{"id":"https://openalex.org/W4413277841","doi":"https://doi.org/10.1109/icip55913.2025.11084673","title":"Enabling Controllable, Identity Preserving, Non-Rigid Edits in Human-Centric Images","display_name":"Enabling Controllable, Identity Preserving, Non-Rigid Edits in Human-Centric Images","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413277841","doi":"https://doi.org/10.1109/icip55913.2025.11084673"},"language":"en","primary_location":{"id":"doi:10.1109/icip55913.2025.11084673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093367368","display_name":"Nikolai Warner","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolai Warner","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111870477","display_name":"Jack Kolb","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Kolb","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055189318","display_name":"Meera Hahn","orcid":"https://orcid.org/0009-0004-1549-088X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meera Hahn","raw_affiliation_strings":["Google, Inc.,Mountain View,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc.,Mountain View,CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079026336","display_name":"Jonathan Huang","orcid":"https://orcid.org/0000-0002-3428-9952"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Huang","raw_affiliation_strings":["Google, Inc.,Mountain View,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc.,Mountain View,CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076825006","display_name":"Vighnesh Birodkar","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vighnesh Birodkar","raw_affiliation_strings":["Google, Inc.,Mountain View,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc.,Mountain View,CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070348998","display_name":"Irfan Essa","orcid":"https://orcid.org/0000-0002-6236-2969"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Irfan Essa","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA","institution_ids":["https://openalex.org/I130701444"]}]}],"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":0.20843984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"629","last_page":"634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9631999731063843,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9631999731063843,"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":0.9289000034332275,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9067999720573425,"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/computer-science","display_name":"Computer science","score":0.6453554630279541},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6136501431465149},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41346630454063416},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37538641691207886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3361518383026123},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.15515220165252686},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.11429166793823242}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6453554630279541},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6136501431465149},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41346630454063416},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37538641691207886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3361518383026123},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.15515220165252686},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.11429166793823242}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip55913.2025.11084673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2080873731","https://openalex.org/W2471768434","https://openalex.org/W2964134613","https://openalex.org/W3015356384","https://openalex.org/W3173873424","https://openalex.org/W4313041141","https://openalex.org/W4385535562","https://openalex.org/W4386057725","https://openalex.org/W4386075924","https://openalex.org/W4386076215","https://openalex.org/W4386076520","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4392411949","https://openalex.org/W4402727040","https://openalex.org/W4409262948"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,46,92],"approach":[1],"the":[2,36,48,85,95,105],"problem":[3],"of":[4,22,28,35,50,74,84,97,108],"inserting":[5],"a":[6,9,23,25,29,32,59,69,114,130],"person":[7],"into":[8],"novel":[10,70],"scene":[11],"and":[12,31,55,78,104,128],"controlling":[13],"their":[14],"pose":[15,89,118],"via":[16,58],"text":[17,33,82],"guidance.":[18],"Given":[19],"an":[20],"image":[21,27],"person,":[24],"masked":[26],"scene,":[30],"description":[34],"target":[37],"pose,":[38],"our":[39,51],"model":[40],"generates":[41],"realistic,":[42],"highly":[43],"controllable":[44,98],"images.":[45,64],"validate":[47],"robustness":[49],"model\u2019s":[52],"true-to-text":[53],"accuracy":[54],"identity":[56,99],"preservation":[57,100],"user":[60],"study":[61],"on":[62],"in-the-wild":[63,102],"In":[65],"addition,":[66],"we":[67],"present":[68],"dataset":[71],"containing":[72],"pairs":[73],"frames":[75],"from":[76],"human-centric":[77],"action-rich":[79],"videos,":[80],"with":[81],"captions":[83],"difference":[86],"in":[87,117],"human":[88],"between":[90],"frames.":[91],"also":[93],"explore":[94],"challenges":[96],"for":[101],"scenes":[103],"failure":[106],"modes":[107],"similar":[109],"models.":[110],"Our":[111],"methods":[112,123],"achieve":[113],"10%":[115],"increase":[116],"adherence":[119],"(PCKt@0.5)":[120],"over":[121],"comparable":[122],"without":[124],"compromising":[125],"visual":[126],"fidelity,":[127],"show":[129],"clear":[131],"qualitative":[132],"improvement.":[133]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}