{"id":"https://openalex.org/W4416058421","doi":"https://doi.org/10.1109/iccv51701.2025.01413","title":"SDMATTE: Grafting Diffusion Models for Interactive Matting","display_name":"SDMATTE: Grafting Diffusion Models for Interactive Matting","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416058421","doi":"https://doi.org/10.1109/iccv51701.2025.01413"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01413","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/2508.00443","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073538544","display_name":"Longfei Huang","orcid":"https://orcid.org/0009-0006-4761-7384"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longfei Huang","raw_affiliation_strings":["Shanghai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814743","display_name":"Liang Yu","orcid":"https://orcid.org/0009-0007-3922-3454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Liang","raw_affiliation_strings":["vivo Mobile Communication Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo Mobile Communication Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397087","display_name":"Hao Zhang","orcid":"https://orcid.org/0009-0007-1175-5918"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["vivo Mobile Communication Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo Mobile Communication Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071487514","display_name":"Jinwei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinwei Chen","raw_affiliation_strings":["vivo Mobile Communication Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo Mobile Communication Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020174269","display_name":"Dong Wei","orcid":"https://orcid.org/0000-0001-8616-2040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Dong","raw_affiliation_strings":["vivo Mobile Communication Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo Mobile Communication Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043224371","display_name":"L. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lunde Chen","raw_affiliation_strings":["Shanghai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054915839","display_name":"Wanyu Liu","orcid":"https://orcid.org/0000-0003-4146-9449"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanyu Liu","raw_affiliation_strings":["Shanghai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374449","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-6767-2982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["vivo Mobile Communication Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo Mobile Communication Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062345781","display_name":"Peng-Tao Jiang","orcid":"https://orcid.org/0000-0002-1786-4943"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng-Tao Jiang","raw_affiliation_strings":["vivo Mobile Communication Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo Mobile Communication Co., Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5073538544"],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52784882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15229","last_page":"15239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.36640000343322754,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.36640000343322754,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2639000117778778,"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/T11019","display_name":"Image Enhancement Techniques","score":0.2425999939441681,"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/focus","display_name":"Focus (optics)","score":0.6039000153541565},{"id":"https://openalex.org/keywords/opacity","display_name":"Opacity","score":0.5715000033378601},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5126000046730042},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49889999628067017},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.43320000171661377},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.42980000376701355},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.40880000591278076},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.38339999318122864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458999752998352},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6039000153541565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5727999806404114},{"id":"https://openalex.org/C60056205","wikidata":"https://www.wikidata.org/wiki/Q691914","display_name":"Opacity","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5054000020027161},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38339999318122864},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3366999924182892},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C64073096","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Interactive visualization","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01413","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:2508.00443","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00443","pdf_url":"https://arxiv.org/pdf/2508.00443","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"},{"id":"doi:10.48550/arxiv.2508.00443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.00443","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:2508.00443","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00443","pdf_url":"https://arxiv.org/pdf/2508.00443","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"interactive":[1,60,70,99,166],"matting":[2,71],"methods":[3],"have":[4],"shown":[5],"satisfactory":[6],"performance":[7,158],"in":[8,19,23,37,165],"capturing":[9],"the":[10,80,88,136,156],"primary":[11],"regions":[12],"of":[13,31,83,106,112,159],"objects,":[14],"but":[15],"they":[16],"fall":[17],"short":[18],"extracting":[20],"fine-grained":[21],"details":[22],"edge":[24],"regions.":[25],"Diffusion":[26],"models":[27,85],"trained":[28],"on":[29,140,152],"billions":[30],"image-text":[32],"pairs,":[33],"demonstrate":[34,155],"exceptional":[35],"capability":[36,91,96],"modeling":[38],"highly":[39],"complex":[40],"data":[41],"distributions":[42],"and":[43,86,109,124,170],"synthesizing":[44],"realistic":[45],"texture":[46],"details,":[47],"while":[48],"exhibiting":[49],"robust":[50],"text-driven":[51,89],"interaction":[52,90,95],"capabilities,":[53],"making":[54],"them":[55],"an":[56],"attractive":[57],"solution":[58],"for":[59],"matting.":[61,100,167],"To":[62],"this":[63],"end,":[64],"we":[65,78,102,128],"propose":[66,129],"SDMatte,":[67],"a":[68,130],"diffusion-driven":[69],"model,":[72],"with":[73],"three":[74],"key":[75],"contributions.":[76],"First,":[77],"exploit":[79],"powerful":[81],"priors":[82],"diffusion":[84],"transform":[87],"into":[92,115],"visual":[93,107,144],"prompt-driven":[94],"to":[97,120,138,147],"enable":[98],"Second,":[101],"integrate":[103],"coordinate":[104],"embeddings":[105,111],"prompts":[108],"opacity":[110,125],"target":[113],"objects":[114],"U-Net,":[116],"enhancing":[117],"SDMatte's":[118],"sensitivity":[119],"spatial":[121],"position":[122],"information":[123],"information.":[126],"Third,":[127],"masked":[131],"self-attention":[132],"mechanism":[133],"that":[134],"enables":[135],"model":[137,171],"focus":[139],"areas":[141],"specified":[142],"by":[143],"prompts,":[145],"leading":[146],"better":[148],"performance.":[149],"Extensive":[150],"experiments":[151],"multiple":[153],"datasets":[154],"superior":[157],"our":[160],"method,":[161],"validating":[162],"its":[163],"effectiveness":[164],"Our":[168],"code":[169],"are":[172],"available":[173],"at":[174],"https://github.com/vivoCameraResearch/SDMatte.":[175]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}