{"id":"https://openalex.org/W3206082266","doi":"https://doi.org/10.1145/3474085.3475436","title":"Diverse Image Inpainting with Bidirectional and Autoregressive Transformers","display_name":"Diverse Image Inpainting with Bidirectional and Autoregressive Transformers","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206082266","doi":"https://doi.org/10.1145/3474085.3475436","mag":"3206082266"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475436","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-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":"https://openalex.org/A5090126397","display_name":"Yingchen Yu","orcid":"https://orcid.org/0000-0002-7893-0764"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yingchen Yu","raw_affiliation_strings":["Nanyang Technological University & Alibaba Group, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University & Alibaba Group, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064046791","display_name":"Fangneng Zhan","orcid":"https://orcid.org/0000-0003-1502-6847"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fangneng Zhan","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101182307","display_name":"Rongliang Wu","orcid":"https://orcid.org/0000-0002-5586-0628"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rongliang WU","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043984873","display_name":"Jianxiong Pan","orcid":"https://orcid.org/0000-0002-6969-1407"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxiong Pan","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003133537","display_name":"Kaiwen Cui","orcid":"https://orcid.org/0000-0003-1007-5113"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kaiwen Cui","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023507910","display_name":"Shijian Lu","orcid":"https://orcid.org/0000-0002-6766-2506"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shijian Lu","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009442846","display_name":"Feiying Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiying Ma","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101763148","display_name":"Xuansong Xie","orcid":"https://orcid.org/0000-0002-3671-799X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuansong Xie","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100382077","display_name":"Chunyan Miao","orcid":"https://orcid.org/0000-0002-0300-3448"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chunyan Miao","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5090126397"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":9.9051,"has_fulltext":false,"cited_by_count":144,"citation_normalized_percentile":{"value":0.98757613,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"78"},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9962999820709229,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.982200026512146,"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":0.9484934210777283},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.8780876994132996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6607739329338074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6555348038673401},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5354673266410828},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5223916172981262},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.47412538528442383},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4526980221271515},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4464157521724701},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4164399206638336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18730422854423523},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06347599625587463}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.9484934210777283},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8780876994132996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607739329338074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6555348038673401},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5354673266410828},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5223916172981262},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.47412538528442383},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4526980221271515},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4464157521724701},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4164399206638336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18730422854423523},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06347599625587463},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475436","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1834627138","https://openalex.org/W1975049209","https://openalex.org/W1993120651","https://openalex.org/W2093212899","https://openalex.org/W2100415658","https://openalex.org/W2133665775","https://openalex.org/W2161348917","https://openalex.org/W2165736859","https://openalex.org/W2254014057","https://openalex.org/W2295936755","https://openalex.org/W2331128040","https://openalex.org/W2732026016","https://openalex.org/W2738588019","https://openalex.org/W2798365772","https://openalex.org/W2904785373","https://openalex.org/W2962785568","https://openalex.org/W2962974533","https://openalex.org/W2963073614","https://openalex.org/W2963255313","https://openalex.org/W2963420272","https://openalex.org/W2963709863","https://openalex.org/W2963712589","https://openalex.org/W2963981733","https://openalex.org/W2964082390","https://openalex.org/W2987563462","https://openalex.org/W3035251567","https://openalex.org/W3035575271","https://openalex.org/W3043547428","https://openalex.org/W3096509145","https://openalex.org/W3108554146","https://openalex.org/W3120387510","https://openalex.org/W3167101089","https://openalex.org/W4240726888","https://openalex.org/W4249710618"],"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/W2587407424","https://openalex.org/W2907830442"],"abstract_inverted_index":{"Image":[0],"inpainting":[1,91,160],"is":[2,70],"an":[3,88],"underdetermined":[4],"inverse":[5],"problem,":[6],"which":[7,112,131],"naturally":[8,113],"allows":[9,114],"diverse":[10,55,116],"contents":[11,56],"to":[12,49,108],"fill":[13],"up":[14],"the":[15,64,106,115,125],"missing":[16,119,139],"or":[17],"corrupted":[18,73],"regions":[19,75,140],"realistically.":[20],"Prevalent":[21],"approaches":[22],"using":[23],"convolutional":[24],"neural":[25],"networks":[26],"(CNNs)":[27],"can":[28],"synthesize":[29],"visually":[30],"pleasant":[31],"contents,":[32],"but":[33],"CNNs":[34],"suffer":[35],"from":[36,82],"limited":[37],"perception":[38],"fields":[39],"for":[40,101,141],"capturing":[41],"global":[42],"features.":[43],"With":[44],"image-level":[45],"attention,":[46],"transformers":[47,69,107],"enable":[48],"model":[50,128],"long-range":[51],"dependencies":[52],"and":[53,156,162],"generate":[54],"with":[57,80],"autoregressive":[58,68,98,110],"modeling":[59,134],"of":[60,118,135,138],"pixel-sequence":[61],"distributions.":[62],"However,":[63],"unidirectional":[65],"attention":[66],"in":[67,158],"suboptimal":[71],"as":[72],"image":[74,90,102,143,159],"may":[76],"have":[77],"arbitrary":[78],"shapes":[79],"contexts":[81],"any":[83],"direction.":[84],"We":[85],"propose":[86],"BAT-Fill,":[87],"innovative":[89],"framework":[92],"that":[93,151],"introduces":[94],"a":[95],"novel":[96],"bidirectional":[97],"transformer":[99],"(BAT)":[100],"inpainting.":[103],"BAT":[104],"utilizes":[105],"learn":[109],"distributions,":[111],"generation":[117],"contents.":[120],"In":[121],"addition,":[122],"it":[123],"incorporates":[124],"masked":[126],"language":[127],"like":[129],"BERT,":[130],"enables":[132],"bidirectionally":[133],"contextual":[136],"information":[137],"better":[142],"completion.":[144],"Extensive":[145],"experiments":[146],"over":[147],"multiple":[148],"datasets":[149],"show":[150],"BAT-Fill":[152],"achieves":[153],"superior":[154],"diversity":[155],"fidelity":[157],"qualitatively":[161],"quantitatively.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":40},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}