{"id":"https://openalex.org/W4417281808","doi":"https://doi.org/10.1109/iccv51701.2025.01732","title":"Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models","display_name":"Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417281808","doi":"https://doi.org/10.1109/iccv51701.2025.01732"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01732","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.11073","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109149472","display_name":"H.Y. Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyang Wei","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007325130","display_name":"Shuaizheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shuaizheng Liu","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101456902","display_name":"Chun Yuan","orcid":"https://orcid.org/0000-0002-3590-6676"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yuan","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433931","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-5808-5313"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18640","last_page":"18650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6837999820709229,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6837999820709229,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.12800000607967377,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.03929999843239784,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7519000172615051},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6638000011444092},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5454000234603882},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5331000089645386},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4821000099182129},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4810999929904938},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.4187999963760376},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4142000079154968}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7519000172615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7120000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6736000180244446},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6638000011444092},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5331000089645386},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.4187999963760376},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4142000079154968},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41130000352859497},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3898000121116638},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.33640000224113464},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.32690000534057617},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.32679998874664307},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.2743000090122223},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01732","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:2503.11073","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11073","pdf_url":"https://arxiv.org/pdf/2503.11073","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.2503.11073","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.11073","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.11073","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11073","pdf_url":"https://arxiv.org/pdf/2503.11073","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":[{"id":"https://openalex.org/G4213465990","display_name":null,"funder_award_id":"2022YFB4701400/4701402","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"By":[0],"leveraging":[1],"the":[2,46,57,65,84,102,107,115,119,130,139,147,152,164,168,192],"generative":[3,197],"priors":[4],"from":[5],"pre-trained":[6,66],"text-to-image":[7],"diffusion":[8],"models,":[9],"significant":[10],"progress":[11],"has":[12],"been":[13],"made":[14],"in":[15,30,185],"real-world":[16],"image":[17,103,112,120,124,131,135,148,153,169,178],"super-resolution":[18],"(Real-ISR).":[19],"However,":[20],"these":[21,52],"methods":[22],"tend":[23],"to":[24,38,60,63,100,162],"generate":[25],"inaccurate":[26],"and":[27,42,82,106,114,127,155,204],"unnatural":[28],"reconstructions":[29],"complex":[31,186],"and/or":[32],"heavily":[33],"degraded":[34],"scenes,":[35],"primarily":[36],"due":[37],"their":[39],"limited":[40],"perception":[41],"understanding":[43],"capability":[44],"of":[45,167,194],"input":[47,85],"low-quality":[48,86],"image.":[49],"To":[50],"address":[51],"limitations,":[53],"we":[54,94,144],"propose,":[55],"for":[56,199],"first":[58],"time":[59],"our":[61],"knowledge,":[62],"adapt":[64],"autoregressive":[67,195],"multimodal":[68,196],"model":[69,203],"such":[70],"as":[71],"Lumina-mGPT":[72,99],"into":[73],"a":[74,157],"robust":[75,200],"Real-ISR":[76],"model,":[77],"namely":[78],"PURE,":[79],"which":[80],"Perceives":[81],"Understands":[83],"image,":[87],"then":[88],"REstores":[89],"its":[90],"high-quality":[91,134],"counterpart.":[92],"Specifically,":[93],"implement":[95],"instruction":[96],"tuning":[97],"on":[98],"perceive":[101],"degradation":[104],"level":[105],"relationships":[108],"between":[109],"previously":[110],"generated":[111],"tokens":[113,136],"next":[116],"token,":[117],"understand":[118],"content":[121,179],"by":[122,132],"generating":[123,133,181],"semantic":[125],"descriptions,":[126],"consequently":[128],"restore":[129],"autoregressively":[137],"with":[138,188],"collected":[140],"information.":[141],"In":[142],"addition,":[143],"reveal":[145],"that":[146,175],"token":[149],"entropy":[150],"reflects":[151],"structure":[154,166],"present":[156],"entropy-based":[158],"Top-k":[159],"sampling":[160],"strategy":[161],"optimize":[163],"local":[165],"during":[170],"inference.":[171],"Experimental":[172],"results":[173],"demonstrate":[174],"PURE":[176],"preserves":[177],"while":[180],"realistic":[182],"details,":[183],"especially":[184],"scenes":[187],"multiple":[189],"objects,":[190],"showcasing":[191],"potential":[193],"models":[198],"Real-ISR.":[201],"The":[202],"code":[205],"will":[206],"be":[207],"available":[208],"at":[209],"https://github.com/nonwhy/PURE.":[210]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}