{"id":"https://openalex.org/W4400448381","doi":"https://doi.org/10.1109/tpami.2024.3424835","title":"High-Fidelity and Efficient Pluralistic Image Completion With Transformers","display_name":"High-Fidelity and Efficient Pluralistic Image Completion With Transformers","publication_year":2024,"publication_date":"2024-07-09","ids":{"openalex":"https://openalex.org/W4400448381","doi":"https://doi.org/10.1109/tpami.2024.3424835","pmid":"https://pubmed.ncbi.nlm.nih.gov/38980773"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3424835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3424835","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5026082030","display_name":"Ziyu Wan","orcid":"https://orcid.org/0000-0003-2421-3484"},"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":"Ziyu Wan","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-2421-3484","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031225215","display_name":"Jingbo Zhang","orcid":"https://orcid.org/0000-0003-0009-2315"},"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":"Jingbo Zhang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-0009-2315","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364587","display_name":"Dongdong Chen","orcid":"https://orcid.org/0000-0002-4642-4373"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongdong Chen","raw_affiliation_strings":["Microsoft Cloud+AI, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4642-4373","affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-7014-5377","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6385,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84247519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"46","issue":"12","first_page":"9612","last_page":"9629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9768000245094299,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9652000069618225,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6062177419662476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6050073504447937},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5788716077804565},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5274888277053833},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4755677580833435},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4549122154712677},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.43304163217544556},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3759458661079407},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32415035367012024},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1602993905544281},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12718403339385986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6062177419662476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050073504447937},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5788716077804565},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5274888277053833},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4755677580833435},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4549122154712677},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.43304163217544556},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3759458661079407},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32415035367012024},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1602993905544281},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12718403339385986},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3424835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3424835","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38980773","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38980773","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1975049209","https://openalex.org/W1993120651","https://openalex.org/W1999360130","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2295936755","https://openalex.org/W2423557781","https://openalex.org/W2502312327","https://openalex.org/W2594057160","https://openalex.org/W2611104282","https://openalex.org/W2732026016","https://openalex.org/W2738588019","https://openalex.org/W2752796333","https://openalex.org/W2768959015","https://openalex.org/W2798365772","https://openalex.org/W2803418063","https://openalex.org/W2896457183","https://openalex.org/W2907097116","https://openalex.org/W2908510526","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2963083275","https://openalex.org/W2963255313","https://openalex.org/W2963351113","https://openalex.org/W2963420272","https://openalex.org/W2982763192","https://openalex.org/W2989207674","https://openalex.org/W2989505547","https://openalex.org/W3034482833","https://openalex.org/W3035002246","https://openalex.org/W3035251567","https://openalex.org/W3043547428","https://openalex.org/W3085536450","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3111079994","https://openalex.org/W3130440474","https://openalex.org/W3136958399","https://openalex.org/W3170841864","https://openalex.org/W3171125843","https://openalex.org/W3175375202","https://openalex.org/W3180355996","https://openalex.org/W3199003182","