{"id":"https://openalex.org/W4414360181","doi":"https://doi.org/10.24963/ijcai.2025/186","title":"Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution","display_name":"Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360181","doi":"https://doi.org/10.24963/ijcai.2025/186"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/186","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5033864788","display_name":"Chuanren Liu","orcid":"https://orcid.org/0000-0001-9030-8495"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zihang Liu","raw_affiliation_strings":["Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389499","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0000-0001-5727-9450"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhang","raw_affiliation_strings":["Nanjing University"],"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050748634","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2077-1246"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["School of Computer Science, Peking University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033864788"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":1.428,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86053925,"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":"1666","last_page":"1674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.977400004863739,"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":0.977400004863739,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9682999849319458,"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"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9621999859809875,"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/inference","display_name":"Inference","score":0.6362000107765198},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6330000162124634},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5559999942779541},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5554999709129333},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4487000107765198},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4343999922275543},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4171000123023987},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.38989999890327454},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38519999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034000158309937},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6362000107765198},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6330000162124634},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5559999942779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5555999875068665},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5554999709129333},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4487000107765198},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40869998931884766},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3702000081539154},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.28299999237060547},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.25220000743865967},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.25110000371932983},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/186","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"image":[1],"super-resolution":[2],"(SR)":[3],"methods":[4],"have":[5,11],"demonstrated":[6],"remarkable":[7],"performance.":[8],"Recent":[9],"advancements":[10],"introduced":[12],"deterministic":[13],"sampling":[14,70,96],"processes":[15],"that":[16,63,98,151],"reduce":[17],"inference":[18,31],"from":[19],"15":[20],"iterative":[21],"steps":[22],"to":[23,48,85],"a":[24,59,94,128],"single":[25],"step,":[26],"thereby":[27],"significantly":[28,153],"improving":[29],"the":[30,49,69,75,101,118],"speed":[32],"of":[33],"existing":[34],"diffusion":[35,61,119],"models.":[36],"However,":[37],"their":[38],"efficiency":[39],"remains":[40],"limited":[41],"when":[42],"handling":[43],"complex":[44,163],"semantic":[45,65,89,111,129,135],"regions":[46,116],"due":[47],"single-step":[50],"inference.":[51],"To":[52,121],"address":[53],"this":[54],"limitation,":[55],"we":[56,73,92,125],"propose":[57,127],"SAMSR,":[58],"semantic-guided":[60],"framework":[62],"incorporates":[64],"segmentation":[66,83],"masks":[67,84],"into":[68],"process.":[71,120],"Specifically,":[72],"introduce":[74],"SAM-Noise":[76],"Module,":[77],"which":[78,132],"refines":[79],"Gaussian":[80],"noise":[81,106],"using":[82],"preserve":[86],"spatial":[87],"and":[88,105,139,147,157],"features.":[90],"Furthermore,":[91],"develop":[93],"pixel-wise":[95,134],"strategy":[97],"dynamically":[99],"adjusts":[100],"residual":[102],"transfer":[103],"rate":[104],"strength":[107],"based":[108],"on":[109,144],"pixel-level":[110],"weights,":[112],"prioritizing":[113],"semantically":[114,162],"rich":[115],"during":[117],"enhance":[122],"model":[123],"training,":[124],"also":[126],"consistency":[130],"loss,":[131],"aligns":[133],"weights":[136],"between":[137],"predictions":[138],"ground":[140],"truth.":[141],"Extensive":[142],"experiments":[143],"both":[145],"real-world":[146],"synthetic":[148],"datasets":[149],"demonstrate":[150],"SAMSR":[152],"improves":[154],"perceptual":[155],"quality":[156],"detail":[158],"recovery,":[159],"particularly":[160],"in":[161],"images.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}