{"id":"https://openalex.org/W4390241477","doi":"https://doi.org/10.1109/tmm.2023.3347094","title":"Deep Unrestricted Document Image Rectification","display_name":"Deep Unrestricted Document Image Rectification","publication_year":2023,"publication_date":"2023-12-26","ids":{"openalex":"https://openalex.org/W4390241477","doi":"https://doi.org/10.1109/tmm.2023.3347094"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3347094","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.08796","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068201443","display_name":"Hao Feng","orcid":"https://orcid.org/0000-0001-8127-6639"},"institutions":[{"id":"https://openalex.org/I4210114190","display_name":"Shanghai Zhangjiang Laboratory","ror":"https://ror.org/0208qbg77","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114190"]},{"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":"Hao Feng","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","Zhangjiang Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Zhangjiang Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210114190"]},{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101422154","display_name":"Shaokai Liu","orcid":"https://orcid.org/0009-0004-6095-6132"},"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":"Shaokai Liu","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089561793","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-9624-7451"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":["Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia"],"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"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":"Wengang Zhou","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"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":"Houqiang Li","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.952,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.99996,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":94},"biblio":{"volume":"26","issue":null,"first_page":"6142","last_page":"6154"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwriting Recognition and Text Detection","score":0.9975,"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/T10601","display_name":"Handwriting Recognition and Text Detection","score":0.9975,"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 Image Forgery Detection and Identification","score":0.9837,"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/T10824","display_name":"Shape Matching and Object Recognition","score":0.9466,"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/image-rectification","display_name":"Image rectification","score":0.67243904},{"id":"https://openalex.org/keywords/document-image-analysis","display_name":"Document Image Analysis","score":0.646098},{"id":"https://openalex.org/keywords/image-forgery-detection","display_name":"Image Forgery Detection","score":0.53894},{"id":"https://openalex.org/keywords/scene-text-recognition","display_name":"Scene Text Recognition","score":0.531036},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text Detection","score":0.52653},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.51984316},{"id":"https://openalex.org/keywords/jpeg-compression","display_name":"JPEG Compression","score":0.510351},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.41825455}],"concepts":[{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.86403847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84629},{"id":"https://openalex.org/C171614847","wikidata":"https://www.wikidata.org/wiki/Q1262415","display_name":"Image rectification","level":4,"score":0.67243904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5931951},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.51984316},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43171826},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43142816},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.43100196},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4267051},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42668432},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.41825455},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.412903},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39000678},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34001678},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3245027},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3347094","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2304.08796","pdf_url":"https://arxiv.org/pdf/2304.08796","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2304.08796","pdf_url":"https://arxiv.org/pdf/2304.08796","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"U20A20183"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"62021001"}],"datasets":[],"versions":[],"referenced_works_count":73,"referenced_works":["https://openalex.org/W1517058277","https://openalex.org/W1575866751","https://openalex.org/W1580389772","https://openalex.org/W1647671624","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1998042868","https://openalex.org/W2001642682","https://openalex.org/W2013822448","https://openalex.org/W2027238116","https://openalex.org/W2044607679","https://openalex.org/W2071106922","https://openalex.org/W2090518410","https://openalex.org/W2096085152","https://openalex.org/W2098270921","https://openalex.org/W2112193096","https://openalex.org/W2113640817","https://openalex.org/W2115263911","https://openalex.org/W2120449447","https://openalex.org/W2121498135","https://openalex.org/W2133665775","https://openalex.org/W2138283657","https://openalex.org/W2149884040","https://openalex.org/W2150504994","https://openalex.org/W2151103935","https://openalex.org/W2161175365","https://openalex.org/W2169527406","https://openalex.org/W2170265032","https://openalex.org/W2170332640","https://openalex.org/W2194775991","https://openalex.org/W2412396436","https://openalex.org/W2743390484","https://openalex.org/W2777280533","https://openalex.org/W2794680924","https://openalex.org/W2798905980","https://openalex.org/W2894857688","https://openalex.org/W2902561591","https://openalex.org/W2904479140","https://openalex.org/W2963587345","https://openalex.org/W2981413347","https://openalex.org/W2981771415","https://openalex.org/W2985998306","https://openalex.org/W2998621280","https://openalex.org/W3019533076","https://openalex.org/W3022710784","https://openalex.org/W3025800305","https://openalex.org/W3047176958","https://openalex.org/W3049081235","https://openalex.org/W3094927345","https://openalex.org/W3096609285","https://openalex.org/W3109908659","https://openalex.org/W3120043490","https://openalex.org/W3206086363","https://openalex.org/W3207713347","https://openalex.org/W3210178292","https://openalex.org/W4210337376","https://openalex.org/W4214546754","https://openalex.org/W4221149365","https://openalex.org/W4251279466","https://openalex.org/W4285529970","https://openalex.org/W4285981773","https://openalex.org/W4304091571","https://openalex.org/W4311992557","https://openalex.org/W4312233877","https://openalex.org/W4312462986","https://openalex.org/W4312891697","https://openalex.org/W4313163001","https://openalex.org/W4321368497","https://openalex.org/W4366330503","https://openalex.org/W4385245566","https://openalex.org/W4386141732","https://openalex.org/W4389575063","https://openalex.org/W764651262"],"related_works":["https://openalex.org/W2755641224","https://openalex.org/W2630526526","https://openalex.org/W2392564394","https://openalex.org/W2375893148","https://openalex.org/W2372715484","https://openalex.org/W2348028808","https://openalex.org/W2069867538","https://openalex.org/W2036165812","https://openalex.org/W2021845495","https://openalex.org/W139502281"],"abstract_inverted_index":{"In":[0,65],"recent":[1],"years,":[2],"tremendous":[3],"efforts":[4],"have":[5],"been":[6],"made":[7],"on":[8,82],"document":[9,21,57,76,126,143,176,205],"image":[10,35,58,77,144,206],"rectification,":[11,59,78,207],"but":[12],"existing":[13],"advanced":[14],"algorithms":[15],"are":[16,180],"limited":[17],"to":[18,137],"processing":[19],"restricted":[20],"images,":[22],"i.e.,":[23],"the":[24,33,83,100,118,123,129,158,167,172,183,186,209],"input":[25,84],"images":[26,127],"must":[27],"incorporate":[28],"a":[29,38,53,71,105,149,200],"complete":[30],"document.":[31],"Once":[32],"captured":[34],"merely":[36],"involves":[37],"local":[39],"text":[40],"region,":[41],"its":[42],"rectification":[43,159,173],"quality":[44],"is":[45,135,166],"degraded":[46],"and":[47,113,128,153,182,188,212],"unsatisfactory.":[48],"Our":[49,87],"previously":[50],"proposed":[51],"DocTr,":[52],"transformer-assisted":[54],"network":[55],"for":[56,75,109,141,156,171,203],"also":[60],"suffers":[61],"from":[62],"this":[63,66,165],"limitation.":[64],"work,":[67],"we":[68,98,116,147],"present":[69],"DocTr++,":[70],"novel":[72],"unified":[73],"framework":[74],"without":[79],"any":[80],"restrictions":[81],"distorted":[85,125],"images.":[86,177],"major":[88],"technical":[89],"improvements":[90],"can":[91],"be":[92],"concluded":[93],"in":[94],"three":[95],"aspects.":[96],"Firstly,":[97],"upgrade":[99],"original":[101],"architecture":[102],"by":[103],"adopting":[104],"hierarchical":[106],"encoder-decoder":[107],"structure":[108],"multi-scale":[110],"representation":[111],"extraction":[112],"parsing.":[114],"Secondly,":[115],"reformulate":[117],"pixel-wise":[119],"mapping":[120],"relationship":[121],"between":[122],"unrestricted":[124,142,175],"distortion-free":[130],"counterparts.":[131],"The":[132],"obtained":[133],"data":[134],"used":[136],"train":[138],"our":[139,162,191,195],"DocTr++":[140,196],"rectification.":[145],"Thirdly,":[146],"contribute":[148],"real-world":[150],"test":[151],"set":[152],"metrics":[154],"applicable":[155],"evaluating":[157],"quality.":[160],"To":[161],"best":[163],"knowledge,":[164],"first":[168],"learning-based":[169,215],"method":[170],"of":[174,190,214],"Extensive":[178],"experiments":[179],"conducted,":[181],"results":[184],"demonstrate":[185],"effectiveness":[187],"superiority":[189],"method.":[192],"We":[193],"hope":[194],"will":[197],"serve":[198],"as":[199],"strong":[201],"baseline":[202],"generic":[204],"prompting":[208],"further":[210],"advancement":[211],"application":[213],"algorithms.":[216]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4390241477","counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2024-11-23T16:13:51.976981","created_date":"2023-12-27"}