{"id":"https://openalex.org/W4393405457","doi":"https://doi.org/10.1109/tpami.2024.3384406","title":"Transformer Based Pluralistic Image Completion With Reduced Information Loss","display_name":"Transformer Based Pluralistic Image Completion With Reduced Information Loss","publication_year":2024,"publication_date":"2024-04-02","ids":{"openalex":"https://openalex.org/W4393405457","doi":"https://doi.org/10.1109/tpami.2024.3384406","pmid":"https://pubmed.ncbi.nlm.nih.gov/38564348"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3384406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3384406","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/A5101800088","display_name":"Qiankun Liu","orcid":"https://orcid.org/0000-0002-7457-2090"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiankun Liu","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7457-2090","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102392263","display_name":"Yuqi Jiang","orcid":"https://orcid.org/0000-0003-3345-0553"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Jiang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3345-0553","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036850912","display_name":"Zhentao Tan","orcid":"https://orcid.org/0000-0001-9095-4462"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhentao Tan","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-9095-4462","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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":"middle","author":{"id":"https://openalex.org/A5100738025","display_name":"Ying Fu","orcid":"https://orcid.org/0000-0002-6677-694X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Fu","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6677-694X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045938154","display_name":"Qi Chu","orcid":"https://orcid.org/0000-0003-3028-0755"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-3028-0755","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081114810","display_name":"Gang Hua","orcid":"https://orcid.org/0000-0001-9522-6157"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Hua","raw_affiliation_strings":["Wormpex AI Research LLC, Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9522-6157","affiliations":[{"raw_affiliation_string":"Wormpex AI Research LLC, Bellevue, WA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064573190","display_name":"Nenghai Yu","orcid":"https://orcid.org/0000-0003-4417-9316"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenghai Yu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-4417-9316","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1914,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.96945023,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"46","issue":"10","first_page":"6652","last_page":"6668"},"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":0.9998999834060669,"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":0.9998999834060669,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9990000128746033,"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":0.9955999851226807,"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/encoder","display_name":"Encoder","score":0.7435147762298584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6829259395599365},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6413605213165283},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.6196340322494507},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6058619022369385},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.5933656096458435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5841224193572998},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5821967124938965},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5337606072425842},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.46271297335624695},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35882139205932617},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24786797165870667}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7435147762298584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829259395599365},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6413605213165283},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.6196340322494507},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6058619022369385},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.5933656096458435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5841224193572998},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5821967124938965},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5337606072425842},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.46271297335624695},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35882139205932617},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24786797165870667},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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.2024.3384406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3384406","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:38564348","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38564348","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":[{"id":"https://openalex.org/G2575069074","display_name":null,"funder_award_id":"62088101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