{"id":"https://openalex.org/W4415539751","doi":"https://doi.org/10.1145/3746027.3755603","title":"<i>FreeInsert</i> : Personalized Object Insertion with Geometric and Style Control","display_name":"<i>FreeInsert</i> : Personalized Object Insertion with Geometric and Style Control","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539751","doi":"https://doi.org/10.1145/3746027.3755603"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755603","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5004323368","display_name":"Yuhong Zhang","orcid":"https://orcid.org/0009-0000-8902-0013"},"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":"Yuhong Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-8902-0013","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111215638","display_name":"H J Wang","orcid":"https://orcid.org/0009-0008-0995-0092"},"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":"Han Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-0995-0092","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiwen Wang","orcid":"https://orcid.org/0009-0002-6575-907X"},"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":"Yiwen Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-6575-907X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577089","display_name":"Rong Xie","orcid":"https://orcid.org/0000-0002-8261-5337"},"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":"Rong Xie","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8261-5337","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002404808","display_name":"Li Song","orcid":"https://orcid.org/0000-0002-7124-5182"},"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":"Li Song","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7124-5182","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"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":"10361","last_page":"10369"},"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":0.9995999932289124,"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":0.9995999932289124,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9994999766349792,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994000196456909,"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/object","display_name":"Object (grammar)","score":0.7365000247955322},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.571399986743927},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5497999787330627},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5378999710083008},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5253999829292297},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.461899995803833},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4275999963283539},{"id":"https://openalex.org/keywords/geometric-modeling","display_name":"Geometric modeling","score":0.4032999873161316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373999953269958},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7365000247955322},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6503999829292297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6111000180244446},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.571399986743927},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5378999710083008},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.461899995803833},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.3391000032424927},{"id":"https://openalex.org/C40319758","wikidata":"https://www.wikidata.org/wiki/Q5535477","display_name":"Geometric design","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.2800000011920929},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C32990609","wikidata":"https://www.wikidata.org/wiki/Q306542","display_name":"Transformation geometry","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755603","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2475287302","https://openalex.org/W2603777577","https://openalex.org/W2939873304","https://openalex.org/W2969803502","https://openalex.org/W3136544170","https://openalex.org/W4312933868","https://openalex.org/W4386072096","https://openalex.org/W4386083141","https://openalex.org/W4386113271","https://openalex.org/W4390872636","https://openalex.org/W4390873054","https://openalex.org/W4390873331","https://openalex.org/W4402716004"],"related_works":[],"abstract_inverted_index":{"Text-to-image":[0],"diffusion":[1,196,207],"models":[2],"have":[3],"made":[4],"significant":[5],"progress":[6],"in":[7,92,138],"image":[8,17,28,165],"generation,":[9],"allowing":[10],"for":[11],"effortless":[12],"customized":[13],"generation.":[14],"However,":[15],"existing":[16,139],"editing":[18,153],"methods":[19,46,78],"still":[20],"face":[21],"certain":[22],"limitations":[23],"when":[24],"dealing":[25],"with":[26,189],"personalized":[27],"composition":[29],"tasks.":[30],"First,":[31],"there":[32,70],"is":[33,71,187],"the":[34,42,67,72,81,85,89,99,136,146,155,206],"issue":[35],"of":[36,38,74,95,101],"lack":[37,94],"geometric":[39,64,132,173,185],"control":[40,65,193],"over":[41,66],"inserted":[43,86],"objects.":[44,68],"Current":[45],"are":[47],"confined":[48],"to":[49,61],"2D":[50,147,164],"space":[51],"and":[52,88,158,191],"typically":[53],"rely":[54],"on":[55],"textual":[56],"instructions,":[57],"making":[58],"it":[59,161],"challenging":[60],"maintain":[62],"precise":[63],"Second,":[69],"challenge":[73,100],"style":[75,82,190],"consistency.":[76],"Existing":[77],"often":[79],"overlook":[80],"consistency":[83],"between":[84],"object":[87,124,148],"background,":[90],"resulting":[91],"a":[93,118,163,167],"realism.":[96],"In":[97],"addition,":[98],"inserting":[102],"objects":[103],"into":[104,126,149,162],"images":[105,204],"without":[106],"extensive":[107],"training":[108],"remains":[109],"significant.":[110],"To":[111],"address":[112],"these":[113],"issues,":[114],"we":[115,143],"propose":[116],"FreeInsert,":[117],"novel":[119],"training-free":[120],"framework":[121],"that":[122],"customizes":[123],"insertion":[125],"arbitrary":[127],"scenes":[128],"by":[129],"leveraging":[130],"3D":[131,140,156],"information.":[133],"Benefiting":[134],"from":[135,166],"advances":[137],"generation":[141],"models,":[142],"first":[144],"convert":[145],"3D,":[150],"perform":[151],"interactive":[152],"at":[154],"level,":[157],"then":[159],"re-render":[160],"specified":[168],"view.":[169,179],"This":[170],"process":[171],"introduces":[172],"controls":[174],"such":[175],"as":[176,184],"shape":[177],"or":[178],"The":[180],"rendered":[181],"image,":[182],"serving":[183],"control,":[186],"combined":[188],"content":[192],"achieved":[194],"through":[195],"adapters,":[197],"ultimately":[198],"producing":[199],"geometrically":[200],"controlled,":[201],"style-consistent":[202],"edited":[203],"via":[205],"model.":[208]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
