{"id":"https://openalex.org/W4400819434","doi":"https://doi.org/10.1145/3658150","title":"Transparent Image Layer Diffusion using Latent Transparency","display_name":"Transparent Image Layer Diffusion using Latent Transparency","publication_year":2024,"publication_date":"2024-07-19","ids":{"openalex":"https://openalex.org/W4400819434","doi":"https://doi.org/10.1145/3658150"},"language":"en","primary_location":{"id":"doi:10.1145/3658150","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3658150","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/A5079385579","display_name":"Lvmin Zhang","orcid":"https://orcid.org/0000-0003-3503-5791"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lvmin Zhang","raw_affiliation_strings":["Stanford University, Stanford, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3503-5791","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States of America","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045835385","display_name":"Maneesh Agrawala","orcid":"https://orcid.org/0000-0002-8996-7327"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maneesh Agrawala","raw_affiliation_strings":["Stanford University, Stanford, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-8996-7327","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States of America","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":27.6917,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.99608511,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"43","issue":"4","first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9991000294685364,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9983999729156494,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9909999966621399,"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":0.7281466722488403},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.6516252756118774},{"id":"https://openalex.org/keywords/latent-image","display_name":"Latent image","score":0.5895633697509766},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.4587031602859497},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3767964541912079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.352460116147995},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.162562757730484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281466722488403},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.6516252756118774},{"id":"https://openalex.org/C205372313","wikidata":"https://www.wikidata.org/wiki/Q355645","display_name":"Latent image","level":3,"score":0.5895633697509766},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.4587031602859497},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3767964541912079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.352460116147995},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.162562757730484},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3658150","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3658150","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":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2000514066","https://openalex.org/W2190424233","https://openalex.org/W2811296358","https://openalex.org/W2898387366","https://openalex.org/W2903549434","https://openalex.org/W2948070565","https://openalex.org/W2962737447","https://openalex.org/W2962793481","https://openalex.org/W2963304750","https://openalex.org/W2964326990","https://openalex.org/W3034684802","https://openalex.org/W3107032263","https://openalex.org/W3110257065","https://openalex.org/W3171358896","https://openalex.org/W3216352822","https://openalex.org/W4240870799","https://openalex.org/W4248023924","https://openalex.org/W4251617126","https://openalex.org/W4288089799","https://openalex.org/W4293932153","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4385283764","https://openalex.org/W4385681234","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4387609219","https://openalex.org/W4388009985","https://openalex.org/W4390873195","https://openalex.org/W4390873316"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,102,118],"present":[1],"an":[2],"approach":[3],"enabling":[4],"large-scale":[5],"pretrained":[6,44,77],"latent":[7,40,45,65,73,83,100,121],"diffusion":[8,46,56,84],"models":[9],"to":[10,70,126,135,140,194],"generate":[11],"transparent":[12,20,25,91,108,170,190,197],"images.":[13],"The":[14,27],"method":[15,28],"allows":[16],"generation":[17],"of":[18,23,42,53,75,152,187],"single":[19],"images":[21,191],"or":[22,132],"multiple":[24],"layers.":[26],"learns":[29],"a":[30,43,64,90,114],"\"latent":[31],"transparency\"":[32],"that":[33,120,160],"encodes":[34],"alpha":[35],"channel":[36],"transparency":[37,62,122],"into":[38,89],"the":[39,50,54,60,71,76,98,104,185],"manifold":[41],"model.":[47,78],"It":[48],"preserves":[49],"production-ready":[51],"quality":[52,186],"large":[55],"model":[57,85,105],"by":[58,94],"regulating":[59],"added":[61],"as":[63,177],"offset":[66],"with":[67,97,106],"minimal":[68],"changes":[69],"original":[72],"distribution":[74],"In":[79],"this":[80],"way,":[81],"any":[82],"can":[86,123],"be":[87,124,133],"converted":[88],"image":[92,109,130],"generator":[93],"finetuning":[95],"it":[96],"adjusted":[99],"space.":[101],"train":[103],"1M":[107],"layer":[110,145,148,153],"pairs":[111],"collected":[112],"using":[113],"human-in-the-loop":[115],"collection":[116],"scheme.":[117],"show":[119],"applied":[125],"different":[127],"open":[128],"source":[129],"generators,":[131],"adapted":[134],"various":[136],"conditional":[137],"control":[138,151],"systems":[139],"achieve":[141],"applications":[142],"like":[143,199],"foreground/background-conditioned":[144],"generation,":[146,149],"joint":[147],"structural":[150],"contents,":[154],"etc.":[155],"A":[156],"user":[157],"study":[158],"finds":[159],"in":[161],"most":[162],"cases":[163],"(97%)":[164],"users":[165],"prefer":[166],"our":[167,188],"natively":[168],"generated":[169,189],"content":[171],"over":[172],"previous":[173],"ad-hoc":[174],"solutions":[175],"such":[176],"generating":[178],"and":[179],"then":[180],"matting.":[181],"Users":[182],"also":[183],"report":[184],"is":[192],"comparable":[193],"real":[195],"commercial":[196],"assets":[198],"Adobe":[200],"Stock.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}