{"id":"https://openalex.org/W4417000851","doi":"https://doi.org/10.1145/3763341","title":"MALeR: Improving Compositional Fidelity in Layout-Guided Generation","display_name":"MALeR: Improving Compositional Fidelity in Layout-Guided Generation","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W4417000851","doi":"https://doi.org/10.1145/3763341"},"language":"en","primary_location":{"id":"doi:10.1145/3763341","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3763341","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-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/A5108568541","display_name":"S Saxena","orcid":"https://orcid.org/0009-0009-4964-2454"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shivank Saxena","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068290564","display_name":"Dhruv Srivastava","orcid":"https://orcid.org/0000-0002-6789-4390"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]},{"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":["IN","US"],"is_corresponding":false,"raw_author_name":"Dhruv Srivastava","raw_affiliation_strings":["Adobe Research, Hyderabad, India","International Institute of Information Technology, Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Adobe Research, Hyderabad, India","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003125633","display_name":"Makarand Tapaswi","orcid":"https://orcid.org/0000-0001-8800-9015"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Makarand Tapaswi","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108568541"],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42069037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":"6","first_page":"1","last_page":"12"},"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":0.9567000269889832,"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":0.9567000269889832,"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":0.007799999788403511,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0071000000461936,"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/rendering","display_name":"Rendering (computer graphics)","score":0.7379999756813049},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6061999797821045},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4307999908924103},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.33959999680519104},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3357999920845032},{"id":"https://openalex.org/keywords/morphing","display_name":"Morphing","score":0.3264999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816100001335144},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7379999756813049},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763000249862671},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4440999925136566},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.37779998779296875},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3763341","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3763341","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W4385270985","https://openalex.org/W4389205309","https://openalex.org/W4390873054"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,49,133,148],"text-to-image":[3],"models":[4],"have":[5,39],"enabled":[6],"a":[7,26,84,93,115],"new":[8],"era":[9],"of":[10,89,127,167],"creative":[11],"and":[12,23,64,96,138,153,172],"controllable":[13],"image":[14],"generation.":[15],"However,":[16,42],"generating":[17,165],"compositional":[18,50,135,149],"scenes":[19,168],"with":[20,129,169],"multiple":[21,130,170,173],"subjects":[22,53,102,128,171],"attributes":[24,69,174],"remains":[25],"significant":[27],"challenge.":[28],"To":[29],"enhance":[30],"user":[31],"control":[32],"over":[33],"subject":[34],"placement,":[35],"several":[36],"layout-guided":[37],"methods":[38,44],"been":[40],"proposed.":[41],"these":[43,90],"face":[45],"numerous":[46],"challenges,":[47],"particularly":[48,162],"scenes.":[51,136],"Unintended":[52],"often":[54],"appear":[55],"outside":[56,105],"the":[57,106],"layouts,":[58,98],"generated":[59],"images":[60,166],"can":[61],"be":[62],"out-of-distribution":[63],"contain":[65],"unnatural":[66],"artifacts,":[67],"or":[68],"bleed":[70],"across":[71],"subjects,":[72],"leading":[73],"to":[74,157],"incorrect":[75],"visual":[76],"outputs.":[77],"In":[78],"this":[79],"work,":[80],"we":[81,113],"propose":[82,114],"MALeR,":[83],"method":[85,100,144],"that":[86,120,142],"addresses":[87],"each":[88],"challenges.":[91],"Given":[92],"text":[94],"prompt":[95],"corresponding":[97],"our":[99,143],"prevents":[101,121],"from":[103],"appearing":[104],"given":[107],"layouts":[108],"while":[109],"being":[110],"in-distribution.":[111],"Additionally,":[112],"masked,":[116],"attribute-aware":[117],"binding":[118,155],"mechanism":[119],"attribute":[122,154],"leakage,":[123],"enabling":[124],"accurate":[125],"rendering":[126],"attributes,":[131],"even":[132],"complex":[134],"Qualitative":[137],"quantitative":[139],"evaluation":[140],"demonstrates":[141],"achieves":[145],"superior":[146],"performance":[147],"accuracy,":[150],"generation":[151],"consistency,":[152],"compared":[156],"previous":[158],"work.":[159],"MALeR":[160],"is":[161],"adept":[163],"at":[164],"per":[175],"subject.":[176]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-04T00:00:00"}