{"id":"https://openalex.org/W4386080987","doi":"https://doi.org/10.48550/arxiv.2308.10040","title":"ControlCom: Controllable Image Composition using Diffusion Model","display_name":"ControlCom: Controllable Image Composition using Diffusion Model","publication_year":2023,"publication_date":"2023-08-19","ids":{"openalex":"https://openalex.org/W4386080987","doi":"https://doi.org/10.48550/arxiv.2308.10040"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2308.10040","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.10040","pdf_url":"https://arxiv.org/pdf/2308.10040","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.10040","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100335215","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0001-9172-698X","observed_orcids":["https://orcid.org/0000-0001-9172-698X","https://orcid.org/0000-0001-5527-5499","https://orcid.org/0009-0008-6416-4967"]},"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":"Zhang, Bo","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053217897","display_name":"Yuxuan Duan","orcid":"https://orcid.org/0009-0003-1176-2692","observed_orcids":["https://orcid.org/0009-0003-1176-2692"]},"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":"Duan, Yuxuan","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lan, Jun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan, Jun","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107194390","display_name":"Yan Hong","orcid":"https://orcid.org/0000-0001-6401-0812","observed_orcids":["https://orcid.org/0000-0001-6401-0812"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong, Yan","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101236538","display_name":"Huijia Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Huijia","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109203493","display_name":"Weiqiang Wang","orcid":"https://orcid.org/0000-0002-6159-619X","observed_orcids":["https://orcid.org/0000-0002-6159-619X","https://orcid.org/0000-0002-7185-2804","https://orcid.org/0000-0001-5734-1226"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Weiqiang","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032618817","display_name":"Li Niu","orcid":"https://orcid.org/0000-0003-1970-8634","observed_orcids":["https://orcid.org/0000-0003-1970-8634"]},"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":"Niu, Li","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":65,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T11659","display_name":"Advanced Image Fusion Techniques","score":9.999999747378752e-05,"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/T12357","display_name":"Digital Media Forensic Detection","score":9.999999747378752e-05,"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/image-composition","display_name":"image composition","score":0.9670000076293945},{"id":"https://openalex.org/keywords/controllable-image-generation","display_name":"controllable image generation","score":0.6919999718666077},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.875},{"id":"https://openalex.org/keywords/image-blending","display_name":"image blending","score":0.9380000233650208},{"id":"https://openalex.org/keywords/image-harmonization","display_name":"image harmonization","score":0.9829999804496765},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"view synthesis","score":0.9909999966621399},{"id":"https://openalex.org/keywords/self-supervised-training","display_name":"self-supervised training","score":0.8209999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7276406288146973},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6406363248825073},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6151377558708191},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5989049673080444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.534816324710846},{"id":"https://openalex.org/C78087231","wikidata":"https://www.wikidata.org/wiki/Q5156759","display_name":"Composite image filter","level":3,"score":0.5126144289970398},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.5112431049346924},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4910774230957031},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.46758437156677246},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4470389783382416},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4418404698371887},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4369319677352905},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4084147810935974},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3579959273338318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13665813207626343},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2308.10040","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.10040","pdf_url":"https://arxiv.org/pdf/2308.10040","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2308.10040","doi":"https://doi.org/10.48550/arxiv.2308.10040","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2308.10040","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.10040","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.10040","pdf_url":"https://arxiv.org/pdf/2308.10040","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386080987.pdf","grobid_xml":"https://content.openalex.org/works/W4386080987.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4390874575"],"related_works":["https://openalex.org/W4319452911","https://openalex.org/W7201956352","https://openalex.org/W4412710296","https://openalex.org/W4321473567","https://openalex.org/W4404403135","https://openalex.org/W4404582941","https://openalex.org/W4392678166","https://openalex.org/W4416252293","https://openalex.org/W4394593093","https://openalex.org/W4386075528"],"abstract_inverted_index":{"Image":[0],"composition":[1,19,64],"targets":[2],"at":[3,157],"synthesizing":[4],"a":[5,10,61,86,92,102],"realistic":[6],"composite":[7,30,120,145],"image":[8,37,63,74,76],"from":[9,42],"pair":[11],"of":[12,44,52,95,119],"foreground":[13,47,53,109,117],"and":[14,49,80,131,143,152],"background":[15],"images.":[16,121],"Recently,":[17],"generative":[18,81],"methods":[20],"are":[21],"built":[22],"on":[23,46,127],"large":[24],"pretrained":[25],"diffusion":[26,72,113],"models":[27],"to":[28,106],"generate":[29,140],"images,":[31],"considering":[32],"their":[33],"great":[34],"potential":[35],"in":[36,70,111],"generation.":[38],"However,":[39],"they":[40],"suffer":[41],"lack":[43],"controllability":[45],"attributes":[48],"poor":[50],"preservation":[51],"identity.":[54],"To":[55],"address":[56],"these":[57],"challenges,":[58],"we":[59,84,100],"propose":[60,101],"controllable":[62,144],"method":[65,124,138],"that":[66,136],"unifies":[67],"four":[68],"tasks":[69],"one":[71],"model:":[73],"blending,":[75],"harmonization,":[77],"view":[78],"synthesis,":[79],"composition.":[82],"Meanwhile,":[83],"design":[85],"self-supervised":[87],"training":[88,96],"framework":[89],"coupled":[90],"with":[91],"tailored":[93],"pipeline":[94],"data":[97],"preparation.":[98],"Moreover,":[99],"local":[103],"enhancement":[104],"module":[105],"enhance":[107],"the":[108,112,116],"details":[110],"model,":[114],"improving":[115],"fidelity":[118],"The":[122,150],"proposed":[123],"is":[125],"evaluated":[126],"both":[128],"public":[129],"benchmark":[130],"real-world":[132],"data,":[133],"which":[134],"demonstrates":[135],"our":[137],"can":[139],"more":[141],"faithful":[142],"images":[146],"than":[147],"existing":[148],"approaches.":[149],"code":[151],"model":[153],"will":[154],"be":[155],"available":[156],"https://github.com/bcmi/ControlCom-Image-Composition.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-08-23T00:00:00"}