{"id":"https://openalex.org/W4387596111","doi":"https://doi.org/10.1145/3581783.3612200","title":"Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model","display_name":"Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387596111","doi":"https://doi.org/10.1145/3581783.3612200"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612200","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.07222","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007476607","display_name":"Shiyuan Yang","orcid":"https://orcid.org/0000-0001-8213-5803"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shiyuan Yang","raw_affiliation_strings":["City University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-8213-5803","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373756","display_name":"Xiaodong Chen","orcid":"https://orcid.org/0000-0003-1624-2680"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Chen","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-1624-2680","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013972536","display_name":"Jing Liao","orcid":"https://orcid.org/0000-0001-7014-5377"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Liao","raw_affiliation_strings":["City University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-7014-5377","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7077,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.97852853,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3190","last_page":"3199"},"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":0.9995999932289124,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9391999840736389,"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/inpainting","display_name":"Inpainting","score":0.9721693992614746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7700814008712769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6777815222740173},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5711605548858643},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5611586570739746},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5375926494598389},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5331577062606812},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5201040506362915},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5088763236999512},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5086034536361694},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.499133825302124},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3588918149471283},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3492160439491272},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08613935112953186},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0859907865524292},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0816463828086853}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.9721693992614746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700814008712769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6777815222740173},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5711605548858643},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5611586570739746},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5375926494598389},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5331577062606812},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5201040506362915},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5088763236999512},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5086034536361694},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.499133825302124},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3588918149471283},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3492160439491272},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08613935112953186},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0859907865524292},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0816463828086853},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612200","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2310.07222","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.07222","pdf_url":"https://arxiv.org/pdf/2310.07222","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.07222","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.07222","pdf_url":"https://arxiv.org/pdf/2310.07222","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":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1993120651","https://openalex.org/W2054366734","https://openalex.org/W2105038642","https://openalex.org/W2796286534","https://openalex.org/W2798365772","https://openalex.org/W2896434438","https://openalex.org/W2962770929","https://openalex.org/W2963420272","https://openalex.org/W2964148878","https://openalex.org/W2982763192","https://openalex.org/W2990886896","https://openalex.org/W3013135579","https://openalex.org/W3035512475","https://openalex.org/W3036167779","https://openalex.org/W3043547428","https://openalex.org/W3103635814","https://openalex.org/W3136958399","https://openalex.org/W3199003182","https://openalex.org/W3212516020","https://openalex.org/W3216352822","https://openalex.org/W4214926101","https://openalex.org/W4281485151","https://openalex.org/W4312497550","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4319300158","https://openalex.org/W4385270985","https://openalex.org/W4385271281","https://openalex.org/W4386057725","https://openalex.org/W4386071604","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4386076425","https://openalex.org/W4386076532","https://openalex.org/W4386083141","https://openalex.org/W4386083151","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W2244018504","https://openalex.org/W4242046654","https://openalex.org/W3174923100","https://openalex.org/W3134074939","https://openalex.org/W2117562399","https://openalex.org/W4298074124","https://openalex.org/W3214306048","https://openalex.org/W2587407424"],"abstract_inverted_index":{"Recently,":[0],"text-to-image":[1],"denoising":[2],"diffusion":[3],"probabilistic":[4],"models":[5],"(DDPMs)":[6],"have":[7,14,127],"demonstrated":[8],"impressive":[9],"image":[10,20],"generation":[11],"capabilities":[12,149],"and":[13,49,61,111,131],"also":[15],"been":[16],"successfully":[17],"applied":[18],"to":[19,41,58,123,141],"inpainting.":[21],"However,":[22],"in":[23,152],"practice,":[24],"users":[25],"often":[26],"require":[27,62,114],"more":[28],"control":[29],"over":[30],"the":[31],"inpainting":[32,54,81,148],"process":[33],"beyond":[34],"textual":[35],"guidance,":[36,87],"especially":[37],"when":[38],"they":[39],"want":[40],"composite":[42],"objects":[43],"with":[44],"customized":[45,124],"appearance,":[46],"color,":[47],"shape,":[48],"layout.":[50],"Unfortunately,":[51],"existing":[52,142],"diffusion-based":[53],"methods":[55,144],"are":[56],"limited":[57],"single-modal":[59,143],"guidance":[60],"task-specific":[63,115],"training,":[64],"hindering":[65],"their":[66],"cross-modal":[67],"scalability.":[68],"To":[69],"address":[70],"these":[71,100],"limitations,":[72],"we":[73],"propose":[74],"Uni-paint,":[75],"a":[76,97],"unified":[77],"framework":[78],"for":[79],"multimodal":[80,147],"that":[82,134],"offers":[83],"various":[84],"modes":[85],"of":[86,99],"including":[88],"unconditional,":[89],"text-driven,":[90],"stroke-driven,":[91],"exemplar-driven":[92],"inpainting,":[93],"as":[94,96],"well":[95],"combination":[98],"modes.":[101],"Furthermore,":[102],"our":[103,136],"Uni-paint":[104],"is":[105,156],"based":[106],"on":[107,117],"pretrained":[108],"Stable":[109],"Diffusion":[110],"does":[112],"not":[113,150],"training":[116],"specific":[118],"datasets,":[119],"enabling":[120],"few-shot":[121],"generalizability":[122],"images.":[125],"We":[126],"conducted":[128],"extensive":[129],"qualitative":[130],"quantitative":[132],"evaluations":[133],"show":[135],"approach":[137],"achieves":[138],"comparable":[139],"results":[140],"while":[145],"offering":[146],"available":[151,157],"other":[153],"methods.":[154],"Code":[155],"at":[158],"https://github.com/ysy31415/unipaint.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}