{"id":"https://openalex.org/W7138237379","doi":"https://doi.org/10.1609/aaai.v40i9.37648","title":"RAA: Achieving Interactive Remove/Add Anything via Fully Synthetic Data","display_name":"RAA: Achieving Interactive Remove/Add Anything via Fully Synthetic Data","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138237379","doi":"https://doi.org/10.1609/aaai.v40i9.37648"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i9.37648","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37648","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i9.37648","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Delong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Delong Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126765764","display_name":"Haotian Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Hou","raw_affiliation_strings":["Beihang University\nSenseTime"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University\nSenseTime","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129701139","display_name":"Zhaohui Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaohui Hou","raw_affiliation_strings":["SenseTime"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129652888","display_name":"Shihao Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihao Han","raw_affiliation_strings":["SenseTime"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104300294","display_name":"Zhiyuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Huang","raw_affiliation_strings":["SenseTime"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072763304","display_name":"Mingjie Zhan","orcid":"https://orcid.org/0000-0001-8221-9089"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Zhan","raw_affiliation_strings":["SenseTime"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129704185","display_name":"Fei Su","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Su","raw_affiliation_strings":["Beijing University of Posts and Telecommunications\nBeijing Key Laboratory of Network System and Network Culture, China\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications\nBeijing Key Laboratory of Network System and Network Culture, China\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129642271","display_name":"Zhicheng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Zhao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications\nBeijing Key Laboratory of Network System and Network Culture, China\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications\nBeijing Key Laboratory of Network System and Network Culture, China\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26076442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"9","first_page":"7123","last_page":"7131"},"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":0.8795999884605408,"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":0.8795999884605408,"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":0.013899999670684338,"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/T11019","display_name":"Image Enhancement Techniques","score":0.011699999682605267,"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/pipeline","display_name":"Pipeline (software)","score":0.6699000000953674},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.6100999712944031},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5917999744415283},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.576200008392334},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4438000023365021},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.41510000824928284},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.38609999418258667},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3684999942779541},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.36239999532699585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8360000252723694},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6699000000953674},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.6100999712944031},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.576200008392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5672000050544739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47200000286102295},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.38609999418258667},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.35519999265670776},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.2655999958515167},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i9.37648","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37648","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37648","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i9.37648","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37648","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Precise":[0],"and":[1,8,33,43,65,94,108,132,172,201,204],"controllable":[2],"image":[3,18,122],"editing,":[4],"especially":[5],"object":[6,102],"removal":[7,202],"insertion,":[9],"represents":[10],"one":[11],"of":[12,118,135,177],"the":[13,113],"most":[14],"common":[15],"demands":[16],"in":[17],"manipulation.":[19],"However,":[20],"existing":[21,195],"methods":[22,197],"suffer":[23],"from":[24],"severe":[25],"limitations.":[26],"Mask-based":[27],"inpainting":[28,159],"often":[29],"introduces":[30],"visual":[31,186],"artifacts":[32],"semantic":[34],"inconsistencies,":[35],"while":[36,183],"instruction-based":[37],"approaches":[38],"lack":[39],"accurate":[40],"spatial":[41,153],"control":[42,107],"tend":[44],"to":[45,80,90],"unintentionally":[46],"modify":[47],"background":[48],"regions.":[49],"To":[50],"address":[51],"these":[52],"issues,":[53],"we":[54,60,142],"propose":[55],"two":[56],"key":[57],"contributions.":[58],"First,":[59],"develop":[61],"a":[62,75,84,95,133,147,157],"fully":[63],"automated":[64,105],"self-improving":[66],"pipeline":[67,73],"for":[68,104],"synthetic":[69],"data":[70],"generation.":[71],"This":[72,110],"utilizes":[74],"Large":[76],"Language":[77],"Model":[78],"(LLM)":[79],"generate":[81],"diverse":[82],"prompts,":[83],"Diffusion":[85],"Transformer":[86],"(DiT)":[87],"fine-tuned":[88],"evolutionarily":[89],"synthesize":[91],"high-quality":[92,121],"images,":[93],"Multimodal":[96],"LLM":[97],"(MLLM)":[98],"combined":[99],"with":[100,127,151],"open-set":[101],"detector":[103],"quality":[106],"annotation.":[109],"process":[111],"produces":[112],"Remove/Add":[114,144],"Dataset":[115],"(RAD),":[116],"consisting":[117],"over":[119],"514,510":[120],"pairs,":[123],"each":[124],"richly":[125],"annotated":[126],"bounding":[128],"boxes,":[129],"segmentation":[130],"masks,":[131],"variety":[134],"editing":[136,149,164],"instructions.":[137],"Second,":[138],"based":[139],"on":[140,168,198],"RAD,":[141],"introduce":[143],"Anything":[145],"(RAA),":[146],"novel":[148],"framework":[150],"precise":[152],"control.":[154],"Built":[155],"upon":[156],"diffusion-based":[158],"model,":[160],"RAA":[161,192],"achieves":[162],"high":[163],"accuracy":[165],"by":[166],"conditioning":[167],"both":[169,199],"textual":[170],"instructions":[171],"an":[173],"explicitly":[174],"defined":[175],"region":[176],"interest":[178],"(ROI),":[179],"enabling":[180],"efficient":[181],"fine-tuning":[182],"maintaining":[184],"global":[185],"coherence.":[187],"Extensive":[188],"experiments":[189],"demonstrate":[190],"that":[191],"significantly":[193],"outperforms":[194],"open-source":[196],"addition":[200],"tasks,":[203],"even":[205],"slightly":[206],"surpasses":[207],"costly":[208],"proprietary":[209],"models.":[210]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}