{"id":"https://openalex.org/W4413145108","doi":"https://doi.org/10.1109/cvpr52734.2025.01701","title":"Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation","display_name":"Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145108","doi":"https://doi.org/10.1109/cvpr52734.2025.01701"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100441156","display_name":"Hyunsoo Kim","orcid":"https://orcid.org/0000-0003-2859-0252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyunsoo Kim","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770745","display_name":"Donghyun Kim","orcid":"https://orcid.org/0000-0001-6267-4746"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donghyun Kim","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385540","display_name":"Suhyun Kim","orcid":"https://orcid.org/0000-0002-3272-114X"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Suhyun Kim","raw_affiliation_strings":["Kyung Hee University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18250","last_page":"18259"},"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":0.9287999868392944,"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":0.9287999868392944,"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":0.919700026512146,"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/analogy","display_name":"Analogy","score":0.7836138606071472},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.6103720664978027},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.593776524066925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4923950433731079},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4176808297634125},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36241060495376587},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3610507845878601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34481629729270935},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33082854747772217},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.12337315082550049},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10355889797210693}],"concepts":[{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.7836138606071472},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.6103720664978027},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.593776524066925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4923950433731079},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4176808297634125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36241060495376587},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3610507845878601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34481629729270935},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33082854747772217},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.12337315082550049},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10355889797210693},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2392206215","https://openalex.org/W2365201483","https://openalex.org/W2355561779","https://openalex.org/W2352407775","https://openalex.org/W108701362","https://openalex.org/W2186567693","https://openalex.org/W2469799552","https://openalex.org/W2768582344","https://openalex.org/W4308645358","https://openalex.org/W28964973"],"abstract_inverted_index":{"How":[0],"can":[1],"we":[2,82,145,176,189],"generate":[3,105,221],"an":[4,139],"image":[5],"B<sup":[6,19,108,224],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[7,14,20,27,97,109,154,225],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u2032</sup>":[8,15,28,98,155,226],"that":[9,88,207],"satisfies":[10],"A":[11,94,151],":":[12,18],"A<sup":[13,96,153],"::":[16],"B":[17,103],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u2032</sup>,":[21],"given":[22],"the":[23,91,123,148,160,169,191],"input":[24,131],"images":[25],"A,A<sup":[26],"and":[29,95,99,152,156,196,215],"B?":[30],"Recent":[31],"works":[32],"have":[33],"tackled":[34],"this":[35,80,143],"challenge":[36],"through":[37,180],"approaches":[38],"like":[39],"visual":[40,44],"in-context":[41],"learning":[42],"or":[43,75],"instruction.":[45],"However,":[46],"these":[47],"methods":[48],"are":[49],"typically":[50],"limited":[51],"to":[52,72,102,104,119,132,185,220],"specific":[53],"models":[54,63],"(e.g.":[55,64],"In-structPix2Pix.":[56],"Inpainting":[57],"models)":[58],"rather":[59,136],"than":[60,137],"general":[61],"diffusion":[62,134],"Stable":[65],"Diffusion,":[66],"SDXL).":[67],"This":[68],"dependency":[69],"may":[70],"lead":[71],"inherited":[73],"biases":[74],"lower":[76],"editing":[77],"capabilities.":[78],"In":[79],"paper,":[81],"propose":[83,190],"Difference":[84,149,208],"Inversion,":[85],"a":[86,106,126,165,173,228],"method":[87],"isolates":[89],"only":[90],"difference":[92],"from":[93],"applies":[100],"it":[101,116,158,179],"plausible":[107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u2032</sup>.":[110],"To":[111,142,171],"address":[112],"model":[113],"de":[114],"pendency,":[115],"is":[117],"crucial":[118],"structure":[120],"prompts":[121],"in":[122,227],"form":[124],"of":[125,162,168,200],"\"Full":[127],"Prompt\"":[128],"suitable":[129],"for":[130],"stable":[133],"models,":[135],"using":[138],"\"Instruction":[140],"Prompt\".":[141],"end,":[144],"accurately":[146],"extract":[147,172],"between":[150],"combine":[157],"with":[159],"prompt":[161],"B,":[163],"enabling":[164],"plug-and-play":[166],"application":[167],"difference.":[170],"precise":[174],"difference,":[175],"first":[177],"identify":[178],"1)":[181],"Delta":[182],"Interpolation.":[183],"Additionally,":[184],"ensure":[186],"accurate":[187],"training,":[188],"2)":[192],"Token":[193,201],"Consistency":[194],"Loss":[195],"3)":[197],"Zero":[198],"Initialization":[199],"Embeddings.":[202],"Our":[203],"extensive":[204],"experiments":[205],"demonstrate":[206],"Inversion":[209],"outperforms":[210],"existing":[211],"baselines":[212],"both":[213],"quantitatively":[214],"qualitatively,":[216],"indicating":[217],"its":[218],"ability":[219],"more":[222],"feasible":[223],"model-agnostic":[229],"manner.":[230]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}