{"id":"https://openalex.org/W7138277327","doi":"https://doi.org/10.1609/aaai.v40i12.37933","title":"Axis-Aligned Document Dewarping","display_name":"Axis-Aligned Document Dewarping","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138277327","doi":"https://doi.org/10.1609/aaai.v40i12.37933"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i12.37933","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37933","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i12.37933","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129652053","display_name":"Chaoyun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chaoyun Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063942521","display_name":"I\u2010Chao Shen","orcid":"https://orcid.org/0000-0003-4201-3793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"I-Chao Shen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129663030","display_name":"Takeo Igarashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takeo Igarashi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129699204","display_name":"Caigui Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caigui Jiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5129652053"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62788963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"12","first_page":"9702","last_page":"9710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8611000180244446,"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":"Handwritten Text Recognition Techniques","score":0.8611000180244446,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.042399998754262924,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.020800000056624413,"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/preprocessor","display_name":"Preprocessor","score":0.5525000095367432},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4997999966144562},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4641999900341034},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.459199994802475},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.43479999899864197},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4194999933242798},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3889999985694885},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.38089999556541443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6554999947547913},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5525000095367432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210000276565552},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.38089999556541443},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3057999908924103},{"id":"https://openalex.org/C136520226","wikidata":"https://www.wikidata.org/wiki/Q302814","display_name":"Geometric data analysis","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i12.37933","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37933","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i12.37933","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37933","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Document":[0],"dewarping":[1,96],"is":[2,32,37],"crucial":[3],"for":[4,68,82,99],"many":[5],"applications.":[6],"However,":[7],"existing":[8,138],"learning-based":[9],"methods":[10],"rely":[11],"heavily":[12],"on":[13,136],"supervised":[14],"regression":[15],"with":[16,47,119],"annotated":[17],"data":[18],"without":[19],"fully":[20],"leveraging":[21],"the":[22,48,53,69,83,95,100,141],"inherent":[23,49],"geometric":[24,76,115],"properties":[25],"of":[26,52],"physical":[27],"documents.":[28,59],"Our":[29],"key":[30],"insight":[31],"that":[33,111],"a":[34,105,129],"well-dewarped":[35],"document":[36,80],"defined":[38],"by":[39,144],"its":[40],"axis-aligned":[41,50,75],"feature":[42],"lines.":[43],"This":[44],"property":[45],"aligns":[46,118],"nature":[51],"discrete":[54],"grid":[55],"geometry":[56],"in":[57],"planar":[58],"Harnessing":[60],"this":[61],"property,":[62],"we":[63,72,86,103],"introduce":[64,104],"three":[65],"synergistic":[66],"contributions:":[67],"training":[70],"phase,":[71,85,102],"propose":[73,87],"an":[74,88],"constraint":[77],"to":[78,93,146],"enhance":[79],"dewarping;":[81],"inference":[84],"axis":[89],"alignment":[90],"preprocessing":[91],"strategy":[92],"reduce":[94],"difficulty;":[97],"and":[98,117],"evaluation":[101],"new":[106],"metric,":[107],"Axis-Aligned":[108],"Distortion":[109],"(AAD),":[110],"not":[112],"only":[113],"incorporates":[114],"meaning":[116],"human":[120],"visual":[121],"perception":[122],"but":[123],"also":[124],"demonstrates":[125],"greater":[126],"robustness.":[127],"As":[128],"result,":[130],"our":[131],"method":[132],"achieves":[133],"state-of-the-art":[134],"performance":[135],"multiple":[137],"benchmarks,":[139],"improving":[140],"AAD":[142],"metric":[143],"18.2%":[145],"34.5%.":[147]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}