{"id":"https://openalex.org/W7109950815","doi":"https://doi.org/10.1145/3757377.3763913","title":"DvD: Unleashing a Generative Paradigm for Document Dewarping via Coordinates-based Diffusion Model","display_name":"DvD: Unleashing a Generative Paradigm for Document Dewarping via Coordinates-based Diffusion Model","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7109950815","doi":"https://doi.org/10.1145/3757377.3763913"},"language":null,"primary_location":{"id":"doi:10.1145/3757377.3763913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","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":null,"display_name":"Weiguang Zhang","orcid":"https://orcid.org/0009-0005-8783-0326"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weiguang Zhang","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University, Suzhou, China and University of Liverpool, Liverpool, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University, Suzhou, China and University of Liverpool, Liverpool, United Kingdom","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huangcheng Lu","orcid":"https://orcid.org/0009-0002-9808-8823"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huangcheng Lu","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University, Suzhou, China and University of Liverpool, Liverpool, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University, Suzhou, China and University of Liverpool, Liverpool, United Kingdom","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Maizhen Ning","orcid":"https://orcid.org/0000-0002-8842-4187"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maizhen Ning","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University, Suzhou, China and University of Liverpool, Liverpool, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University, Suzhou, China and University of Liverpool, Liverpool, United Kingdom","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaowei Huang","orcid":"https://orcid.org/0000-0001-6267-0366"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaowei Huang","raw_affiliation_strings":["University of Liverpool, Liverpool, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Liverpool, Liverpool, United Kingdom","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-0707-8076"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaizhu Huang","orcid":"https://orcid.org/0000-0002-3034-9639"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaizhu Huang","raw_affiliation_strings":["Duke Kunshan University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University, Suzhou, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qiufeng Wang","orcid":"https://orcid.org/0000-0002-0918-4606"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiufeng Wang","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I69356397"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86125471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.7305999994277954,"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":0.7305999994277954,"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":0.06759999692440033,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.024399999529123306,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6922000050544739},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5896000266075134},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.498199999332428},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4745999872684479},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.46369999647140503},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3084000051021576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080000281333923},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6922000050544739},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4745999872684479},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46369999647140503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4124999940395355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33899998664855957},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757377.3763913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7454974212","display_name":null,"funder_award_id":"92370119, 62436009, 62276258 and 62376113","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W236100371","https://openalex.org/W1517058277","https://openalex.org/W1580389772","https://openalex.org/W1901129140","https://openalex.org/W2027238116","https://openalex.org/W2033628967","https://openalex.org/W2084911352","https://openalex.org/W2090518410","https://openalex.org/W2098270921","https://openalex.org/W2115263911","https://openalex.org/W2120449447","https://openalex.org/W2121498135","https://openalex.org/W2161175365","https://openalex.org/W2169786363","https://openalex.org/W2170265032","https://openalex.org/W2220930568","https://openalex.org/W2412396436","https://openalex.org/W2798905980","https://openalex.org/W2894857688","https://openalex.org/W2981771415","https://openalex.org/W2985998306","https://openalex.org/W3025800305","https://openalex.org/W3049081235","https://openalex.org/W3094927345","https://openalex.org/W3207713347","https://openalex.org/W4214546754","https://openalex.org/W4221149365","https://openalex.org/W4285529970","https://openalex.org/W4285981773","https://openalex.org/W4304091571","https://openalex.org/W4312462986","https://openalex.org/W4312891697","https://openalex.org/W4367368531","https://openalex.org/W4387614553","https://openalex.org/W4389575063","https://openalex.org/W4390872088","https://openalex.org/W4390872297","https://openalex.org/W4394625559","https://openalex.org/W4402422281","https://openalex.org/W4402422666","https://openalex.org/W4402716330","https://openalex.org/W4402753885","https://openalex.org/W4402753965","https://openalex.org/W4403780658","https://openalex.org/W4404390483","https://openalex.org/W4404943901","https://openalex.org/W4405416283","https://openalex.org/W4407246897","https://openalex.org/W4409263268","https://openalex.org/W4410758641","https://openalex.org/W4413156197","https://openalex.org/W6891917377"],"related_works":[],"abstract_inverted_index":{"Document":[0],"dewarping":[1,63,140,145,159,174],"aims":[2],"to":[3,28,43,48,57,65,89,126],"rectify":[4],"deformations":[5],"in":[6,35,61],"photographic":[7],"document":[8,30,49,62,72,91,131,139,158],"images,":[9],"thus":[10],"improving":[11],"text":[12],"readability,":[13],"which":[14],"has":[15],"attracted":[16],"much":[17],"attention":[18],"and":[19,200,205],"made":[20],"great":[21],"progress,":[22],"but":[23],"it":[24,38,52],"is":[25,39,53],"still":[26],"challenging":[27],"preserve":[29],"structures.":[31,132],"Given":[32],"recent":[33],"advances":[34],"diffusion":[36,59],"models,":[37],"natural":[40],"for":[41,113],"us":[42],"consider":[44],"their":[45,66],"potential":[46],"applicability":[47],"dewarping.":[50],"However,":[51],"far":[54],"from":[55],"straightforward":[56],"adopt":[58],"models":[60,146],"due":[64],"unfaithful":[67],"control":[68],"on":[69,191],"highly":[70],"complex":[71],"images":[73],"(e.g.,":[74],"2000":[75],"\u00d7":[76],"3000":[77],"resolution).":[78],"In":[79,116,133],"this":[80,149],"paper,":[81],"we":[82,118,135,151],"propose":[83,120],"DvD,":[84],"the":[85,128],"first":[86],"generative":[87],"model":[88],"tackle":[90],"Dewarping":[92],"via":[93],"a":[94,102,111,121,154],"Diffusion":[95],"framework.":[96],"To":[97,148],"be":[98,208],"specific,":[99],"DvD":[100,182],"introduces":[101],"coordinate-level":[103],"denoising":[104],"instead":[105],"of":[106,130,173],"typical":[107],"pixel-level":[108],"denoising,":[109],"generating":[110],"mapping":[112],"deformation":[114],"rectification.":[115],"addition,":[117],"further":[119],"time-variant":[122],"condition":[123],"refinement":[124],"mechanism":[125],"enhance":[127],"preservation":[129],"experiments,":[134],"find":[136],"that":[137,179],"current":[138],"benchmarks":[141],"can":[142,183],"not":[143],"evaluate":[144],"comprehensively.":[147],"end,":[150],"present":[152],"AnyPhotoDoc6300,":[153],"rigorously":[155],"designed":[156],"large-scale":[157],"benchmark":[160,204],"comprising":[161],"6,300":[162],"real":[163],"image":[164],"pairs":[165],"across":[166,194],"three":[167],"distinct":[168],"domains,":[169],"enabling":[170],"fine-grained":[171],"evaluation":[172],"models.":[175],"Comprehensive":[176],"experiments":[177],"demonstrate":[178],"our":[180],"proposed":[181],"achieve":[184],"state-of-the-art":[185],"performance":[186],"with":[187],"acceptable":[188],"computational":[189],"efficiency":[190],"multiple":[192],"metrics":[193],"various":[195],"benchmarks,":[196],"including":[197],"DocUNet,":[198],"DIR300,":[199],"AnyPhotoDoc6300.":[201],"The":[202],"new":[203],"code":[206],"will":[207],"publicly":[209],"available":[210],"at":[211],"https://github.com/hanquansanren/DvD.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-08T00:00:00"}