{"id":"https://openalex.org/W4416506201","doi":"https://doi.org/10.1109/iccv51701.2025.02404","title":"Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography","display_name":"Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416506201","doi":"https://doi.org/10.1109/iccv51701.2025.02404"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02404","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/2506.22753","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092256856","display_name":"Jianing Zhang","orcid":"https://orcid.org/0009-0006-0658-1194"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianing Zhang","raw_affiliation_strings":["Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776956","display_name":"Jiayi Zhu","orcid":"https://orcid.org/0009-0003-0463-9442"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Zhu","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035071058","display_name":"Fei-Yu Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyu Ji","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028126515","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0009-0002-8141-3722"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109358502","display_name":"Xiaoyun Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyun Yuan","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"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":"25914","last_page":"25924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.31929999589920044,"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/T11019","display_name":"Image Enhancement Techniques","score":0.31929999589920044,"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/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.22660000622272491,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10638","display_name":"Optical measurement and interference techniques","score":0.09830000251531601,"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/hallucinating","display_name":"Hallucinating","score":0.5396000146865845},{"id":"https://openalex.org/keywords/computational-photography","display_name":"Computational photography","score":0.46889999508857727},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.46630001068115234},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4580000042915344},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4487999975681305},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.44670000672340393},{"id":"https://openalex.org/keywords/photography","display_name":"Photography","score":0.44110000133514404},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4194999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664000153541565},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5235000252723694},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.46889999508857727},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.44110000133514404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43560001254081726},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C161218011","wikidata":"https://www.wikidata.org/wiki/Q11827794","display_name":"Multipath propagation","level":3,"score":0.4025000035762787},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3547999858856201},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.3019999861717224},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.3001999855041504},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C125045340","wikidata":"https://www.wikidata.org/wiki/Q6002224","display_name":"Image formation","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.272599995136261}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02404","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:2506.22753","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.22753","pdf_url":"https://arxiv.org/pdf/2506.22753","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.2506.22753","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.22753","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:2506.22753","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.22753","pdf_url":"https://arxiv.org/pdf/2506.22753","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/G1990530581","display_name":null,"funder_award_id":"62271283","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5465080215","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Metalenses":[0],"offer":[1],"significant":[2],"potential":[3],"for":[4,34,58,132],"ultra-compact":[5],"computational":[6,16],"imaging":[7,36],"but":[8],"face":[9],"challenges":[10],"from":[11,67],"complex":[12,119],"optical":[13,25,120],"degradation":[14],"and":[15,79,89,106,121,127,146],"restoration":[17],"difficulties.":[18],"Existing":[19],"methods":[20],"typically":[21],"rely":[22],"on":[23],"precise":[24],"calibration":[26],"or":[27],"massive":[28],"paired":[29],"datasets,":[30],"which":[31],"are":[32],"non-trivial":[33],"real-world":[35,133],"systems.":[37],"Furthermore,":[38],"a":[39,110,129],"lack":[40],"of":[41,71,91],"control":[42],"over":[43],"the":[44],"inference":[45],"process":[46],"often":[47],"results":[48,136],"in":[49],"undesirable":[50],"hallucinated":[51],"artifacts.":[52],"We":[53],"introduce":[54],"Degradation-Modeled":[55],"Multipath":[56],"Diffusion":[57],"tunable":[59,99],"metalens":[60],"photography,":[61],"leveraging":[62],"powerful":[63],"natural":[64],"image":[65,148],"priors":[66],"pretrained":[68],"models":[69,118],"instead":[70],"large":[72],"datasets.":[73],"Our":[74],"framework":[75],"uses":[76],"positive,":[77],"neutral,":[78],"negative-prompt":[80],"paths":[81],"to":[82],"balance":[83],"high-frequency":[84],"detail":[85],"generation,":[86],"structural":[87],"fidelity,":[88],"suppression":[90],"metalens-specific":[92],"degradation,":[93],"alongside":[94],"\\textit{pseudo}":[95],"data":[96],"augmentation.":[97],"A":[98],"decoder":[100],"enables":[101],"controlled":[102],"trade-offs":[103],"between":[104],"fidelity":[105],"perceptual":[107],"quality.":[108],"Additionally,":[109],"spatially":[111],"varying":[112],"degradation-aware":[113],"attention":[114],"(SVDA)":[115],"module":[116],"adaptively":[117],"sensor-induced":[122],"degradation.":[123],"Finally,":[124],"we":[125],"design":[126],"build":[128],"millimeter-scale":[130],"MetaCamera":[131],"validation.":[134],"Extensive":[135],"show":[137],"that":[138],"our":[139],"approach":[140],"outperforms":[141],"state-of-the-art":[142],"methods,":[143],"achieving":[144],"high-fidelity":[145],"sharp":[147],"reconstruction.":[149],"More":[150],"materials:":[151],"https://dmdiff.github.io/.":[152]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}