{"id":"https://openalex.org/W4417124691","doi":"https://doi.org/10.1145/3757377.3763867","title":"Object-level Visual Prompts for Compositional Image Generation","display_name":"Object-level Visual Prompts for Compositional Image Generation","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417124691","doi":"https://doi.org/10.1145/3757377.3763867"},"language":null,"primary_location":{"id":"doi:10.1145/3757377.3763867","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763867","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3757377.3763867","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030443008","display_name":"Gaurav Parmar","orcid":"https://orcid.org/0000-0001-8640-2243"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Parmar","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0001-8640-2243","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076541595","display_name":"Or Patashnik","orcid":"https://orcid.org/0000-0001-7757-6137"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Or Patashnik","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0001-7757-6137","affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086597688","display_name":"Kuan-Chieh Wang","orcid":"https://orcid.org/0000-0002-6785-8146"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuan-Chieh Wang","raw_affiliation_strings":["Snap Inc., Palo Alto, USA"],"raw_orcid":"https://orcid.org/0000-0002-6785-8146","affiliations":[{"raw_affiliation_string":"Snap Inc., Palo Alto, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093624098","display_name":"Daniil Ostashev","orcid":"https://orcid.org/0009-0009-7259-7399"},"institutions":[{"id":"https://openalex.org/I4210125711","display_name":"Snap40 (United Kingdom)","ror":"https://ror.org/03a2dk673","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210125711"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniil Ostashev","raw_affiliation_strings":["Snap Inc., London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0009-7259-7399","affiliations":[{"raw_affiliation_string":"Snap Inc., London, United Kingdom","institution_ids":["https://openalex.org/I4210125711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029497982","display_name":"Srinivasa G. Narasimhan","orcid":"https://orcid.org/0000-0003-0389-1921"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivasa Narasimhan","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0003-0389-1921","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102883508","display_name":"Jun-Yan Zhu","orcid":"https://orcid.org/0000-0001-8504-3410"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun-Yan Zhu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0001-8504-3410","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036688260","display_name":"Daniel Cohen\u2010Or","orcid":"https://orcid.org/0000-0001-6777-7445"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Daniel Cohen-Or","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0001-6777-7445","affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022318529","display_name":"Kfir Aberman","orcid":"https://orcid.org/0000-0002-4958-601X"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kfir Aberman","raw_affiliation_strings":["Snap Inc., Palo Alto, USA"],"raw_orcid":"https://orcid.org/0000-0002-4958-601X","affiliations":[{"raw_affiliation_string":"Snap Inc., Palo Alto, USA","institution_ids":["https://openalex.org/I4210142583"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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":0.8666999936103821,"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":0.8666999936103821,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.025200000032782555,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01140000019222498,"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/bottleneck","display_name":"Bottleneck","score":0.6789000034332275},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6531000137329102},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6288999915122986},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6019999980926514},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.590399980545044},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4036000072956085},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.39320001006126404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639999985694885},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6789000034332275},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6531000137329102},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6019999980926514},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.590399980545044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5623999834060669},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48159998655319214},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.39320001006126404},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3621000051498413},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3255000114440918},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29269999265670776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2773999869823456}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757377.3763867","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763867","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3757377.3763867","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763867","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2222512263","https://openalex.org/W2962785568","https://openalex.org/W3174265363","https://openalex.org/W4312933868","https://openalex.org/W4385270985","https://openalex.org/W4385271055","https://openalex.org/W4385527149","https://openalex.org/W4385535331","https://openalex.org/W4386072096","https://openalex.org/W4386075631","https://openalex.org/W4386076027","https://openalex.org/W4386076425","https://openalex.org/W4386076458","https://openalex.org/W4389347744","https://openalex.org/W4389539268","https://openalex.org/W4389539271","https://openalex.org/W4390872671","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4390874393","https://openalex.org/W4394625750","https://openalex.org/W4400580465","https://openalex.org/W4400582187","https://openalex.org/W4402660138","https://openalex.org/W4402703034","https://openalex.org/W4402727368","https://openalex.org/W4402727764","https://openalex.org/W4402733577","https://openalex.org/W4402753775","https://openalex.org/W4402754201","https://openalex.org/W4402774219","https://openalex.org/W4404984152","https://openalex.org/W4405003032","https://openalex.org/W4413157087"],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1,72],"a":[2,10,73,97,108],"method":[3],"for":[4,100],"composing":[5],"object-level":[6,150],"visual":[7,57,87,133,178],"prompts":[8,134],"within":[9],"text-to-image":[11,185],"diffusion":[12],"model.":[13],"Our":[14],"approach":[15],"addresses":[16],"the":[17,31,48,51,55,104,129,132,155,173,181],"task":[18,44],"of":[19,50,131,176,184],"generating":[20,61],"semantically":[21],"coherent":[22],"compositions":[23,63,170],"across":[24,64],"diverse":[25,62,168],"scenes":[26],"and":[27,33,81,120,143,159],"styles,":[28],"similar":[29],"to":[30,46,153],"versatility":[32],"expressiveness":[34],"offered":[35],"by":[36],"text":[37],"prompts.":[38],"A":[39],"key":[40],"challenge":[41],"in":[42,54,78,139],"this":[43,69],"is":[45],"preserve":[47,172],"identity":[49,130,157],"objects":[52],"depicted":[53],"input":[56],"prompts,":[58],"while":[59,135],"also":[60],"different":[65],"images.":[66],"To":[67],"address":[68],"challenge,":[70],"we":[71,147],"new":[74],"KV-mixed":[75],"cross-attention":[76],"mechanism,":[77],"which":[79],"keys":[80,90,119],"values":[82,105,121],"are":[83,91],"learned":[84],"from":[85,93,107,122],"distinct":[86],"representations.":[88],"The":[89],"derived":[92],"an":[94],"encoder":[95,111],"with":[96],"small":[98],"bottleneck":[99,110],"layout":[101,160],"control,":[102],"whereas":[103],"come":[106],"larger":[109],"that":[112,164,171],"captures":[113],"fine-grained":[114],"appearance":[115],"details.":[116],"By":[117],"mixing":[118],"these":[123],"complementary":[124],"sources,":[125],"our":[126,165],"model":[127],"preserves":[128],"supporting":[136],"flexible":[137],"variations":[138],"object":[140],"arrangement,":[141],"pose,":[142],"composition.":[144],"During":[145],"inference,":[146],"further":[148],"propose":[149],"compositional":[151],"guidance":[152],"improve":[154],"method\u2019s":[156],"preservation":[158],"correctness.":[161],"Results":[162],"show":[163],"technique":[166],"produces":[167],"scene":[169],"unique":[174],"characteristics":[175],"each":[177],"prompt,":[179],"expanding":[180],"creative":[182],"potential":[183],"generation.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-08T00:00:00"}