{"id":"https://openalex.org/W4413887386","doi":"https://doi.org/10.1109/tpami.2025.3604574","title":"An End-to-End Depth-Based Pipeline for Selfie Image Rectification","display_name":"An End-to-End Depth-Based Pipeline for Selfie Image Rectification","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4413887386","doi":"https://doi.org/10.1109/tpami.2025.3604574","pmid":"https://pubmed.ncbi.nlm.nih.gov/40889307"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3604574","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3604574","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tpami.2025.3604574","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011417458","display_name":"Ahmed Alhawwary","orcid":null},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ahmed Alhawwary","raw_affiliation_strings":["Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0009-0009-8723-9885","affiliations":[{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036883469","display_name":"Janne Mustaniemi","orcid":null},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Janne Mustaniemi","raw_affiliation_strings":["Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0009-0007-3705-1927","affiliations":[{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060853953","display_name":"Phong Nguyen-Ha","orcid":"https://orcid.org/0000-0002-9678-0886"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Phong Nguyen-Ha","raw_affiliation_strings":["Qualcomm AI Research, Ha Noi, North, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-9678-0886","affiliations":[{"raw_affiliation_string":"Qualcomm AI Research, Ha Noi, North, Vietnam","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072890921","display_name":"Janne Heikkil\u00e4","orcid":"https://orcid.org/0000-0003-0073-0866"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Janne Heikkil\u00e4","raw_affiliation_strings":["Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0003-0073-0866","affiliations":[{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.762,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77243437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"48","issue":"1","first_page":"79","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.8385000228881836,"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"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.8385000228881836,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.8180999755859375,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.7773000001907349,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/computer-vision","display_name":"Computer vision","score":0.7290757894515991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7225845456123352},{"id":"https://openalex.org/keywords/selfie","display_name":"Selfie","score":0.6574288606643677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6446226239204407},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5883612036705017},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5868368744850159},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.5691537857055664},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4634992778301239},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15239813923835754}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7290757894515991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7225845456123352},{"id":"https://openalex.org/C2777454149","wikidata":"https://www.wikidata.org/wiki/Q12068677","display_name":"Selfie","level":2,"score":0.6574288606643677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6446226239204407},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5883612036705017},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5868368744850159},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.5691537857055664},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4634992778301239},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15239813923835754},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3604574","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3604574","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40889307","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40889307","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tpami.2025.3604574","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3604574","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2018727909","https://openalex.org/W2133665775","https://openalex.org/W2159528054","https://openalex.org/W2194775991","https://openalex.org/W2468014222","https://openalex.org/W2471866883","https://openalex.org/W2950689937","https://openalex.org/W2957317972","https://openalex.org/W2962785568","https://openalex.org/W2963800363","https://openalex.org/W2988112387","https://openalex.org/W3010001210","https://openalex.org/W3034528136","https://openalex.org/W3035524985","https://openalex.org/W3173102319","https://openalex.org/W3174458495","https://openalex.org/W3180770160","https://openalex.org/W4206560112","https://openalex.org/W4312383858","https://openalex.org/W4312453532","https://openalex.org/W4321504740","https://openalex.org/W4376851255","https://openalex.org/W4390872519","https://openalex.org/W4399739474","https://openalex.org/W4402727487","https://openalex.org/W4402915470","https://openalex.org/W4404002642"],"related_works":["https://openalex.org/W2795495259","https://openalex.org/W3028531746","https://openalex.org/W2759481820","https://openalex.org/W4251333111","https://openalex.org/W3122792572","https://openalex.org/W2888671135","https://openalex.org/W4362657427","https://openalex.org/W4307239547","https://openalex.org/W3003689229","https://openalex.org/W3087996744"],"abstract_inverted_index":{"Portraits":[0],"or":[1],"selfie":[2],"images":[3],"taken":[4],"from":[5,11,167],"a":[6,41,92,203,235],"close":[7],"distance":[8,53],"typically":[9],"suffer":[10],"perspective":[12,30],"distortion.":[13,31],"In":[14],"this":[15],"paper,":[16],"we":[17,120,150,193],"propose":[18],"an":[19,81,122],"end-to-end":[20,97],"deep":[21,42],"learning-based":[22],"rectification":[23,225],"pipeline":[24,226],"to":[25,34,49,70,80,84,95,107,125,180,185,201],"mitigate":[26],"the":[27,36,51,56,60,66,71,87,109,114,117,127,131,135,152,160,168,171,174,182,186,195],"effects":[28],"of":[29,99,116,130,140,170],"We":[32,90],"learn":[33],"predict":[35,126],"facial":[37],"depth":[38,46,101],"by":[39,54],"training":[40,98],"CNN.":[43],"The":[44,74],"estimated":[45],"is":[47],"utilized":[48],"adjust":[50],"camera-to-subject":[52],"moving":[55],"camera":[57,61,132],"farther,":[58],"increasing":[59],"focal":[62],"length,":[63],"and":[64,103,163,216,219,230],"reprojecting":[65],"3D":[67,237],"image":[68,155],"features":[69,76],"new":[72],"perspective.":[73],"reprojected":[75],"are":[77],"then":[78],"fed":[79],"inpainting":[82,118],"module":[83,124],"fill":[85],"in":[86],"missing":[88],"pixels.":[89],"leverage":[91],"differentiable":[93],"renderer":[94],"enable":[96],"our":[100,191,224],"estimation":[102],"feature":[104],"extraction":[105],"nets":[106],"improve":[108],"rectified":[110],"outputs.":[111],"To":[112,189],"boost":[113],"results":[115,221,233],"module,":[119],"incorporate":[121],"auxiliary":[123],"horizontal":[128],"movement":[129],"which":[133],"decreases":[134],"area":[136],"that":[137,223],"requires":[138],"hallucination":[139],"challenging":[141],"face":[142,162,183,206],"parts":[143],"such":[144],"as":[145],"ears.":[146],"Unlike":[147],"previous":[148,228],"works,":[149],"process":[151],"full-frame":[153],"input":[154],"at":[156],"once":[157],"without":[158],"cropping":[159],"subject's":[161,187],"processing":[164],"it":[165],"separately":[166],"rest":[169],"body,":[172],"eliminating":[173],"need":[175],"for":[176],"complex":[177],"post-processing":[178],"steps":[179],"attach":[181],"back":[184],"body.":[188],"train":[190],"network,":[192],"utilize":[194],"popular":[196],"game":[197],"engine":[198],"Unreal":[199],"Engine":[200],"generate":[202],"large":[204],"synthetic":[205],"dataset":[207],"containing":[208],"various":[209],"subjects,":[210],"head":[211],"poses,":[212],"expressions,":[213],"eyewear,":[214],"clothes,":[215],"lighting.":[217],"Quantitative":[218],"qualitative":[220],"show":[222],"outperforms":[227],"methods,":[229],"produces":[231],"comparable":[232],"with":[234],"time-consuming":[236],"GAN-based":[238],"method":[239],"while":[240],"being":[241],"more":[242],"than":[243],"260":[244],"times":[245],"faster.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-04T23:47:47.292601","created_date":"2025-10-10T00:00:00"}