalex.org/W3106333289","https://openalex.org/W3108367042","https://openalex.org/W3141117710","https://openalex.org/W3158252298","https://openalex.org/W3174711319","https://openalex.org/W3176381160","https://openalex.org/W3180268133","https://openalex.org/W3180355996","https://openalex.org/W3209453723","https://openalex.org/W3215495615","https://openalex.org/W4224035735","https://openalex.org/W4226125322","https://openalex.org/W4231697575","https://openalex.org/W4281485151","https://openalex.org/W4283388932","https://openalex.org/W4294791355","https://openalex.org/W4297488929","https://openalex.org/W4306820534","https://openalex.org/W4308163867","https://openalex.org/W4312388283","https://openalex.org/W4312529868","https://openalex.org/W4312911498","https://openalex.org/W4312933868","https://openalex.org/W4312956471","https://openalex.org/W4312977351","https://openalex.org/W4312995674","https://openalex.org/W4313148383","https://openalex.org/W6600324250","https://openalex.org/W6640963894","https://openalex.org/W6679045638","https://openalex.org/W6713645886","https://openalex.org/W6728889164","https://openalex.org/W6755312952","https://openalex.org/W6758114194","https://openalex.org/W6773451322","https://openalex.org/W6779823529","https://openalex.org/W6780593937","https://openalex.org/W6782826594","https://openalex.org/W6783713337","https://openalex.org/W6788603129","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6796242362","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6839517220","https://openalex.org/W6839643428","https://openalex.org/W6840815571","https://openalex.org/W6846007759","https://openalex.org/W6846655393"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W1981780420","https://openalex.org/W2063982682","https://openalex.org/W2182707996"],"abstract_inverted_index":{"We":[0,105],"propose":[1],"a":[2,21,120,126,131,146,161],"new":[3,117],"framework":[4,58,87],"for":[5,122],"conditional":[6],"image":[7],"synthesis":[8],"from":[9,17],"semantic":[10,23,38],"layouts":[11,166],"of":[12,34,93,101],"any":[13],"precision":[14,46,139],"levels,":[15,47],"ranging":[16],"pure":[18],"text":[19,42,132],"to":[20,61,110,136,151],"2D":[22],"canvas":[24],"with":[25,40,68,115,167],"precise":[26],"shapes.":[27],"More":[28],"specifically,":[29],"the":[30,54,65,78,83,112,156,176,184],"input":[31],"layout":[32,185],"consists":[33],"one":[35],"or":[36],"more":[37],"regions":[39],"free-form":[41],"descriptions":[43],"and":[44,72,97,130,142,145,170,189],"adjustable":[45],"which":[48],"can":[49,179],"be":[50],"set":[51],"based":[52],"on":[53],"desired":[55],"controllability.":[56],"The":[57],"naturally":[59],"reduces":[60],"text-to-image":[62],"(T2I)":[63],"at":[64,77,98,186],"lowest":[66],"level":[67],"no":[69],"shape":[70],"information,":[71],"it":[73],"becomes":[74],"segmentation-to-image":[75],"(S2I)":[76],"highest":[79],"level.":[80],"By":[81],"supporting":[82],"levels":[84],"in-between,":[85],"our":[86],"is":[88],"flexible":[89],"in":[90],"assisting":[91],"users":[92],"different":[94,99],"drawing":[95],"expertise":[96],"stages":[100],"their":[102],"creative":[103],"workflow.":[104],"introduce":[106],"several":[107],"novel":[108],"techniques":[109],"address":[111],"challenges":[113],"coming":[114],"this":[116],"setup,":[118],"including":[119],"pipeline":[121],"collecting":[123],"training":[124],"data;":[125],"precision-encoded":[127],"mask":[128],"pyramid":[129],"feature":[133],"map":[134],"representation":[135],"jointly":[137],"encode":[138],"level,":[140],"semantics,":[141],"composition":[143],"information;":[144],"multi-scale":[147],"guided":[148],"diffusion":[149],"model":[150],"synthesize":[152],"images.":[153],"To":[154],"evaluate":[155],"proposed":[157,177],"method,":[158],"we":[159],"collect":[160],"test":[162],"dataset":[163],"containing":[164],"user-drawn":[165],"diverse":[168],"scenes":[169],"styles.":[171],"Experimental":[172],"results":[173],"show":[174],"that":[175],"method":[178],"generate":[180],"high-quality":[181],"images":[182],"following":[183],"given":[187],"precision,":[188],"compares":[190],"favorably":[191],"against":[192],"existing":[193],"methods.":[194],"Project":[195],"page":[196],"https://zengxianyu.github.io/scenec/":[197]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}