{"id":"https://openalex.org/W4416012293","doi":"https://doi.org/10.1002/cav.70119","title":"Person\u2010In\u2010Situ: Scene\u2010Consistent Human Image Insertion With Occlusion\u2010Aware Pose Control","display_name":"Person\u2010In\u2010Situ: Scene\u2010Consistent Human Image Insertion With Occlusion\u2010Aware Pose Control","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W4416012293","doi":"https://doi.org/10.1002/cav.70119"},"language":"en","primary_location":{"id":"doi:10.1002/cav.70119","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cav.70119","pdf_url":null,"source":{"id":"https://openalex.org/S100062975","display_name":"Computer Animation and Virtual Worlds","issn_l":"1546-4261","issn":["1546-4261","1546-427X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Animation and Virtual Worlds","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.04052","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shun Masuda","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shun Masuda","raw_affiliation_strings":["University of Tsukuba  Ibaraki Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba  Ibaraki Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079605823","display_name":"Yuki Endo","orcid":"https://orcid.org/0000-0001-5132-3350"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Endo","raw_affiliation_strings":["University of Tsukuba  Ibaraki Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba  Ibaraki Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001835128","display_name":"Yoshihiro Kanamori","orcid":"https://orcid.org/0000-0003-2843-1729"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiro Kanamori","raw_affiliation_strings":["University of Tsukuba  Ibaraki Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba  Ibaraki Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":{"value":3040,"currency":"USD","value_usd":3040},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00807928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"3","first_page":null,"last_page":null},"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":0.541100025177002,"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":0.541100025177002,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.10040000081062317,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.06989999860525131,"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/leverage","display_name":"Leverage (statistics)","score":0.5777999758720398},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.4571000039577484},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4187000095844269},{"id":"https://openalex.org/keywords/compositing","display_name":"Compositing","score":0.39239999651908875},{"id":"https://openalex.org/keywords/occlusion","display_name":"Occlusion","score":0.37130001187324524},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.33489999175071716}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.781000018119812},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7705000042915344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376999855041504},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5777999758720398},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.4571000039577484},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C129315195","wikidata":"https://www.wikidata.org/wiki/Q1121886","display_name":"Compositing","level":3,"score":0.39239999651908875},{"id":"https://openalex.org/C2776268601","wikidata":"https://www.wikidata.org/wiki/Q968808","display_name":"Occlusion","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2619999945163727}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1002/cav.70119","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cav.70119","pdf_url":null,"source":{"id":"https://openalex.org/S100062975","display_name":"Computer Animation and Virtual Worlds","issn_l":"1546-4261","issn":["1546-4261","1546-427X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Animation and Virtual Worlds","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2505.04052","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.04052","pdf_url":"https://arxiv.org/pdf/2505.04052","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2505.04052","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.04052","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.04052","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.04052","pdf_url":"https://arxiv.org/pdf/2505.04052","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"Compositing":[1],"human":[2],"figures":[3],"into":[4],"scene":[5,104,149],"images":[6],"has":[7],"broad":[8],"applications":[9],"in":[10,36],"areas":[11],"such":[12],"as":[13],"entertainment":[14],"and":[15,31,68,111,123,136,155],"advertising.":[16],"However,":[17],"existing":[18,144],"methods":[19,142],"often":[20],"cannot":[21],"handle":[22],"occlusion":[23,87,121],"of":[24,102],"the":[25,34,37,46,75,95,103,106,114,125],"inserted":[26,47],"person":[27,35,76,107,115,126],"by":[28,146],"foreground":[29],"objects":[30],"unnaturally":[32],"place":[33],"frontmost":[38],"layer.":[39],"Moreover,":[40],"they":[41],"offer":[42],"limited":[43],"control":[44,62],"over":[45],"person's":[48],"pose.":[49],"To":[50],"address":[51],"these":[52],"challenges,":[53],"we":[54],"propose":[55],"two":[56],"methods.":[57],"Both":[58],"allow":[59],"explicit":[60,132],"pose":[61],"via":[63],"a":[64,78,92,99],"3D":[65],"body":[66],"model":[67,96],"leverage":[69],"latent":[70],"diffusion":[71],"models":[72],"to":[73],"synthesize":[74],"at":[77],"contextually":[79],"appropriate":[80],"depth,":[81],"naturally":[82],"handling":[83],"occlusions":[84,154],"without":[85,131],"requiring":[86],"masks.":[88],"The":[89,117],"first":[90,97],"is":[91],"two\u2010stage":[93],"approach:":[94],"learns":[98,120],"depth":[100,133],"map":[101],"with":[105],"through":[108],"supervised":[109],"learning,":[110],"then":[112],"synthesizes":[113,124],"accordingly.":[116],"second":[118],"method":[119],"implicitly":[122],"directly":[127],"from":[128],"input":[129],"data":[130],"supervision.":[134],"Quantitative":[135],"qualitative":[137],"evaluations":[138],"show":[139],"that":[140],"both":[141],"outperform":[143],"approaches":[145],"better":[147],"preserving":[148],"consistency":[150],"while":[151],"accurately":[152],"reflecting":[153],"user\u2010specified":[156],"poses.":[157]},"counts_by_year":[],"updated_date":"2026-05-23T06:10:36.450269","created_date":"2025-10-10T00:00:00"}