{"id":"https://openalex.org/W4415945537","doi":"https://doi.org/10.1109/iccv51701.2025.01832","title":"Diffusion Transformer Meets Multi-Level Wavelet Spectrum for Single Image Super-Resolution","display_name":"Diffusion Transformer Meets Multi-Level Wavelet Spectrum for Single Image Super-Resolution","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415945537","doi":"https://doi.org/10.1109/iccv51701.2025.01832"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.01832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.01175","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100690406","display_name":"Peijun Du","orcid":"https://orcid.org/0000-0002-2488-2656"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Peng Du","raw_affiliation_strings":["Samsung R&D Institute China Xi'an (SRCX),China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China Xi'an (SRCX),China","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424007","display_name":"Hui Li","orcid":"https://orcid.org/0009-0008-8256-2109"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["Samsung R&D Institute China Xi'an (SRCX),China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China Xi'an (SRCX),China","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048535532","display_name":"Han Xu","orcid":"https://orcid.org/0000-0003-2026-0654"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Han Xu","raw_affiliation_strings":["Samsung R&D Institute China Xi'an (SRCX),China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China Xi'an (SRCX),China","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110245655","display_name":"Paul Barom Jeon","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Paul Barom Jeon","raw_affiliation_strings":["Samsung Electronics Co., LTD.,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., LTD.,South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363866","display_name":"Dongwook Lee","orcid":"https://orcid.org/0000-0002-8229-3040"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongwook Lee","raw_affiliation_strings":["Samsung Electronics Co., LTD.,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., LTD.,South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110223580","display_name":"Daehyun Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daehyun Ji","raw_affiliation_strings":["Samsung Electronics Co., LTD.,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., LTD.,South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100589586","display_name":"Ran Yang","orcid":"https://orcid.org/0009-0003-6098-9658"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ran Yang","raw_affiliation_strings":["Samsung R&D Institute China Xi'an (SRCX),China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China Xi'an (SRCX),China","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101854974","display_name":"Feng Zhu","orcid":"https://orcid.org/0000-0003-1597-277X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Feng Zhu","raw_affiliation_strings":["Samsung R&D Institute China Xi'an (SRCX),China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China Xi'an (SRCX),China","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29322563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19700","last_page":"19710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.7682999968528748,"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":0.7682999968528748,"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":0.11860000342130661,"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/T11897","display_name":"Digital Holography and Microscopy","score":0.03519999980926514,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.7421000003814697},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.5753999948501587},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.5303999781608582},{"id":"https://openalex.org/keywords/wavelet-packet-decomposition","display_name":"Wavelet packet decomposition","score":0.5164999961853027},{"id":"https://openalex.org/keywords/stationary-wavelet-transform","display_name":"Stationary wavelet transform","score":0.478300005197525},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46959999203681946},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4652000069618225},{"id":"https://openalex.org/keywords/second-generation-wavelet-transform","display_name":"Second-generation wavelet transform","score":0.4498000144958496}],"concepts":[{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.7421000003814697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5939000248908997},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.5753999948501587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5618000030517578},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.5303999781608582},{"id":"https://openalex.org/C155777637","wikidata":"https://www.wikidata.org/wiki/Q2736187","display_name":"Wavelet packet decomposition","level":4,"score":0.5164999961853027},{"id":"https://openalex.org/C73339587","wikidata":"https://www.wikidata.org/wiki/Q1375942","display_name":"Stationary wavelet transform","level":5,"score":0.478300005197525},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46959999203681946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C111350171","wikidata":"https://www.wikidata.org/wiki/Q7443700","display_name":"Second-generation wavelet transform","level":5,"score":0.4498000144958496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4438000023365021},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.42399999499320984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C199550912","wikidata":"https://www.wikidata.org/wiki/Q3238415","display_name":"Lifting scheme","level":5,"score":0.33640000224113464},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.3167000114917755},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C173642442","wikidata":"https://www.wikidata.org/wiki/Q1253346","display_name":"Decimation","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26499998569488525},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C100921725","wikidata":"https://www.wikidata.org/wiki/Q1650811","display_name":"Spatial frequency","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.01175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.01175","pdf_url":"https://arxiv.org/pdf/2511.01175","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.01175","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.01175","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.01175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.01175","pdf_url":"https://arxiv.org/pdf/2511.01175","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Discrete":[0,96],"Wavelet":[1,60,97],"Transform":[2,98],"(DWT)":[3],"has":[4],"been":[5],"widely":[6],"explored":[7],"to":[8,74,83,99,124,138],"enhance":[9],"the":[10,31,44,67,76,113,140,162],"performance":[11,169],"of":[12,69,118,164],"image":[13,59,153],"superresolution":[14],"(SR).":[15],"Despite":[16],"some":[17],"DWT-based":[18],"methods":[19],"improving":[20],"SR":[21,63,89],"by":[22],"capturing":[23],"fine-grained":[24],"frequency":[25,35,80,131],"signals,":[26],"most":[27],"existing":[28],"approaches":[29],"neglect":[30],"interrelations":[32,77],"among":[33,78],"multiscale":[34,79],"sub-bands,":[36,81,147],"resulting":[37],"in":[38,43,143,152],"inconsistencies":[39],"and":[40,72,87,130,145,174],"unnatural":[41],"artifacts":[42],"reconstructed":[45],"images.":[46],"To":[47],"address":[48],"this":[49],"challenge,":[50],"we":[51,92],"propose":[52],"a":[53,84,94,116],"Diffusion":[54],"Transformer":[55],"model":[56],"based":[57],"on":[58,157,170],"spectra":[61,114],"for":[62,120],"(DTWSR).":[64],"DTWSR":[65],"incorporates":[66],"superiority":[68],"diffusion":[70],"models":[71],"transformers":[73],"capture":[75,125],"leading":[82],"more":[85],"consistence":[86],"realistic":[88],"image.":[90],"Specifically,":[91],"use":[93],"Multi-level":[95],"decompose":[100],"images":[101],"into":[102,115],"wavelet":[103],"spectra.":[104],"A":[105,133],"pyramid":[106],"tokenization":[107],"method":[108],"is":[109,135],"proposed":[110],"which":[111],"embeds":[112],"sequence":[117],"tokens":[119],"transformer":[121],"model,":[122],"facilitating":[123],"features":[126],"from":[127],"both":[128,171],"spatial":[129],"domain.":[132],"dual-decoder":[134],"designed":[136],"elaborately":[137],"handle":[139],"distinct":[141],"variances":[142],"low-frequency":[144],"high-frequency":[146],"without":[148],"omitting":[149],"their":[150],"alignment":[151],"generation.":[154],"Extensive":[155],"experiments":[156],"multiple":[158],"benchmark":[159],"datasets":[160],"demonstrate":[161],"effectiveness":[163],"our":[165],"method,":[166],"with":[167],"high":[168],"perception":[172],"quality":[173],"fidelity.":[175]},"counts_by_year":[],"updated_date":"2025-11-06T23:20:22.142202","created_date":"2025-11-06T00:00:00"}