{"id":"https://openalex.org/W4405094424","doi":"https://doi.org/10.1109/iccv51701.2025.01416","title":"Pinco: Position-Induced Consistent Adapter for Diffusion Transformer in Foreground-Conditioned Inpainting","display_name":"Pinco: Position-Induced Consistent Adapter for Diffusion Transformer in Foreground-Conditioned Inpainting","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405094424","doi":"https://doi.org/10.1109/iccv51701.2025.01416"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.03812","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074251934","display_name":"Guangben Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangben Lu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101551627","display_name":"Yuzhen Du","orcid":"https://orcid.org/0000-0002-1539-4247"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhen Du","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108958962","display_name":"Yizhe Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhe Tang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101795676","display_name":"Zhimin Sun","orcid":"https://orcid.org/0000-0002-1292-8872"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhimin Sun","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108902322","display_name":"Yifan Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Yi","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108958962","display_name":"Yizhe Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Qi","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101442365","display_name":"Tianyi Wang","orcid":"https://orcid.org/0000-0003-4746-9124"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Wang","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084218062","display_name":"Lizhuang Ma","orcid":"https://orcid.org/0000-0003-1653-4341"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhuang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009914328","display_name":"Fangyuan Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyuan Zou","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15266","last_page":"15276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9563000202178955,"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":0.9563000202178955,"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":0.9036999940872192,"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/adapter","display_name":"Adapter (computing)","score":0.7131076455116272},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.6558359861373901},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6329911947250366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41588151454925537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33020728826522827},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.21741700172424316},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1777898073196411},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1059914231300354},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06496527791023254}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7131076455116272},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.6558359861373901},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6329911947250366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41588151454925537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33020728826522827},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.21741700172424316},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1777898073196411},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1059914231300354},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06496527791023254},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.03812","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03812","pdf_url":"https://arxiv.org/pdf/2412.03812","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2412.03812","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.03812","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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:2412.03812","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03812","pdf_url":"https://arxiv.org/pdf/2412.03812","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[{"id":"https://openalex.org/G1053635409","display_name":null,"funder_award_id":"YG2023QNB17,YG2024QNA44","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7209988896","display_name":null,"funder_award_id":"L222117","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G8845801817","display_name":null,"funder_award_id":"62302297,72192821,62272447,62472282,62472285","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W2244018504","https://openalex.org/W4242046654","https://openalex.org/W3174923100","https://openalex.org/W3134074939","https://openalex.org/W2135359786"],"abstract_inverted_index":{"Foreground-conditioned":[0],"inpainting":[1,26,73],"aims":[2],"to":[3,31,46,111,151,172,181],"seamlessly":[4],"fill":[5],"the":[6,14,49,56,60,86,89,100,105,115,123,128,134,168,177,185,197],"background":[7],"region":[8],"of":[9,38,88,167,176,200],"an":[10],"image":[11,25,136],"by":[12,120],"utilizing":[13],"provided":[15],"foreground":[16,90,101,129],"subject":[17,39,102,118,160,186,201],"and":[18,59,117,154,163,180,203,216],"a":[19,70,95,141,190],"text":[20,50,61,81,116],"description.":[21,62],"While":[22],"existing":[23],"T2I-based":[24],"methods":[27],"can":[28,125],"be":[29],"applied":[30],"this":[32],"task,":[33],"they":[34],"suffer":[35],"from":[36],"issues":[37],"shape":[40,87],"expansion,":[41],"distortion,":[42],"or":[43],"impaired":[44],"ability":[45],"align":[47],"with":[48,79],"description,":[51],"resulting":[52],"in":[53,218],"inconsistencies":[54],"between":[55,114],"visual":[57],"elements":[58],"To":[63],"address":[64],"these":[65],"challenges,":[66],"we":[67,93,139,188],"propose":[68],"Pinco,":[69],"plug-and-play":[71],"foreground-conditioned":[72,219],"adapter":[74],"that":[75,98,122,147,210],"generates":[76],"high-quality":[77,165],"backgrounds":[78],"good":[80],"alignment":[82],"while":[83,132],"effectively":[84,126],"preserving":[85],"subject.":[91],"Firstly,":[92],"design":[94,140],"Self-Consistent":[96],"Adapter":[97],"integrates":[99],"features":[103,119,156,179,202],"into":[104],"layout-related":[106],"self-attention":[107],"layer,":[108],"which":[109],"helps":[110],"alleviate":[112],"conflicts":[113],"ensuring":[121,164],"model":[124],"consider":[127],"subject's":[130,169],"characteristics":[131],"processing":[133],"overall":[135],"layout.":[137],"Secondly,":[138],"Decoupled":[142],"Image":[143],"Feature":[144],"Extraction":[145],"method":[146,212],"employs":[148],"distinct":[149],"architectures":[150],"extract":[152],"semantic":[153],"spatial":[155],"separately,":[157],"significantly":[158],"improving":[159,196],"feature":[161],"extraction":[162],"preservation":[166],"shape.":[170],"Thirdly,":[171],"ensure":[173],"precise":[174],"utilization":[175],"extracted":[178],"focus":[182],"attention":[183],"on":[184],"region,":[187],"introduce":[189],"Shared":[191],"Positional":[192],"Embedding":[193],"Anchor,":[194],"greatly":[195],"model's":[198],"understanding":[199],"boosting":[204],"training":[205],"efficiency.":[206],"Extensive":[207],"experiments":[208],"demonstrate":[209],"our":[211],"achieves":[213],"superior":[214],"performance":[215],"efficiency":[217],"inpainting.":[220]},"counts_by_year":[],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}