{"id":"https://openalex.org/W4387635233","doi":"https://doi.org/10.48550/arxiv.2310.08094","title":"SingleInsert: Inserting New Concepts from a Single Image into Text-to-Image Models for Flexible Editing","display_name":"SingleInsert: Inserting New Concepts from a Single Image into Text-to-Image Models for Flexible Editing","publication_year":2023,"publication_date":"2023-10-12","ids":{"openalex":"https://openalex.org/W4387635233","doi":"https://doi.org/10.48550/arxiv.2310.08094"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.08094","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08094","pdf_url":"https://arxiv.org/pdf/2310.08094","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.08094","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024918504","display_name":"Zijie Wu","orcid":"https://orcid.org/0000-0002-0675-6525","observed_orcids":["https://orcid.org/0000-0002-0675-6525","https://orcid.org/0009-0004-1171-9763"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033661654","display_name":"Chaohui Yu","orcid":"https://orcid.org/0000-0002-7852-4491","observed_orcids":["https://orcid.org/0000-0002-7852-4491"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Chaohui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100297954","display_name":"Zhu Zhen","orcid":"https://orcid.org/0009-0007-2075-0457","observed_orcids":["https://orcid.org/0009-0007-2075-0457"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644279","display_name":"Fan Wang","orcid":"https://orcid.org/0000-0003-0020-1470","observed_orcids":["https://orcid.org/0000-0003-0020-1470","https://orcid.org/0000-0002-9836-0893","https://orcid.org/0009-0002-9458-7430"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940","observed_orcids":["https://orcid.org/0000-0002-3449-5940"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":1.0,"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":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.0,"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/text-to-image-models","display_name":"text-to-image models","score":0.8270000219345093},{"id":"https://openalex.org/keywords/single-image-editing","display_name":"single-image editing","score":0.6589999794960022},{"id":"https://openalex.org/keywords/embedding-fine-tuning","display_name":"embedding fine-tuning","score":0.7049999833106995},{"id":"https://openalex.org/keywords/language-drift","display_name":"language drift","score":0.8190000057220459},{"id":"https://openalex.org/keywords/novel-view-synthesis","display_name":"novel view synthesis","score":0.8820000290870667},{"id":"https://openalex.org/keywords/visual-fidelity","display_name":"visual fidelity","score":0.5720000267028809},{"id":"https://openalex.org/keywords/semantic-loss","display_name":"semantic loss","score":0.4729999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820887565612793},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6924301385879517},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6924183964729309},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6403255462646484},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5811965465545654},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5164437294006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43207859992980957},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.42897751927375793},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.411360502243042},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.410395085811615},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3254801630973816},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.08094","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08094","pdf_url":"https://arxiv.org/pdf/2310.08094","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.08094","doi":"https://doi.org/10.48550/arxiv.2310.08094","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.08094","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.08094","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08094","pdf_url":"https://arxiv.org/pdf/2310.08094","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W4224231624","https://openalex.org/W2332512904","https://openalex.org/W2319626700"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,20,84,163],"text-to-image":[3],"(T2I)":[4],"models":[5],"enables":[6],"high-quality":[7],"image":[8,33],"generation":[9,166],"with":[10,39,64,129,167],"flexible":[11,173],"textual":[12],"control.":[13],"To":[14,191],"utilize":[15],"the":[16,21,40,44,59,65,80,85,112,117,123,130,134,139,153,158],"abundant":[17],"visual":[18,71,144,169],"priors":[19],"off-the-shelf":[22],"T2I":[23,45,140],"models,":[24],"a":[25,95,108,148,202],"series":[26],"of":[27,43,212],"methods":[28,52],"try":[29],"to":[30,34,120,151],"invert":[31],"an":[32,90,196],"proper":[35],"embedding":[36,119],"that":[37,79],"aligns":[38],"semantic":[41,149],"space":[42],"model.":[46],"However,":[47],"these":[48],"image-to-text":[49],"(I2T)":[50],"inversion":[51],"typically":[53],"need":[54],"multiple":[55,184],"source":[56],"images":[57],"containing":[58],"same":[60],"concept":[61,165],"or":[62],"struggle":[63],"imbalance":[66],"between":[67],"editing":[68,197,213],"flexibility":[69],"and":[70,93,97,146,183,200],"fidelity.":[72],"In":[73,111,133],"this":[74],"work,":[75],"we":[76,115,137,194],"point":[77],"out":[78],"critical":[81],"problem":[82],"lies":[83],"foreground-background":[86],"entanglement":[87],"when":[88],"learning":[89],"intended":[91],"concept,":[92],"propose":[94],"simple":[96],"effective":[98],"baseline":[99],"for":[100,142,209],"single-image":[101,179],"I2T":[102],"inversion,":[103],"named":[104,204],"SingleInsert.":[105],"SingleInsert":[106,161,176],"adopts":[107],"two-stage":[109],"scheme.":[110],"first":[113],"stage,":[114,136],"regulate":[116],"learned":[118],"concentrate":[121],"on":[122],"foreground":[124],"area":[125],"without":[126,187],"being":[127],"associated":[128],"irrelevant":[131],"background.":[132],"second":[135],"finetune":[138],"model":[141],"better":[143],"resemblance":[145],"devise":[147],"loss":[150],"prevent":[152],"language":[154],"drift":[155],"problem.":[156],"With":[157],"proposed":[159],"techniques,":[160],"excels":[162],"single":[164],"high":[168],"fidelity":[170],"while":[171],"allowing":[172],"editing.":[174],"Additionally,":[175],"can":[177],"perform":[178],"novel":[180],"view":[181],"synthesis":[182],"concepts":[185],"composition":[186],"requiring":[188],"joint":[189],"training.":[190],"facilitate":[192],"evaluation,":[193],"design":[195],"prompt":[198],"list":[199],"introduce":[201],"metric":[203],"Editing":[205],"Success":[206],"Rate":[207],"(ESR)":[208],"quantitative":[210],"assessment":[211],"flexibility.":[214],"Our":[215],"project":[216],"page":[217],"is:":[218],"https://jarrentwu1031.github.io/SingleInsert-web/":[219]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-10-14T00:00:00"}