{"id":"https://openalex.org/W4408355791","doi":"https://doi.org/10.1109/icassp49660.2025.10890576","title":"Dual Encoders for Diffusion-based Image Inpainting","display_name":"Dual Encoders for Diffusion-based Image Inpainting","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355791","doi":"https://doi.org/10.1109/icassp49660.2025.10890576"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5101891671","display_name":"Dezhi Zheng","orcid":"https://orcid.org/0000-0001-5055-3939"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezhi Zheng","raw_affiliation_strings":["Shenzhen University,Computer Vision Institute, School of Computer Science and Software Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,Computer Vision Institute, School of Computer Science and Software Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032382826","display_name":"Ying Deng","orcid":"https://orcid.org/0000-0003-4643-3525"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaijun Deng","raw_affiliation_strings":["Shenzhen University,Computer Vision Institute, School of Computer Science and Software Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,Computer Vision Institute, School of Computer Science and Software Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698854","display_name":"Jinbao Wang","orcid":"https://orcid.org/0000-0001-5916-8965"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinbao Wang","raw_affiliation_strings":["Shenzhen University,National Engineering Laboratory for Big Data System Computing Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,National Engineering Laboratory for Big Data System Computing Technology,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109508986","display_name":"Linlin Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linlin Shen","raw_affiliation_strings":["Shenzhen University,Computer Vision Institute, School of Computer Science and Software Engineering,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,Computer Vision Institute, School of Computer Science and Software Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9943000078201294,"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":0.9943000078201294,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9900000095367432,"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":0.9835000038146973,"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/inpainting","display_name":"Inpainting","score":0.8824319839477539},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6210021376609802},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6196784973144531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5982174873352051},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5615304112434387},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5050316452980042},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5041197538375854},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.49793076515197754},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3418315649032593},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07525047659873962}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.8824319839477539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6210021376609802},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6196784973144531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5982174873352051},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5615304112434387},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5050316452980042},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5041197538375854},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.49793076515197754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3418315649032593},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07525047659873962},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329174","display_name":"Shenzhen Municipal Science and Technology Innovation Council","ror":"https://ror.org/017n8df75"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2133665775","https://openalex.org/W2738588019","https://openalex.org/W2752796333","https://openalex.org/W2962785568","https://openalex.org/W2963420272","https://openalex.org/W3035426499","https://openalex.org/W3199003182","https://openalex.org/W3214312641","https://openalex.org/W4312497550","https://openalex.org/W4312870564","https://openalex.org/W4312933868","https://openalex.org/W4313069043","https://openalex.org/W4385271281","https://openalex.org/W4386071604","https://openalex.org/W4389539423","https://openalex.org/W4390872829","https://openalex.org/W4390873054","https://openalex.org/W4402727155","https://openalex.org/W4404024902","https://openalex.org/W4404625217","https://openalex.org/W4404726022","https://openalex.org/W6637373629","https://openalex.org/W6640963894","https://openalex.org/W6747827861","https://openalex.org/W6762931180","https://openalex.org/W6779823529","https://openalex.org/W6850630192","https://openalex.org/W6853257882","https://openalex.org/W6856607740","https://openalex.org/W6860658276","https://openalex.org/W6866689913"],"related_works":["https://openalex.org/W2017457812","https://openalex.org/W3178025616","https://openalex.org/W2060947339","https://openalex.org/W2131831293","https://openalex.org/W2946160871","https://openalex.org/W3035059915","https://openalex.org/W1995073329","https://openalex.org/W425542480","https://openalex.org/W49967185","https://openalex.org/W2107727507"],"abstract_inverted_index":{"Current":[0],"diffusion-based":[1],"inpainting":[2],"models":[3,85,111],"struggle":[4],"to":[5,20,43,66,83,93],"preserve":[6],"unmasked":[7],"regions":[8],"or":[9],"generate":[10,21],"highly":[11],"coherent":[12],"content.":[13],"Additionally,":[14],"it":[15],"is":[16],"hard":[17],"for":[18,24],"them":[19],"meaningful":[22],"content":[23],"3D":[25],"inpainting.":[26],"To":[27],"tackle":[28],"these":[29],"challenges,":[30],"we":[31,48,89],"design":[32],"a":[33,53],"plug-and-play":[34,114],"branch":[35,115],"that":[36,110],"runs":[37],"through":[38],"the":[39,60,74,78,95,118],"entire":[40],"generation":[41],"process":[42],"enhance":[44],"existing":[45],"models.":[46],"Specifically,":[47],"utilize":[49],"dual":[50,79],"encoders":[51,80],"-":[52],"Convolutional":[54],"Neural":[55],"Network":[56],"(CNN)":[57],"encoder":[58],"and":[59,73,107,122],"pre-trained":[61],"Variational":[62],"AutoEncoder":[63],"(VAE)":[64],"encoder,":[65],"encode":[67],"masked":[68],"images.":[69],"The":[70],"latent":[71],"code":[72],"feature":[75],"map":[76],"from":[77],"are":[81],"fed":[82],"diffusion":[84],"simultaneously.":[86],"In":[87],"addition,":[88],"apply":[90],"Zero-padded":[91],"initialization":[92],"solve":[94],"problem":[96],"of":[97,120],"mode":[98],"collapse":[99],"caused":[100],"by":[101],"this":[102],"branch.":[103],"Experiments":[104],"on":[105],"BrushBench":[106],"EditBench":[108],"demonstrate":[109],"with":[112],"our":[113,123],"can":[116],"improve":[117],"coherence":[119],"inpainting,":[121],"model":[124],"achieves":[125],"new":[126],"state-of-the-art":[127],"results.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}