6513703716","display_name":null,"funder_award_id":"62331006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8521839720","display_name":null,"funder_award_id":"62171038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W16016350","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1959608418","https://openalex.org/W1993120651","https://openalex.org/W1999360130","https://openalex.org/W2093212899","https://openalex.org/W2102409316","https://openalex.org/W2105038642","https://openalex.org/W2108598243","https://openalex.org/W2169574628","https://openalex.org/W2295936755","https://openalex.org/W2423557781","https://openalex.org/W2547875792","https://openalex.org/W2732026016","https://openalex.org/W2752796333","https://openalex.org/W2798365772","https://openalex.org/W2908510526","https://openalex.org/W2948672349","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2963255313","https://openalex.org/W2991377405","https://openalex.org/W3034482833","https://openalex.org/W3035574324","https://openalex.org/W3035637413","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3107942585","https://openalex.org/W3108554146","https://openalex.org/W3129576130","https://openalex.org/W3136958399","https://openalex.org/W3158252298","https://openalex.org/W3180355996","https://openalex.org/W3199003182","https://openalex.org/W3206082266","https://openalex.org/W3215626407","https://openalex.org/W3216270236","https://openalex.org/W4240726888","https://openalex.org/W4297095622","https://openalex.org/W4301206121","https://openalex.org/W4312309398","https://openalex.org/W4312383858","https://openalex.org/W4312388283","https://openalex.org/W4312446817","https://openalex.org/W4312497550","https://openalex.org/W4312771828","https://openalex.org/W4312804044","https://openalex.org/W4312815172","https://openalex.org/W4313007769","https://openalex.org/W4313051036","https://openalex.org/W4313156423","https://openalex.org/W4321793403","https://openalex.org/W4382465386","https://openalex.org/W4385245566","https://openalex.org/W4386071584","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6675401909","https://openalex.org/W6729448088","https://openalex.org/W6757817989","https://openalex.org/W6762931180","https://openalex.org/W6765779288","https://openalex.org/W6779879114","https://openalex.org/W6784333009","https://openalex.org/W6790978476","https://openalex.org/W6791190667","https://openalex.org/W6796761347","https://openalex.org/W6803872405","https://openalex.org/W6843018836"],"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/W3027110395","https://openalex.org/W3109174731","https://openalex.org/W4285125754"],"abstract_inverted_index":{"Transformer":[0,146],"based":[1,89,197],"methods":[2,198,214],"have":[3],"achieved":[4],"great":[5],"success":[6],"in":[7],"image":[8,38,113,200],"inpainting":[9,174,213],"recently.":[10],"However,":[11],"we":[12,84,102,178],"find":[13],"that":[14,190],"these":[15,82],"solutions":[16],"regard":[17],"each":[18],"pixel":[19],"as":[20,56,69,157,168,184],"a":[21,52,86,104],"token,":[22],"thus":[23],"suffering":[24],"from":[25,30,125,153],"an":[26,144],"information":[27,138],"loss":[28,139],"issue":[29],"two":[31],"aspects:":[32],"1)":[33],"They":[34,47],"downsample":[35],"the":[36,72,78,111,119,122,126,131,137,154,165,173],"input":[37,96,142,158],"into":[39,114],"much":[40,204],"lower":[41],"resolutions":[42],"for":[43,71],"efficiency":[44],"consideration.":[45],"2)":[46],"quantize":[48],"2563RGB":[49],"values":[50],"to":[51,94,171],"small":[53],"number":[54],"(such":[55],"512)":[57],"of":[58,64,77],"quantized":[59,65,166],"color":[60],"values.":[61],"The":[62,108],"indices":[63],"pixels":[66],"are":[67,222],"used":[68],"tokens":[70,117,128,167],"inputs":[73],"and":[74,118,162,181,202,207],"prediction":[75,169],"targets":[76],"transformer.":[79],"To":[80,135],"mitigate":[81],"issues,":[83],"propose":[85],"new":[87],"transformer":[88,196],"framework":[90],"called":[91],"\u201cPUT\u201d.":[92],"Specifically,":[93],"avoid":[95],"downsampling":[97],"while":[98,129],"maintaining":[99],"computation":[100],"efficiency,":[101],"design":[103],"patch-based":[105],"auto-encoder":[106],"P-VQVAE.":[107],"encoder":[109,156],"converts":[110],"masked":[112,123],"non-overlapped":[115],"patch":[116],"decoder":[120],"recovers":[121],"regions":[124,133],"inpainted":[127],"keeping":[130],"unmasked":[132],"unchanged.":[134],"eliminate":[136],"caused":[140],"by":[141],"quantization,":[143],"Un-quantized":[145],"is":[147],"applied.":[148],"It":[149],"directly":[150],"takes":[151],"features":[152],"P-VQVAE":[155],"without":[159],"any":[160],"quantization":[161],"only":[163],"regards":[164],"targets.Furthermore,":[170],"make":[172],"process":[175],"more":[176],"controllable,":[177],"introduce":[179],"semantic":[180],"structural":[182],"conditions":[183],"extra":[185],"guidance.":[186],"Extensive":[187],"experiments":[188],"show":[189],"our":[191],"method":[192],"greatly":[193],"outperforms":[194],"existing":[195],"on":[199,215],"fidelity":[201,209],"achieves":[203],"higher":[205],"diversity":[206],"better":[208],"than":[210],"state-of-the-art":[211],"pluralistic":[212],"complex":[216],"large-scale":[217],"datasets":[218],"(e.g.,":[219],"ImageNet).":[220],"Codes":[221],"available":[223],"athttps://github.com/liuqk3/PUT.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":7}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}