{"id":"https://openalex.org/W4386598277","doi":"https://doi.org/10.1109/icip49359.2023.10222218","title":"Optimizing Transformer for Large-Hole Image Inpainting","display_name":"Optimizing Transformer for Large-Hole Image Inpainting","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386598277","doi":"https://doi.org/10.1109/icip49359.2023.10222218"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5100674833","display_name":"Zixuan Li","orcid":"https://orcid.org/0000-0002-7119-2113"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Li","raw_affiliation_strings":["Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064709384","display_name":"Yuan\u2010Gen Wang","orcid":"https://orcid.org/0000-0003-3010-4196"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan-Gen Wang","raw_affiliation_strings":["Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37987034"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1180","last_page":"1184"},"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":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9976000189781189,"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/T10531","display_name":"Advanced Vision and Imaging","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/inpainting","display_name":"Inpainting","score":0.836521565914154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6930813789367676},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6807685494422913},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6263114213943481},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.622070848941803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5333836674690247},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.46131157875061035},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4129487872123718},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4051051139831543},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.29448777437210083},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12394264340400696},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09932023286819458},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08123201131820679}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.836521565914154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930813789367676},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6807685494422913},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6263114213943481},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.622070848941803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333836674690247},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.46131157875061035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4129487872123718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4051051139831543},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29448777437210083},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12394264340400696},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09932023286819458},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08123201131820679},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3206975426","display_name":null,"funder_award_id":"62272116","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W2055132753","https://openalex.org/W2475287302","https://openalex.org/W2618530766","https://openalex.org/W2732026016","https://openalex.org/W2752796333","https://openalex.org/W2798365772","https://openalex.org/W2908510526","https://openalex.org/W2912083425","https://openalex.org/W2950689937","https://openalex.org/W2991377405","https://openalex.org/W2992838650","https://openalex.org/W3043547428","https://openalex.org/W3096831136","https://openalex.org/W3103556460","https://openalex.org/W3105938520","https://openalex.org/W3108554146","https://openalex.org/W3136958399","https://openalex.org/W3199003182","https://openalex.org/W3203538104","https://openalex.org/W4313051036","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6757817989","https://openalex.org/W6785302134"],"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/W1523707610"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"leveraging":[3],"Convolutional":[4],"Neural":[5],"Network":[6],"(CNN)":[7],"to":[8],"optimize":[9],"Transformer":[10,96],"(called":[11],"hybrid":[12,51],"model)":[13],"has":[14],"achieved":[15],"great":[16],"progress":[17],"in":[18,32],"image":[19,136],"inpainting.":[20],"However,":[21],"the":[22,26,38,57,63,82,92,101,105,111,115,124,128],"slow":[23],"growth":[24],"of":[25,30,94],"effective":[27],"receptive":[28],"field":[29],"CNN":[31],"processing":[33],"large-hole":[34],"regions":[35],"significantly":[36],"limits":[37],"overall":[39],"performance.":[40],"To":[41],"alleviate":[42],"this":[43,45],"problem,":[44],"paper":[46],"proposes":[47],"a":[48,131],"new":[49],"Transformer-CNN-based":[50],"framework":[52,69],"(termed":[53],"PUT+)":[54],"by":[55,110,130],"introducing":[56],"fast":[58],"Fourier":[59],"convolution":[60],"(FFC)":[61],"into":[62,85],"CNN-based":[64],"refinement":[65],"network.":[66],"The":[67,79,98,142],"proposed":[68,125],"introduces":[70],"an":[71],"improved":[72],"Patch-based":[73],"Vector":[74],"Quantized":[75],"Variational":[76],"Auto-Encoder":[77],"(P-VQVAE+).":[78],"encoder":[80],"transforms":[81],"masked":[83,102,140],"region":[84,103,117],"non-overlapping":[86],"patch-based":[87],"unquantized":[88],"feature":[89],"vectors":[90],"as":[91],"input":[93],"Un-Quantized":[95],"(UQ-Transformer).":[97],"decoder":[99],"restores":[100],"from":[104],"predicted":[106],"quantized":[107],"features":[108],"output":[109],"UQ-Transformer":[112],"while":[113],"maintaining":[114],"unmasked":[116],"unchanged.":[118],"Many":[119],"experimental":[120],"results":[121],"show":[122],"that":[123],"method":[126],"outperforms":[127],"state-of-the-art":[129],"large":[132,139],"margin,":[133],"especially":[134],"for":[135],"inpainting":[137],"with":[138],"areas.":[141],"code":[143],"is":[144],"available":[145],"at":[146],"https://github.com/GZHU-DVL/PUTplus.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}