{"id":"https://openalex.org/W4404345336","doi":"https://doi.org/10.1109/iccv51701.2025.02212","title":"ZIM: Zero-Shot Image Matting for Anything","display_name":"ZIM: Zero-Shot Image Matting for Anything","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404345336","doi":"https://doi.org/10.1109/iccv51701.2025.02212"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02212","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.00626","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075668231","display_name":"Beomyoung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Beomyoung Kim","raw_affiliation_strings":["NAVER Cloud, ImageVision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, ImageVision","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chanyong Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanyong Shin","raw_affiliation_strings":["NAVER Cloud, ImageVision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, ImageVision","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057640516","display_name":"Joonhyun Jeong","orcid":"https://orcid.org/0000-0002-0028-8660"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonhyun Jeong","raw_affiliation_strings":["NAVER Cloud, ImageVision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, ImageVision","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101622080","display_name":"Hyungsik Jung","orcid":"https://orcid.org/0000-0002-0771-4503"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungsik Jung","raw_affiliation_strings":["NAVER Cloud, ImageVision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, ImageVision","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043552524","display_name":"Se-Yun Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Se-Yun Lee","raw_affiliation_strings":["NAVER Cloud, ImageVision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, ImageVision","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109699282","display_name":"Sewhan Chun","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sewhan Chun","raw_affiliation_strings":["NAVER Cloud, ImageVision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, ImageVision","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019988954","display_name":"Dong-Hyun Hwang","orcid":"https://orcid.org/0000-0001-5588-4366"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Hyun Hwang","raw_affiliation_strings":["NAVER Cloud, ImageVision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, ImageVision","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102372265","display_name":"Joonsang Yu","orcid":"https://orcid.org/0000-0002-9165-0572"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonsang Yu","raw_affiliation_strings":["NAVER Cloud, ImageVision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, ImageVision","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5075668231"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00068603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23828","last_page":"23838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9524000287055969,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9524000287055969,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.9125999808311462,"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/T13270","display_name":"QR Code Applications and Technologies","score":0.9064000248908997,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/shot","display_name":"Shot (pellet)","score":0.8349452614784241},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.7419064044952393},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5491462349891663},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3170228600502014},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2887876629829407},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.13658097386360168},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11865687370300293},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09339872002601624}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.8349452614784241},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7419064044952393},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5491462349891663},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3170228600502014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2887876629829407},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.13658097386360168},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11865687370300293},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09339872002601624},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02212","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:2411.00626","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.00626","pdf_url":"https://arxiv.org/pdf/2411.00626","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.2411.00626","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.00626","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.00626","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.00626","pdf_url":"https://arxiv.org/pdf/2411.00626","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"The":[0,194],"recent":[1],"segmentation":[2,12,49],"foundation":[3,177],"model,":[4,34],"Segment":[5],"Anything":[6],"Model":[7],"(SAM),":[8],"exhibits":[9],"strong":[10],"zero-shot":[11,31,79,85,149,180],"capabilities,":[13],"but":[14],"it":[15,70],"falls":[16],"short":[17],"in":[18,144,158],"generating":[19],"fine-grained":[20,145],"precise":[21,73,163],"masks.":[22],"To":[23],"address":[24],"this":[25,67],"limitation,":[26],"we":[27,42,82,152],"propose":[28],"a":[29,44,90,100,175,187],"novel":[30],"image":[32,167],"matting":[33,86,181],"called":[35],"ZIM,":[36],"with":[37,66,89,99],"two":[38],"key":[39],"contributions:":[40],"First,":[41],"develop":[43],"label":[45],"converter":[46],"that":[47,139],"transforms":[48],"labels":[50],"into":[51],"detailed":[52],"matte":[53,74,134],"labels,":[54],"constructing":[55],"the":[56,84,110,124,154],"new":[57],"SA1B-Matte":[58],"dataset":[59,68],"without":[60],"costly":[61],"manual":[62],"annotations.":[63],"Training":[64],"SAM":[65],"enables":[69],"to":[71,94,105,112],"generate":[72],"masks":[75],"while":[76],"maintaining":[77],"its":[78,183],"capability.":[80],"Second,":[81],"design":[83],"model":[87,111],"equipped":[88],"hierarchical":[91],"pixel":[92],"decoder":[93],"enhance":[95],"mask":[96,146],"representation,":[97],"along":[98],"prompt-aware":[101],"masked":[102],"attention":[103],"mechanism":[104],"improve":[106],"performance":[107],"by":[108,117],"enabling":[109],"focus":[113],"on":[114],"regions":[115],"specified":[116],"visual":[118],"prompts.":[119],"We":[120],"evaluate":[121],"ZIM":[122,140,157],"using":[123],"newly":[125],"introduced":[126],"MicroMat-3K":[127],"test":[128],"set,":[129],"which":[130],"contains":[131],"high-quality":[132],"micro-level":[133],"labels.":[135],"Experimental":[136],"results":[137],"show":[138],"outperforms":[141],"existing":[142],"methods":[143],"generation":[147],"and":[148,169,182],"generalization.":[150],"Furthermore,":[151],"demonstrate":[153],"versatility":[155],"of":[156,190],"various":[159],"downstream":[160,184],"tasks":[161],"requiring":[162],"masks,":[164],"such":[165],"as":[166],"inpainting":[168],"3D":[170],"NeRF.":[171],"Our":[172],"contributions":[173],"provide":[174],"robust":[176],"for":[178],"advancing":[179],"applications":[185],"across":[186],"wide":[188],"range":[189],"computer":[191],"vision":[192],"tasks.":[193],"code":[195],"is":[196],"available":[197],"at":[198],"https://github.com/naver-ai/ZIM.":[199]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}
