{"id":"https://openalex.org/W7128427970","doi":"https://doi.org/10.1109/tcsvt.2026.3662405","title":"Zippo: RGB-Alpha Joint Modeling With a Unified Diffusion Model","display_name":"Zippo: RGB-Alpha Joint Modeling With a Unified Diffusion Model","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128427970","doi":"https://doi.org/10.1109/tcsvt.2026.3662405"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3662405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3662405","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kangyang Xie","orcid":"https://orcid.org/0009-0003-1048-1274"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangyang Xie","raw_affiliation_strings":["State Key Lab of CAD and CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-1048-1274","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD and CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125436738","display_name":"Binbin Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binbin Yang","raw_affiliation_strings":["College of Computer Science and Technology, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2143-2836","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867737","display_name":"Chenchen Jing","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenchen Jing","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125469848","display_name":"Cheng Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Peng","raw_affiliation_strings":["State Key Lab of CAD and CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7006-1728","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD and CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125456065","display_name":"Meng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125443798","display_name":"Cheng Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Zou","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-4527-7535","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125472592","display_name":"Ming Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1691-6817","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066434602","display_name":"Heqian Qiu","orcid":"https://orcid.org/0000-0002-0963-0311"},"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":"Heqian Qiu","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-0963-0311","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongliang Li","orcid":"https://orcid.org/0000-0002-7481-095X"},"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":"Hongliang Li","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-7481-095X","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125457725","display_name":"Hao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["State Key Lab of CAD and CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4417-614X","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD and CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.13045802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"8845","last_page":"8858"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.6607000231742859,"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/T11019","display_name":"Image Enhancement Techniques","score":0.6607000231742859,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2687000036239624,"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":0.028999999165534973,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6140999794006348},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.40560001134872437},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.398499995470047},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.39430001378059387},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.37130001187324524},{"id":"https://openalex.org/keywords/alpha","display_name":"Alpha (finance)","score":0.36500000953674316},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3646000027656555},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35350000858306885},{"id":"https://openalex.org/keywords/image-formation","display_name":"Image formation","score":0.3522000014781952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6251000165939331},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6140999794006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6136000156402588},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.599399983882904},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.39430001378059387},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C64943373","wikidata":"https://www.wikidata.org/wiki/Q2651003","display_name":"Alpha (finance)","level":4,"score":0.36500000953674316},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3646000027656555},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C125045340","wikidata":"https://www.wikidata.org/wiki/Q6002224","display_name":"Image formation","level":3,"score":0.3522000014781952},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3352000117301941},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31290000677108765},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28940001130104065},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.28600001335144043},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C200873422","wikidata":"https://www.wikidata.org/wiki/Q5448821","display_name":"Filling-in","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C2781399445","wikidata":"https://www.wikidata.org/wiki/Q309254","display_name":"High-dynamic-range imaging","level":4,"score":0.2660999894142151},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C142616399","wikidata":"https://www.wikidata.org/wiki/Q5148604","display_name":"Color image","level":4,"score":0.2540000081062317},{"id":"https://openalex.org/C2961294","wikidata":"https://www.wikidata.org/wiki/Q166863","display_name":"Color space","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3662405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3662405","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8387693189","display_name":null,"funder_award_id":"NO.2022ZD0160101","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,9,251],"generative":[3],"models":[4],"have":[5],"sparked":[6],"growing":[7],"interest":[8],"moving":[10],"beyond":[11],"pure":[12],"image":[13,17,23,44,101,220,227,233],"generation":[14,21,197,221],"toward":[15],"transparent":[16,219],"generation,":[18,226],"i.e.,":[19],"joint":[20,97,196,225,256],"of":[22,99,199,218],"and":[24,45,62,87,102,115,134,148,172,202,229],"its":[25],"alpha":[26,52,103,117,149,170,205,230],"mask.":[27,53,104],"However,":[28],"most":[29],"existing":[30],"approaches":[31],"adopt":[32],"a":[33,37,46,81,91,127,139,186,215,260],"two-stage":[34],"pipeline,":[35],"where":[36],"diffusion-based":[38],"model":[39,164],"first":[40],"generates":[41,108],"an":[42],"RGB":[43,100,147,167,200],"subsequent":[47],"matting":[48],"head":[49],"predicts":[50],"the":[51,68,72,123,160,163,195],"This":[54],"separation":[55],"not":[56,106,240],"only":[57,107,241],"leads":[58],"to":[59,165,180,191,263],"error":[60],"accumulation":[61],"inaccurate":[63],"predictions":[64],"but":[65,111,246],"also":[66,112,247],"overlooks":[67],"intrinsic":[69],"correlation":[70],"between":[71,146],"cross-modal":[73,132],"data.":[74],"In":[75,119,151,178],"this":[76,152],"work,":[77],"we":[78,183],"introduce":[79],"Zippo,":[80],"unified":[82,128],"diffusion":[83,93,141],"framework,":[84],"zipping":[85],"color":[86],"transparency":[88,174],"distributions":[89],"into":[90,126],"single":[92],"model,":[94],"by":[95],"learning":[96],"distribution":[98],"Zippo":[105,121,193,213,239],"high-fidelity":[109],"images":[110,168,201],"produces":[113],"plausible":[114],"sharp":[116],"masks.":[118],"practice,":[120],"inflates":[122],"latent":[124],"space":[125],"representation":[129],"that":[130,143,238],"encodes":[131],"data,":[133],"builds":[135],"upon":[136],"it":[137],"with":[138,194],"modality-aware":[140,187],"process":[142],"flexibly":[144],"switches":[145],"domains.":[150],"process,":[153],"conditioning":[154],"on":[155],"one":[156],"modality":[157],"while":[158],"denoising":[159],"other":[161],"allows":[162],"generate":[166],"from":[169,175],"masks":[171,206],"predict":[173],"input":[176],"images.":[177],"addition":[179],"single-modality":[181],"prediction,":[182,254],"further":[184],"design":[185],"noise":[188],"reassignment":[189],"strategy":[190],"empower":[192],"capability":[198],"their":[203],"corresponding":[204],"under":[207],"text":[208],"guidance.":[209],"With":[210],"these":[211],"techniques,":[212],"supports":[214],"wide":[216],"range":[217],"tasks,":[222],"including":[223],"image-alpha":[224,257],"matting,":[228],"mask":[231],"conditioned":[232],"generation.":[234],"Extensive":[235],"experiments":[236],"demonstrate":[237],"delivers":[242],"superior":[243],"visual":[244,252],"fidelity":[245],"achieves":[248],"competitive":[249],"performance":[250],"downstream":[253],"highlighting":[255],"modeling":[258],"as":[259],"powerful":[261],"alternative":[262],"traditional":[264],"paradigms.":[265]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-02-10T00:00:00"}
