{"id":"https://openalex.org/W4405089057","doi":"https://doi.org/10.48550/arxiv.2412.03017","title":"Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach","display_name":"Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach","publication_year":2024,"publication_date":"2024-12-04","ids":{"openalex":"https://openalex.org/W4405089057","doi":"https://doi.org/10.48550/arxiv.2412.03017"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2412.03017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03017","pdf_url":"https://arxiv.org/pdf/2412.03017","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.03017","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023365341","display_name":"Lingchen Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sun, Lingchen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061924580","display_name":"Rongyuan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Rongyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356303","display_name":"Zhiyuan Ma","orcid":"https://orcid.org/0000-0002-3346-0084"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Zhiyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007325130","display_name":"Shuaizheng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shuaizheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046357019","display_name":"Qiaosi Yi","orcid":"https://orcid.org/0000-0001-9720-4322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi, Qiaosi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5106578837","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-5305-8543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023365341"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9955999851226807,"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":0.9951000213623047,"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/pixel","display_name":"Pixel","score":0.6726919412612915},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.589059054851532},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.535693883895874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49936699867248535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40325745940208435},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38321250677108765},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1418827474117279},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07647135853767395}],"concepts":[{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6726919412612915},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.589059054851532},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.535693883895874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49936699867248535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40325745940208435},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38321250677108765},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1418827474117279},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07647135853767395}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2412.03017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03017","pdf_url":"https://arxiv.org/pdf/2412.03017","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.03017","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.03017","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.03017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03017","pdf_url":"https://arxiv.org/pdf/2412.03017","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Diffusion":[0],"prior-based":[1],"methods":[2,15],"have":[3,36],"shown":[4],"impressive":[5],"results":[6,172,206],"in":[7,22,163,173],"real-world":[8,170],"image":[9],"super-resolution":[10],"(SR).":[11],"However,":[12],"most":[13],"existing":[14],"entangle":[16],"pixel-level":[17,131],"and":[18,31,67,86,105,133,140,152,176,196,214],"semantic-level":[19,197],"SR":[20,40,50,70,88,95,171,205],"objectives":[21],"the":[23,78,93,99,102,106,112,128,138,185,191],"training":[24],"process,":[25],"struggling":[26],"to":[27,46,56,83,145,189,208],"balance":[28],"pixel-wise":[29,194],"fidelity":[30,195],"perceptual":[32],"quality.":[33],"Meanwhile,":[34],"users":[35],"varying":[37],"preferences":[38,59],"on":[39,184],"results,":[41],"thus":[42],"it":[43],"is":[44,125,135],"demanded":[45],"develop":[47],"an":[48],"adjustable":[49,87,181],"model":[51,82],"that":[52,111],"can":[53,115,160,202,216],"be":[54,116,161,217],"tailored":[55],"different":[57],"fidelity-perception":[58],"during":[60,199],"inference":[61],"without":[62,211],"re-training.":[63,212],"We":[64,90],"present":[65],"Pixel-level":[66],"Semantic-level":[68],"Adjustable":[69],"(PiSA-SR),":[71],"which":[72],"learns":[73],"two":[74,119,180,186],"LoRA":[75,121,187],"modules":[76,188],"upon":[77],"pre-trained":[79,150],"stable-diffusion":[80],"(SD)":[81],"achieve":[84],"improved":[85],"results.":[89],"first":[91],"formulate":[92],"SD-based":[94],"problem":[96],"as":[97],"learning":[98,113],"residual":[100],"between":[101],"low-quality":[103],"input":[104],"high-quality":[107],"output,":[108],"then":[109],"show":[110],"objective":[114],"decoupled":[117],"into":[118],"distinct":[120],"weight":[122],"spaces:":[123],"one":[124],"characterized":[126,136],"by":[127,137],"$\\ell_2$-loss":[129],"for":[130],"regression,":[132],"another":[134],"LPIPS":[139],"classifier":[141],"score":[142],"distillation":[143],"losses":[144],"extract":[146],"semantic":[147],"information":[148],"from":[149],"classification":[151],"SD":[153],"models.":[154],"In":[155],"its":[156],"default":[157],"setting,":[158],"PiSA-SR":[159],"performed":[162],"a":[164],"single":[165],"diffusion":[166],"step,":[167],"achieving":[168],"leading":[169],"both":[174],"quality":[175],"efficiency.":[177],"By":[178],"introducing":[179],"guidance":[182],"scales":[183],"control":[190],"strengths":[192],"of":[193],"details":[198],"inference,":[200],"PiSASR":[201],"offer":[203],"flexible":[204],"according":[207],"user":[209],"preference":[210],"Codes":[213],"models":[215],"found":[218],"at":[219],"https://github.com/csslc/PiSA-SR.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}