{"id":"https://openalex.org/W4415538875","doi":"https://doi.org/10.1145/3746027.3755191","title":"Free-Mask: A Novel Paradigm of Integration Between the Segmentation Diffusion Model and Image Editing","display_name":"Free-Mask: A Novel Paradigm of Integration Between the Segmentation Diffusion Model and Image Editing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538875","doi":"https://doi.org/10.1145/3746027.3755191"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755191","doi":"https://doi.org/10.1145/3746027.3755191","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755191","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3746027.3755191","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bo Gao","orcid":"https://orcid.org/0009-0009-2991-1266","observed_orcids":["https://orcid.org/0009-0009-2991-1266"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Gao","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0009-0009-2991-1266","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334392","display_name":"Jianhui Wang","orcid":"https://orcid.org/0009-0009-7053-5645","observed_orcids":["https://orcid.org/0009-0009-7053-5645"]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhui Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0009-7053-5645","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100565377","display_name":"Song Xin-yuan","orcid":"https://orcid.org/0009-0005-4209-5671","observed_orcids":["https://orcid.org/0009-0005-4209-5671","https://orcid.org/0000-0002-7760-6399","https://orcid.org/0000-0003-3414-3117"]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyuan Song","raw_affiliation_strings":["Emory University, Atlanta, Geogia, USA"],"raw_orcid":"https://orcid.org/0009-0005-4209-5671","affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, Geogia, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016719157","display_name":"Yangfan He","orcid":"https://orcid.org/0000-0001-7172-9403","observed_orcids":["https://orcid.org/0000-0001-7172-9403"]},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yangfan He","raw_affiliation_strings":["University of Minnesota-Twin Cities, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0001-7172-9403","affiliations":[{"raw_affiliation_string":"University of Minnesota-Twin Cities, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007259734","display_name":"Fangxu Xing","orcid":"https://orcid.org/0000-0002-0517-0952","observed_orcids":["https://orcid.org/0000-0002-0517-0952"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fangxu Xing","raw_affiliation_strings":["Harvard Medical School, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0517-0952","affiliations":[{"raw_affiliation_string":"Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101850471","display_name":"Tianyu Shi","orcid":"https://orcid.org/0000-0003-4271-0871","observed_orcids":["https://orcid.org/0000-0003-4271-0871","https://orcid.org/0009-0001-9119-778X"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tianyu Shi","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0003-4271-0871","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3574,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69180829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9881","last_page":"9890"},"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":0.5590999722480774,"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":0.5590999722480774,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.31029999256134033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1234000027179718,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/semantic-segmentation","display_name":"semantic segmentation","score":0.7450000047683716},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.6830000281333923},{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.734000027179718},{"id":"https://openalex.org/keywords/image-editing","display_name":"image editing","score":0.9110000133514404},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.8130000233650208},{"id":"https://openalex.org/keywords/zero-shot-segmentation","display_name":"zero-shot segmentation","score":0.8460000157356262},{"id":"https://openalex.org/keywords/segmentation-masks","display_name":"segmentation