{"id":"https://openalex.org/W4285981773","doi":"https://doi.org/10.1145/3528233.3530756","title":"Learning From Documents in the Wild to Improve Document Unwarping","display_name":"Learning From Documents in the Wild to Improve Document Unwarping","publication_year":2022,"publication_date":"2022-07-20","ids":{"openalex":"https://openalex.org/W4285981773","doi":"https://doi.org/10.1145/3528233.3530756"},"language":"en","primary_location":{"id":"doi:10.1145/3528233.3530756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3528233.3530756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings","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/A5100664932","display_name":"Ke Ma","orcid":"https://orcid.org/0000-0001-8853-7782"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ke Ma","raw_affiliation_strings":["Snap Inc., United States of America"],"affiliations":[{"raw_affiliation_string":"Snap Inc., United States of America","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111320476","display_name":"Sagnik Das","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sagnik Das","raw_affiliation_strings":["Stony Brook University, United States of America"],"affiliations":[{"raw_affiliation_string":"Stony Brook University, United States of America","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034904892","display_name":"Zhixin Shu","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhixin Shu","raw_affiliation_strings":["Adobe Research, United States of America"],"affiliations":[{"raw_affiliation_string":"Adobe Research, United States of America","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076307452","display_name":"Dimitris Samaras","orcid":"https://orcid.org/0000-0002-1373-0294"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitris Samaras","raw_affiliation_strings":["Stony Brook University, United States of America"],"affiliations":[{"raw_affiliation_string":"Stony Brook University, United States of America","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100664932"],"corresponding_institution_ids":["https://openalex.org/I4210142583"],"apc_list":null,"apc_paid":null,"fwci":3.4659,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.939945,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9771999716758728,"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":0.9684000015258789,"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/computer-science","display_name":"Computer science","score":0.8271718621253967},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.7006910443305969},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6085034012794495},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5865006446838379},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.567478597164154},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.527802586555481},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4608888328075409},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45930254459381104},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4288037121295929},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.42670345306396484},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4131714403629303},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3898293972015381},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.383034884929657},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32879120111465454},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.18235227465629578},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.16814732551574707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8271718621253967},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7006910443305969},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6085034012794495},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5865006446838379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.567478597164154},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.527802586555481},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4608888328075409},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45930254459381104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4288037121295929},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.42670345306396484},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4131714403629303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3898293972015381},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.383034884929657},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32879120111465454},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.18235227465629578},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.16814732551574707},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3528233.3530756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3528233.3530756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307786","display_name":"Adobe Systems","ror":"https://ror.org/059tvcg64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W129202246","https://openalex.org/W236100371","https://openalex.org/W1510872511","https://openalex.org/W1517058277","https://openalex.org/W1901129140","https://openalex.org/W2001642682","https://openalex.org/W2027238116","https://openalex.org/W2033628967","https://openalex.org/W2038996541","https://openalex.org/W2058415666","https://openalex.org/W2084911352","https://openalex.org/W2090518410","https://openalex.org/W2098270921","https://openalex.org/W2120449447","https://openalex.org/W2124351162","https://openalex.org/W2129154891","https://openalex.org/W2155298532","https://openalex.org/W2168221043","https://openalex.org/W2194775991","https://openalex.org/W2220930568","https://openalex.org/W2412396436","https://openalex.org/W2562066862","https://openalex.org/W2753306693","https://openalex.org/W2786983711","https://openalex.org/W2798302325","https://openalex.org/W2798905980","https://openalex.org/W2894857688","https://openalex.org/W2981771415","https://openalex.org/W2982376094","https://openalex.org/W3034459056","https://openalex.org/W3047176958","https://openalex.org/W3094927345","https://openalex.org/W3175872176","https://openalex.org/W3207713347","https://openalex.org/W4214546754","https://openalex.org/W4253622118"],"related_works":["https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2399890175","https://openalex.org/W4308177873","https://openalex.org/W3202479762","https://openalex.org/W2480493049","https://openalex.org/W2592115649","https://openalex.org/W4322582183","https://openalex.org/W1937392525","https://openalex.org/W2347632764"],"abstract_inverted_index":{"Document":[0],"image":[1],"unwarping":[2,50,129],"is":[3],"important":[4],"for":[5,22,88,127],"document":[6,49,66,108,128,151],"digitization":[7],"and":[8,74,85,106,113,123,130,135,149,164,168],"analysis.":[9],"The":[10],"state-of-the-art":[11,155],"approach":[12],"relies":[13],"on":[14,35,157],"purely":[15],"synthetic":[16,105,148],"data":[17,169],"to":[18,47,99],"train":[19,100],"deep":[20],"networks":[21,29],"unwarping.":[23],"As":[24],"a":[25,94,102,132,145],"result,":[26],"the":[27,79,115],"trained":[28],"have":[30],"generalization":[31],"limitations":[32],"when":[33],"testing":[34],"real-world":[36,54,150],"images,":[37,152],"often":[38],"yielding":[39],"unsatisfying":[40],"results.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,111,153],"propose":[46,93,131],"improve":[48],"performance":[51,156],"by":[52],"incorporating":[53],"images":[55,67,84],"in":[56,71],"training.":[57],"We":[58,77,92],"collected":[59],"Document-in-the-Wild":[60],"(DIW)":[61],"dataset":[62],"contains":[63],"5000":[64],"captured":[65],"with":[68,101,144,160],"large":[69],"diversities":[70],"content,":[72],"shape,":[73],"capturing":[75],"environment.":[76],"annotate":[78],"boundaries":[80],"of":[81,104,117,147],"all":[82],"DIW":[83],"use":[86],"them":[87],"weakly":[89],"supervised":[90],"learning.":[91],"novel":[95],"network":[96],"architecture,":[97],"PaperEdge,":[98],"hybrid":[103],"real":[107],"images.":[109],"Additionally,":[110],"identify":[112],"analyze":[114],"flaws":[116],"popular":[118,158],"evaluation":[119],"metrics,":[120],"e.g.,":[121],"MS-SSIM":[122],"Local":[124],"Distortion":[125,141],"(LD),":[126],"more":[133],"robust":[134],"reliable":[136],"error":[137],"metric":[138],"called":[139],"Aligned":[140],"(AD).":[142],"Training":[143],"combination":[146],"demonstrate":[154],"benchmarks":[159],"comprehensive":[161],"quantitative":[162],"evaluations":[163],"ablation":[165],"studies.":[166],"Code":[167],"are":[170],"available":[171],"at":[172],"https://github.com/cvlab-stonybrook/PaperEdge.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":14}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}