{"id":"https://openalex.org/W4416123327","doi":"https://doi.org/10.1109/iccv51701.2025.01692","title":"Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion Models","display_name":"Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416123327","doi":"https://doi.org/10.1109/iccv51701.2025.01692"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01692","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/2503.21943","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027169198","display_name":"Haoming Cai","orcid":"https://orcid.org/0000-0001-8155-9313"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoming Cai","raw_affiliation_strings":["University of Maryland,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038595095","display_name":"Tsung\u2013Wei Huang","orcid":"https://orcid.org/0000-0002-1478-2678"},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsung-Wei Huang","raw_affiliation_strings":["Dolby Labs,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Labs,USA","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025841262","display_name":"Shiv Gehlot","orcid":"https://orcid.org/0000-0002-2891-8185"},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiv Gehlot","raw_affiliation_strings":["Dolby Labs,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Labs,USA","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016163266","display_name":"Brandon Y. Feng","orcid":"https://orcid.org/0000-0001-7003-9128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brandon Y. Feng","raw_affiliation_strings":["MIT,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103083567","display_name":"Sachin Shah","orcid":"https://orcid.org/0009-0009-4494-3629"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin Shah","raw_affiliation_strings":["University of Maryland,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012578054","display_name":"Guan\u2010Ming Su","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guan-Ming Su","raw_affiliation_strings":["Dolby Labs,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Labs,USA","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088204867","display_name":"Christopher A. Metzler","orcid":"https://orcid.org/0000-0001-6827-7207"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Metzler","raw_affiliation_strings":["University of Maryland,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35780591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18207","last_page":"18217"},"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":0.8518999814987183,"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":0.8518999814987183,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.08160000294446945,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.010200000368058681,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/shadow","display_name":"Shadow (psychology)","score":0.9057000279426575},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6021000146865845},{"id":"https://openalex.org/keywords/portrait","display_name":"Portrait","score":0.5954999923706055},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5060999989509583},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.504800021648407},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.45089998841285706},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.42590001225471497}],"concepts":[{"id":"https://openalex.org/C117797892","wikidata":"https://www.wikidata.org/wiki/Q286363","display_name":"Shadow (psychology)","level":2,"score":0.9057000279426575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6597999930381775},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6021000146865845},{"id":"https://openalex.org/C162462552","wikidata":"https://www.wikidata.org/wiki/Q134307","display_name":"Portrait","level":2,"score":0.5954999923706055},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.492900013923645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49129998683929443},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.42590001225471497},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35510000586509705},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C93038891","wikidata":"https://www.wikidata.org/wiki/Q1061524","display_name":"Intensity (physics)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01692","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:2503.21943","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21943","pdf_url":"https://arxiv.org/pdf/2503.21943","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2503.21943","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.21943","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2503.21943","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21943","pdf_url":"https://arxiv.org/pdf/2503.21943","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":{"Text-to-image":[0],"diffusion":[1,63],"models":[2],"excel":[3],"at":[4],"generating":[5],"diverse":[6,24,112,131],"portraits,":[7],"but":[8],"lack":[9],"intuitive":[10,94],"shadow":[11,59,97],"control.":[12],"Existing":[13],"editing":[14],"approaches,":[15],"as":[16],"post-processing,":[17],"struggle":[18],"to":[19,127],"offer":[20],"effective":[21],"manipulation":[22],"across":[23,111],"styles.":[25,113],"Additionally,":[26],"these":[27,46],"methods":[28],"either":[29],"rely":[30],"on":[31,117,121],"expensive":[32],"real-world":[33,85,122],"light-stage":[34,86],"data":[35,87,119],"collection":[36],"or":[37],"require":[38],"extensive":[39],"computational":[40],"resources":[41],"for":[42],"training.":[43],"To":[44],"address":[45],"limitations,":[47],"we":[48],"introduce":[49],"Shadow":[50,89],"Director,":[51],"a":[52,68,75,135],"method":[53],"that":[54,72],"extracts":[55],"and":[56,80,93,100,109,138],"manipulates":[57],"hidden":[58],"attributes":[60],"within":[61],"well-trained":[62],"models.":[64],"Our":[65],"approach":[66],"uses":[67],"small":[69],"estimation":[70],"network":[71],"requires":[73],"only":[74,116],"few":[76],"thousand":[77],"synthetic":[78,118],"images":[79],"hours":[81],"of":[82],"training-no":[83],"costly":[84],"needed.":[88],"Director":[90],"enables":[91],"parametric":[92],"control":[95],"over":[96],"shape,":[98],"placement,":[99],"intensity":[101],"during":[102],"portrait":[103],"generation":[104],"while":[105],"preserving":[106],"artistic":[107],"integrity":[108],"identity":[110],"Despite":[114],"training":[115],"built":[120],"identities,":[123],"it":[124,134],"generalizes":[125],"effectively":[126],"generated":[128],"portraits":[129],"with":[130],"styles,":[132],"making":[133],"more":[136],"accessible":[137],"resource-friendly":[139],"solution.":[140]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}