https://openalex.org/W3202296139","https://openalex.org/W3204170321","https://openalex.org/W3206082266","https://openalex.org/W3212516020","https://openalex.org/W4226018021","https://openalex.org/W4240726888","https://openalex.org/W4312383858","https://openalex.org/W4312497550","https://openalex.org/W4312579703","https://openalex.org/W4312771828","https://openalex.org/W4312933868","https://openalex.org/W4313021454","https://openalex.org/W4313051036","https://openalex.org/W4324116696","https://openalex.org/W4385245566","https://openalex.org/W4392543517","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6724804524","https://openalex.org/W6734030655","https://openalex.org/W6745992979","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6757857098","https://openalex.org/W6763509872","https://openalex.org/W6765779288","https://openalex.org/W6779823529","https://openalex.org/W6779879114","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6791190667","https://openalex.org/W6842542927"],"related_works":["https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W3125091513","https://openalex.org/W4318832338","https://openalex.org/W1919390113","https://openalex.org/W4248383205","https://openalex.org/W4234745530","https://openalex.org/W2146383839","https://openalex.org/W2231829109","https://openalex.org/W2916591301"],"abstract_inverted_index":{"Image":[0],"completion":[1,263],"has":[2],"made":[3],"tremendous":[4],"progress":[5],"with":[6,90,95,105,141],"convolutional":[7],"neural":[8],"networks":[9],"(CNNs),":[10],"because":[11],"of":[12,80,118,168,179,220,249],"their":[13,47,59],"powerful":[14],"texture":[15,93,116,221],"modeling":[16,50],"capacity.":[17],"However,":[18],"due":[19],"to":[20,64,83,193,215,230,261],"some":[21,106],"inherent":[22],"properties":[23],"(e.g.,":[24],"local":[25,115],"inductive":[26],"prior,":[27],"spatial-invariant":[28],"kernels),":[29],"CNNs":[30],"do":[31],"not":[32],"perform":[33],"well":[34],"in":[35,49,71,247],"understanding":[36],"global":[37,182],"structures":[38,103],"or":[39],"naturally":[40],"support":[41],"pluralistic":[42,84,101,272],"completion.":[43],"Recently,":[44],"transformers":[45],"demonstrate":[46],"power":[48],"the":[51,69,78,110,114,123,136,174,180,187,218,232,240],"long-term":[52],"relationship":[53],"and":[54,92,177,203,223,268,281],"generating":[55],"diverse":[56],"results,":[57],"but":[58,140],"computation":[60],"complexity":[61],"is":[62,135],"quadratic":[63],"input":[65],"length,":[66],"thus":[67],"hampering":[68],"application":[70],"processing":[72],"high-resolution":[73,124],"images.":[74,126],"This":[75],"paper":[76],"brings":[77],"best":[79],"both":[81],"worlds":[82],"image":[85,257],"completion:":[86],"appearance":[87],"prior":[88],"reconstruction":[89],"transformer":[91,99],"replenishment":[94],"CNN.":[96],"The":[97],"former":[98],"recovers":[100],"coherent":[102,204],"together":[104],"coarse":[107,119],"textures,":[108],"while":[109],"latter":[111],"CNN":[112,189],"enhances":[113],"details":[117],"priors":[120],"guided":[121,197,213],"by":[122,150],"masked":[125],"To":[127,199],"decode":[128],"diversified":[129],"outputs":[130],"from":[131],"transformers,":[132],"auto-regressive":[133,293],"sampling":[134,159],"most":[137],"common":[138],"method,":[139],"extremely":[142],"low":[143],"efficiency.":[144],"We":[145],"further":[146],"overcome":[147],"this":[148],"issue":[149],"proposing":[151],"a":[152,208],"new":[153],"decoding":[154,289],"strategy,":[155],"temperature":[156],"annealing":[157],"probabilistic":[158],"(TAPS),":[160],"which":[161],"firstly":[162],"achieves":[163],"more":[164,201],"than":[165],"70\u00d7":[166],"speedup":[167],"inference":[169],"at":[170],"most,":[171],"meanwhile":[172,225],"maintaining":[173],"high":[175],"quality":[176],"diversity":[178,267],"sampled":[181],"structures.":[183],"Moreover,":[184],"we":[185,206,238],"find":[186],"full":[188],"architecture":[190],"will":[191],"lead":[192],"suboptimal":[194],"solutions":[195],"for":[196,271],"upsampling.":[198],"render":[200],"realistic":[202],"contents,":[205],"design":[207],"novel":[209],"module,":[210],"named":[211],"texture-aware":[212],"attention,":[214],"concurrently":[216],"consider":[217],"procedures":[219],"copy":[222],"generation,":[224],"raising":[226],"several":[227],"important":[228],"modifications":[229],"solve":[231],"boundary":[233],"artifacts.":[234],"Through":[235],"dense":[236],"experiments,":[237],"found":[239],"proposed":[241],"method":[242],"vastly":[243],"outperforms":[244],"state-of-the-art":[245],"methods":[246],"terms":[248],"four":[250],"aspects:":[251],"1)":[252],"large":[253,279],"performance":[254],"boost":[255],"on":[256,278],"fidelity":[258,270],"even":[259],"compared":[260],"deterministic":[262],"methods;":[264],"2)":[265],"better":[266],"higher":[269,288],"completion;":[273],"3)":[274],"exceptional":[275],"generalization":[276],"ability":[277],"masks":[280],"generic":[282],"dataset,":[283],"like":[284],"ImageNet.":[285],"4)":[286],"Much":[287],"efficiency":[290],"over":[291],"previous":[292],"based":[294],"methods.":[295]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}