{"id":"https://openalex.org/W4414753768","doi":"https://doi.org/10.1145/3746027.3755225","title":"Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance","display_name":"Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4414753768","doi":"https://doi.org/10.1145/3746027.3755225"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755225","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.17757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102582432","display_name":"Hongxing Fan","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":true,"raw_author_name":"Hongxing Fan","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-4525-8777","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lipeng Wang","orcid":"https://orcid.org/0009-0003-9100-7899"},"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":"Lipeng Wang","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-9100-7899","affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haohua Chen","orcid":"https://orcid.org/0009-0005-4631-0172"},"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":"Haohua Chen","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-4631-0172","affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zehuan Huang","orcid":"https://orcid.org/0009-0002-1883-0777"},"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":"Zehuan Huang","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-1883-0777","affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104301020","display_name":"Jiangtao Wu","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":"Jiangtao Wu","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-9288-3823","affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035443556","display_name":"Lu Sheng","orcid":"https://orcid.org/0000-0002-8525-9163"},"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":"Lu Sheng","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8525-9163","affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102582432"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.1148,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82698158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9911","last_page":"9919"},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9962000250816345,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.988099992275238,"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/amodal-perception","display_name":"Amodal perception","score":0.9146999716758728},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.6547999978065491},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4887999892234802},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4165000021457672},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.38670000433921814},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3824000060558319},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.373199999332428}],"concepts":[{"id":"https://openalex.org/C174478892","wikidata":"https://www.wikidata.org/wiki/Q4747455","display_name":"Amodal perception","level":3,"score":0.9146999716758728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786300003528595},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.6547999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6492999792098999},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5663999915122986},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.38670000433921814},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3472999930381775},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.32910001277923584},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755225","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.17757","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.17757","pdf_url":"https://arxiv.org/pdf/2509.17757","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.17757","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.17757","pdf_url":"https://arxiv.org/pdf/2509.17757","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/G6078352744","display_name":null,"funder_award_id":"62132001","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/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":[],"abstract_inverted_index":{"Amodal":[0],"completion,":[1],"generating":[2],"invisible":[3],"parts":[4],"of":[5,88],"occluded":[6],"objects,":[7],"is":[8],"vital":[9],"for":[10,66],"applications":[11],"like":[12],"image":[13],"editing":[14],"and":[15,57,84,111],"AR.":[16],"Prior":[17],"methods":[18],"face":[19],"challenges":[20],"with":[21],"data":[22],"needs,":[23],"generalization,":[24],"or":[25,90],"error":[26],"accumulation":[27],"in":[28],"progressive":[29],"pipelines.":[30],"We":[31],"propose":[32],"a":[33,63,115],"Collaborative":[34],"Multi-Agent":[35],"Reasoning":[36],"Framework":[37],"based":[38],"on":[39],"upfront":[40],"collaborative":[41],"reasoning":[42],"to":[43,52],"overcome":[44],"these":[45],"issues.":[46],"Our":[47],"framework":[48,125],"uses":[49],"multiple":[50],"agents":[51],"collaboratively":[53],"analyze":[54],"occlusion":[55],"relationships":[56],"determine":[58],"necessary":[59],"boundary":[60],"expansion,":[61],"yielding":[62],"precise":[64],"mask":[65],"inpainting.":[67],"Concurrently,":[68],"an":[69],"agent":[70],"generates":[71],"fine-grained":[72],"textual":[73],"descriptions,":[74],"enabling":[75],"Fine-Grained":[76],"Semantic":[77],"Guidance.":[78],"This":[79],"ensures":[80],"accurate":[81],"object":[82],"synthesis":[83],"prevents":[85],"the":[86],"regeneration":[87],"occluders":[89],"other":[91],"unwanted":[92],"elements,":[93],"especially":[94],"within":[95],"large":[96],"inpainting":[97],"areas.":[98],"Furthermore,":[99],"our":[100,124],"method":[101],"directly":[102],"produces":[103],"layered":[104],"RGBA":[105],"outputs":[106],"guided":[107],"by":[108],"visible":[109],"masks":[110],"attention":[112],"maps":[113],"from":[114],"Diffusion":[116],"Transformer,":[117],"eliminating":[118],"extra":[119],"segmentation.":[120],"Extensive":[121],"evaluations":[122],"demonstrate":[123],"achieves":[126],"state-of-the-art":[127],"visual":[128],"quality.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}