{"id":"https://openalex.org/W4406596051","doi":"https://doi.org/10.1145/3703619.3706048","title":"Multiscale Structure Prompted Diffusion Models for Scene Text Image Super-Resolution","display_name":"Multiscale Structure Prompted Diffusion Models for Scene Text Image Super-Resolution","publication_year":2024,"publication_date":"2024-12-01","ids":{"openalex":"https://openalex.org/W4406596051","doi":"https://doi.org/10.1145/3703619.3706048"},"language":"en","primary_location":{"id":"doi:10.1145/3703619.3706048","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3703619.3706048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","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/A5100552064","display_name":"Huilong Xie","orcid":"https://orcid.org/0009-0000-7899-1615"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huilong Xie","raw_affiliation_strings":["Dalian University, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0000-7899-1615","affiliations":[{"raw_affiliation_string":"Dalian University, Dalian, China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025524501","display_name":"Wanshu Fan","orcid":"https://orcid.org/0000-0001-6299-2795"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanshu Fan Fan","raw_affiliation_strings":["School of Software Engineering, Dalian University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-6299-2795","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Dalian University, Dalian, China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055447805","display_name":"Dongsheng Zhou","orcid":"https://orcid.org/0000-0003-3414-9623"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Zhou","raw_affiliation_strings":["Dalian University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3414-9623","affiliations":[{"raw_affiliation_string":"Dalian University, Dalian, China","institution_ids":["https://openalex.org/I4210092944"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210092944"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31909476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9997000098228455,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9997000098228455,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9962999820709229,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6244227886199951},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.537508487701416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5224903225898743},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5190140008926392},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.515900731086731},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4946136176586151},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.437768816947937},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3373745083808899},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10996618866920471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6244227886199951},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.537508487701416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5224903225898743},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5190140008926392},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.515900731086731},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4946136176586151},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.437768816947937},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3373745083808899},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10996618866920471},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3703619.3706048","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3703619.3706048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1885185971","https://openalex.org/W2114770744","https://openalex.org/W2133665775","https://openalex.org/W2194187530","https://openalex.org/W2607041014","https://openalex.org/W2810983211","https://openalex.org/W2866634454","https://openalex.org/W2954930822","https://openalex.org/W2963470893","https://openalex.org/W2963526661","https://openalex.org/W2964101377","https://openalex.org/W3107840264","https://openalex.org/W3174746398","https://openalex.org/W3177505580","https://openalex.org/W3206615376","https://openalex.org/W4226014430","https://openalex.org/W4285606401","https://openalex.org/W4312923907","https://openalex.org/W4312933868","https://openalex.org/W4382240051","https://openalex.org/W4382449827","https://openalex.org/W4385764576","https://openalex.org/W4390872583","https://openalex.org/W4390874521","https://openalex.org/W6600339963","https://openalex.org/W6797497125"],"related_works":["https://openalex.org/W2362774332","https://openalex.org/W4249245269","https://openalex.org/W2765548132","https://openalex.org/W2025681766","https://openalex.org/W2542402767","https://openalex.org/W3023086044","https://openalex.org/W2294441925","https://openalex.org/W2142226356","https://openalex.org/W2056165575","https://openalex.org/W3210000161"],"abstract_inverted_index":{"Scene":[0],"Text":[1],"Image":[2],"Super-Resolution":[3],"(STISR),":[4],"which":[5,189],"aims":[6],"to":[7,147],"enhance":[8,148],"the":[9,53,102,109,128,133,137,141,145,159,168,183,190,195,200],"resolution":[10],"and":[11,108,140,215],"legibility":[12],"of":[13,47,55],"text":[14,22,121,149,164,212,226],"in":[15,24,28,69,210,228],"low-resolution":[16,138],"images,":[17],"is":[18,35,161,170,185,192],"crucial":[19],"for":[20,37,95,224],"accurate":[21],"recognition":[23,213],"real-world":[25],"scenarios,":[26],"especially":[27],"virtual":[29,229],"reality":[30,230],"(VR)":[31],"environments":[32],"where":[33],"clarity":[34,227],"essential":[36],"immersive":[38],"experiences.":[39],"However,":[40],"existing":[41],"STISR":[42],"methods":[43,209],"often":[44],"fall":[45],"short":[46],"capturing":[48],"detailed":[49],"structural":[50,70,118,124],"information,":[51],"limiting":[52],"quality":[54],"reconstructed":[56],"images.":[57],"While":[58],"diffusion":[59],"models":[60],"offer":[61],"robust":[62],"generative":[63],"abilities,":[64],"they":[65],"can":[66],"still":[67],"result":[68],"inconsistencies,":[71],"particularly":[72],"when":[73],"handling":[74],"highly":[75],"blurred":[76],"or":[77],"distorted":[78],"text.":[79],"To":[80,174],"address":[81,175],"these":[82],"challenges,":[83,157],"we":[84,177],"introduce":[85],"MSPDiff,":[86],"a":[87,179,221],"Multiscale":[88,103],"Structure":[89,104],"Prompted":[90,110],"Diffusion":[91,111],"Model":[92,106,112],"designed":[93],"specifically":[94],"STISR.":[96],"MSPDiff":[97,206],"integrates":[98],"two":[99],"main":[100],"components:":[101],"Generation":[105],"(MSGM)":[107],"(PDM).":[113],"The":[114],"MSGM":[115,146,160,184,196],"captures":[116],"multiscale":[117,142],"features":[119],"from":[120,144],"data,":[122],"generating":[123],"priors":[125],"that":[126,205],"guide":[127],"PDM.":[129],"In":[130],"this":[131],"setup,":[132],"PDM":[134,169,191],"leverages":[135],"both":[136,152,211],"images":[139],"structures":[143],"clarity.":[150],"Training":[151],"components":[153],"simultaneously":[154],"presents":[155],"optimization":[156],"as":[158,220],"constrained":[162],"by":[163],"data":[165],"limitations":[166],"while":[167],"optimized":[171],"using":[172],"noise.":[173],"this,":[176],"implement":[178],"two-stage":[180],"training":[181],"approach:":[182],"trained":[186,193],"initially,":[187],"after":[188],"with":[194],"frozen.":[197],"Experiments":[198],"on":[199],"widely-used":[201],"TextZoom":[202],"benchmark":[203],"demonstrate":[204],"outperforms":[207],"state-of-the-art":[208],"accuracy":[214],"image":[216],"quality,":[217],"establishing":[218],"it":[219],"promising":[222],"approach":[223],"enhancing":[225],"applications.":[231]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}