masks","score":0.5099999904632568}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6603000164031982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.644599974155426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6050999760627747},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45010000467300415},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3806999921798706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.32179999351501465},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.26330000162124634}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3746027.3755191","doi":"https://doi.org/10.1145/3746027.3755191","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755191","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:2411.01819","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.01819","pdf_url":"https://arxiv.org/pdf/2411.01819","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.01819","doi":"https://doi.org/10.48550/arxiv.2411.01819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.01819","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755191","doi":"https://doi.org/10.1145/3746027.3755191","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755191","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415538875.pdf","grobid_xml":"https://content.openalex.org/works/W4415538875.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W611457968","https://openalex.org/W1903029394","https://openalex.org/W2194775991","https://openalex.org/W2306289963","https://openalex.org/W2340897893","https://openalex.org/W2552414813","https://openalex.org/W2561196672","https://openalex.org/W2755136704","https://openalex.org/W2798376494","https://openalex.org/W2799124825","https://openalex.org/W2956648669","https://openalex.org/W2962758679","https://openalex.org/W2962957359","https://openalex.org/W2965572487","https://openalex.org/W2969893028","https://openalex.org/W2982093251","https://openalex.org/W3134816589","https://openalex.org/W3159880945","https://openalex.org/W3162926177","https://openalex.org/W3169823210","https://openalex.org/W4226069476","https://openalex.org/W4226305381","https://openalex.org/W4281485151","https://openalex.org/W4281634598","https://openalex.org/W4306820534","https://openalex.org/W4312526532","https://openalex.org/W4312933868","https://openalex.org/W4312935996","https://openalex.org/W4313166273","https://openalex.org/W4327990734","https://openalex.org/W4383176261","https://openalex.org/W4385569875","https://openalex.org/W4386076368","https://openalex.org/W4386160313","https://openalex.org/W4390874196","https://openalex.org/W4390874575","https://openalex.org/W4408810164","https://openalex.org/W7133187708"],"related_works":["https://openalex.org/W4390872876","https://openalex.org/W4415707824","https://openalex.org/W7133242627","https://openalex.org/W4403842929","https://openalex.org/W4387076523","https://openalex.org/W7138221787","https://openalex.org/W4415797287","https://openalex.org/W6891902983","https://openalex.org/W7133202733","https://openalex.org/W7154996551"],"abstract_inverted_index":{"Current":[0],"semantic":[1],"segmentation":[2,96,131,157],"models":[3,25,158],"typically":[4],"require":[5],"a":[6,13,87,92],"substantial":[7],"amount":[8],"of":[9,42,47,63,82,106,119],"manually":[10],"annotated":[11],"data,":[12,165],"process":[14],"that":[15,90,123,150],"is":[16],"both":[17],"time-consuming":[18],"and":[19,29,76,80,141],"resource-intensive.":[20],"Alternatively,":[21],"leveraging":[22],"advanced":[23,98],"text-to-image":[24,112],"such":[26],"as":[27,34,60],"Midjourney":[28],"Stable":[30,67],"Diffusion":[31,68,93],"has":[32,69],"emerged":[33],"an":[35],"efficient":[36],"strategy,":[37],"enabling":[38],"the":[39,61,78,104,117,135,181],"automatic":[40],"generation":[41,62],"synthetic":[43,83,151],"data":[44,152],"in":[45,167,180],"place":[46],"manual":[48,139],"annotations.":[49],"However,":[50],"previous":[51],"methods":[52],"have":[53],"been":[54],"limited":[55],"to":[56,159],"generating":[57,129],"single-instance":[58],"images,":[59],"multiple":[64,107],"instances":[65],"with":[66,97,138],"proven":[70],"unstable.":[71],"To":[72],"address":[73],"this":[74],"limitation":[75],"expand":[77],"scope":[79],"diversity":[81],"datasets,":[84],"we":[85],"propose":[86],"framework":[88],"\\textbf{Free-Mask}":[89,155,171],"combines":[91],"Model":[94],"for":[95,103],"image":[99],"editing":[100],"capabilities,":[101],"allowing":[102],"integration":[105],"objects":[108],"into":[109],"images":[110],"via":[111],"models.":[113],"Our":[114],"method":[115],"facilitates":[116],"creation":[118],"highly":[120],"realistic":[121],"datasets":[122],"closely":[124],"emulate":[125],"open-world":[126],"environments":[127],"while":[128],"accurate":[130],"masks.":[132],"It":[133],"reduces":[134],"labor":[136],"associated":[137],"annotation":[140],"also":[142],"ensures":[143],"precise":[144],"mask":[145],"generation.":[146],"Experimental":[147],"results":[148,175],"demonstrate":[149],"generated":[153],"by":[154],"enables":[156],"outperform":[160],"those":[161],"trained":[162],"on":[163,176],"real":[164],"especially":[166],"zero-shot":[168],"settings.":[169],"Notably,":[170],"achieves":[172],"new":[173],"state-of-the-art":[174],"previously":[177],"unseen":[178],"classes":[179],"VOC":[182],"2012":[183],"benchmark.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-25T00:00:00"}