{"id":"https://openalex.org/W4385527149","doi":"https://doi.org/10.1145/3588432.3591513","title":"Zero-shot Image-to-Image Translation","display_name":"Zero-shot Image-to-Image Translation","publication_year":2023,"publication_date":"2023-07-19","ids":{"openalex":"https://openalex.org/W4385527149","doi":"https://doi.org/10.1145/3588432.3591513"},"language":"en","primary_location":{"id":"doi:10.1145/3588432.3591513","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591513","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591513","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591513","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030443008","display_name":"Gaurav Parmar","orcid":"https://orcid.org/0000-0001-8640-2243"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Parmar","raw_affiliation_strings":["Carnegie Mellon University, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-8640-2243","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, United States of America","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101960524","display_name":"Krishna Kumar Singh","orcid":"https://orcid.org/0000-0002-8066-6835"},"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":"Krishna Kumar Singh","raw_affiliation_strings":["Adobe, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-8066-6835","affiliations":[{"raw_affiliation_string":"Adobe, United States of America","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079334071","display_name":"Richard Zhang","orcid":"https://orcid.org/0000-0003-2507-4674"},"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":"Richard Zhang","raw_affiliation_strings":["Adobe, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2507-4674","affiliations":[{"raw_affiliation_string":"Adobe, United States of America","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447637","display_name":"Yijun Li","orcid":"https://orcid.org/0000-0001-7295-8750"},"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":"Yijun Li","raw_affiliation_strings":["Adobe, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-7295-8750","affiliations":[{"raw_affiliation_string":"Adobe, United States of America","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085050428","display_name":"Jingwan Lu","orcid":"https://orcid.org/0000-0002-3598-9918"},"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":"Jingwan Lu","raw_affiliation_strings":["Adobe, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-3598-9918","affiliations":[{"raw_affiliation_string":"Adobe, United States of America","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102883508","display_name":"Jun-Yan Zhu","orcid":"https://orcid.org/0000-0001-8504-3410"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun-Yan Zhu","raw_affiliation_strings":["Carnegie Mellon University, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-8504-3410","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, United States of America","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":329,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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":0.9957000017166138,"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":0.9957000017166138,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9693999886512756,"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":0.9596999883651733,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.8826737403869629},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8230392932891846},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.7093760967254639},{"id":"https://openalex.org/keywords/image-translation","display_name":"Image translation","score":0.6988310813903809},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5991340279579163},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5714557766914368},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5367618203163147},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5243568420410156},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5148207545280457},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5071799755096436},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.42532944679260254},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41352641582489014},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08080267906188965}],"concepts":[{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.8826737403869629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230392932891846},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.7093760967254639},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.6988310813903809},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5991340279579163},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5714557766914368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367618203163147},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5243568420410156},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5148207545280457},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5071799755096436},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.42532944679260254},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41352641582489014},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08080267906188965},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588432.3591513","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591513","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591513","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3588432.3591513","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591513","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591513","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307786","display_name":"Adobe Systems","ror":"https://ror.org/059tvcg64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385527149.pdf","grobid_xml":"https://content.openalex.org/works/W4385527149.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1584270973","https://openalex.org/W2519536754","https://openalex.org/W2961363059","https://openalex.org/W2962785568","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2985068832","https://openalex.org/W3013170474","https://openalex.org/W3023742835","https://openalex.org/W3035355202","https://openalex.org/W3094954720","https://openalex.org/W3109910669","https://openalex.org/W3122887115","https://openalex.org/W3135367836","https://openalex.org/W3153469116","https://openalex.org/W3165647589","https://openalex.org/W3177525997","https://openalex.org/W4285981780","https://openalex.org/W4312294878","https://openalex.org/W4312933868"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360","https://openalex.org/W4317695495","https://openalex.org/W4387506531"],"abstract_inverted_index":{"Large-scale":[0],"text-to-image":[1,187],"generative":[2],"models":[3,18,51],"have":[4],"shown":[5],"their":[6],"remarkable":[7],"ability":[8],"to":[9,34,119,133],"synthesize":[10],"diverse,":[11],"high-quality":[12],"images.":[13],"However,":[14],"directly":[15,182],"applying":[16],"these":[17,178],"for":[19,25,32,161,177],"real":[20,163],"image":[21,127,166],"editing":[22,97],"remains":[23],"challenging":[24],"two":[26],"reasons.":[27],"First,":[28],"it":[29],"is":[30],"hard":[31],"users":[33],"craft":[35],"a":[36,143],"perfect":[37],"text":[38,105],"prompt":[39],"depicting":[40],"every":[41],"visual":[42],"detail":[43],"in":[44,56,70,103],"the":[45,63,86,104,110,121,125,129,139,184],"input":[46,64,126],"image.":[47],"Second,":[48],"while":[49],"existing":[50,157,185],"can":[52,84,181],"introduce":[53,67,77],"desirable":[54],"changes":[55,69],"certain":[57],"regions,":[58],"they":[59],"often":[60],"dramatically":[61],"alter":[62],"content":[65,89,111],"and":[66,151,158,164,180],"unexpected":[68],"unwanted":[71],"regions.":[72],"In":[73,168],"this":[74],"work,":[75],"we":[76,113,137],"pix2pix-zero,":[78],"an":[79],"image-to-image":[80],"translation":[81],"method":[82,155,171],"that":[83,99,153],"preserve":[85,109],"original":[87],"image\u2019s":[88],"without":[90],"manual":[91],"prompting.":[92],"We":[93,147],"first":[94],"automatically":[95],"discover":[96],"directions":[98],"reflect":[100],"desired":[101],"edits":[102,179],"embedding":[106],"space.":[107],"To":[108],"structure,":[112],"propose":[114],"cross-attention":[115,122],"guidance,":[116],"which":[117],"aims":[118],"retain":[120],"maps":[123],"of":[124],"throughout":[128],"diffusion":[130,140,188],"process.":[131],"Finally,":[132],"enable":[134],"interactive":[135],"editing,":[136],"distill":[138],"model":[141],"into":[142],"fast":[144],"conditional":[145],"GAN.":[146],"conduct":[148],"extensive":[149],"experiments":[150],"show":[152],"our":[154,170],"outperforms":[156],"concurrent":[159],"works":[160],"both":[162],"synthetic":[165],"editing.":[167],"addition,":[169],"does":[172],"not":[173],"need":[174],"additional":[175],"training":[176],"use":[183],"pre-trained":[186],"model.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":25},{"year":2025,"cited_by_count":102},{"year":2024,"cited_by_count":167},{"year":2023,"cited_by_count":35}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}