{"id":"https://openalex.org/W4413145602","doi":"https://doi.org/10.1109/cvpr52734.2025.02203","title":"ROICtrl: Boosting Instance Control for Visual Generation","display_name":"ROICtrl: Boosting Instance Control for Visual Generation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145602","doi":"https://doi.org/10.1109/cvpr52734.2025.02203"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02203","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/A5101283118","display_name":"Yuchao Gu","orcid":"https://orcid.org/0009-0007-7167-8766"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchao Gu","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110374716","display_name":"Yipin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yipin Zhou","raw_affiliation_strings":["GenAI, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GenAI, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunfan Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunfan Ye","raw_affiliation_strings":["GenAI, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GenAI, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066141653","display_name":"Yixin Nie","orcid":"https://orcid.org/0009-0007-2689-7441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixin Nie","raw_affiliation_strings":["GenAI, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GenAI, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036418431","display_name":"Licheng Yu","orcid":"https://orcid.org/0000-0002-4943-6732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Licheng Yu","raw_affiliation_strings":["GenAI, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GenAI, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001790767","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0003-3752-0803"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083481253","display_name":"Kevin Qinghong Lin","orcid":"https://orcid.org/0000-0003-2568-2346"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kevin Qinghong Lin","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mike Zheng Shou","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23658","last_page":"23667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9811000227928162,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9811000227928162,"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":0.9706000089645386,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9556000232696533,"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/boosting","display_name":"Boosting (machine learning)","score":0.8834290504455566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7220428586006165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5398577451705933},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35165196657180786}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8834290504455566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220428586006165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5398577451705933},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35165196657180786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02203","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3082059448","https://openalex.org/W4313640622","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694"],"abstract_inverted_index":{"Natural":[0],"language":[1],"often":[2],"struggles":[3],"to":[4,21,73,166],"accurately":[5],"associate":[6],"positional":[7],"and":[8,104,110,157],"attribute":[9],"information":[10],"with":[11,54,142,149],"multiple":[12],"instances,":[13],"which":[14],"limits":[15],"current":[16],"text-based":[17],"visual":[18,119],"generation":[19],"models":[20,38,132],"simpler":[22],"compositions":[23],"featuring":[24],"only":[25],"a":[26,50,55,97],"few":[27],"dominant":[28],"instances.":[29],"To":[30],"address":[31],"this":[32,34,61],"limitation,":[33],"work":[35],"enhances":[36],"diffusion":[37,131,144],"by":[39,49,90],"introducing":[40],"regional":[41,136,177],"instance":[42,46,137,178],"control,":[43],"where":[44],"each":[45],"is":[47,140],"governed":[48],"bounding":[51],"box":[52],"paired":[53],"free-form":[56],"caption.":[57],"Previous":[58],"methods":[59],"in":[60,80,92,176],"area":[62],"typically":[63],"rely":[64],"on":[65,114,122],"implicit":[66],"position":[67],"encoding":[68],"or":[69,85],"explicit":[70],"attention":[71],"masks":[72],"separate":[74],"regions":[75],"of":[76],"interest":[77],"(ROIs),":[78],"resulting":[79],"either":[81],"inaccurate":[82],"coordinate":[83],"injection":[84],"large":[86],"computational":[87,183],"overhead.":[88],"Inspired":[89],"ROI-Align":[91,103],"object":[93],"detection,":[94],"we":[95,124],"introduce":[96],"complementary":[98],"operation":[99],"called":[100],"ROI-Unpool.":[101],"Together,":[102],"ROI-":[105],"Unpool":[106],"enable":[107],"explicit,":[108],"efficient,":[109],"accurate":[111],"ROI":[112],"manipulation":[113],"high-resolution":[115],"feature":[116],"maps":[117],"for":[118,129],"generation.":[120,168],"Building":[121],"ROI-Unpool,":[123],"propose":[125],"ROICtrl,":[126],"an":[127],"adapter":[128],"pretrained":[130],"that":[133,171],"enables":[134],"precise":[135],"control.":[138],"ROICtrl":[139,172],"compatible":[141],"community-finetuned":[143],"models,":[145],"as":[146,148],"well":[147],"existing":[150],"spatial-based":[151],"add-ons":[152,159],"(e.g.,":[153,160],"ControlNet,":[154],"T2I-":[155],"Adapter)":[156],"embedding-based":[158],"IP-Adapter,":[161],"ED-LoRA),":[162],"extending":[163],"their":[164],"applications":[165],"multi-instance":[167],"Experiments":[169],"show":[170],"achieves":[173],"superior":[174],"performance":[175],"control":[179],"while":[180],"significantly":[181],"reducing":[182],"costs.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
