{"id":"https://openalex.org/W4417088410","doi":"https://doi.org/10.1145/3799902.3811219","title":"Canvas-to-Image: Compositional Image Generation with Multimodal Controls","display_name":"Canvas-to-Image: Compositional Image Generation with Multimodal Controls","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W4417088410","doi":"https://doi.org/10.1145/3799902.3811219"},"language":null,"primary_location":{"id":"doi:10.1145/3799902.3811219","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811219","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 Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799902.3811219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083169090","display_name":"Yusuf Dalva","orcid":"https://orcid.org/0000-0002-8402-8291"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusuf Dalva","raw_affiliation_strings":["Computer Science, Virginia Tech University, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-8402-8291","affiliations":[{"raw_affiliation_string":"Computer Science, Virginia Tech University, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032922702","display_name":"Guocheng Qian","orcid":"https://orcid.org/0000-0002-2935-8570"},"institutions":[{"id":"https://openalex.org/I4210087851","display_name":"Sunnyvale Public Library","ror":"https://ror.org/006afd344","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210087851"]},{"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":"Gordon Guocheng Qian","raw_affiliation_strings":["Snap, Sunnyvale, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-2935-8570","affiliations":[{"raw_affiliation_string":"Snap, Sunnyvale, California, USA","institution_ids":["https://openalex.org/I4210087851","https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Maya Goldenberg","orcid":"https://orcid.org/0009-0003-8367-7876"},"institutions":[{"id":"https://openalex.org/I4210111150","display_name":"GNA Research (Israel)","ror":"https://ror.org/01npr5x48","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210111150"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Maya Goldenberg","raw_affiliation_strings":["Snap, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0009-0003-8367-7876","affiliations":[{"raw_affiliation_string":"Snap, Tel Aviv, Israel","institution_ids":["https://openalex.org/I4210111150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058383656","display_name":"Tsai-Shien Chen","orcid":"https://orcid.org/0000-0002-8085-0042"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsai-Shien Chen","raw_affiliation_strings":["Snap, Santa Monica, California, USA and Computer Science, University of California Merced, Merced, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-8085-0042","affiliations":[{"raw_affiliation_string":"Snap, Santa Monica, California, USA and Computer Science, University of California Merced, Merced, California, USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","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, Palo Alto, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-4958-601X","affiliations":[{"raw_affiliation_string":"Snap, Palo Alto, California, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058028206","display_name":"Sergey Tulyakov","orcid":"https://orcid.org/0000-0003-3465-1592"},"institutions":[{"id":"https://openalex.org/I4210100321","display_name":"University of Santa Monica","ror":"https://ror.org/0145dtj11","country_code":"US","type":"education","lineage":["https://openalex.org/I4210100321"]},{"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":"Sergey Tulyakov","raw_affiliation_strings":["Snap, Santa Monica, California, USA"],"raw_orcid":"https://orcid.org/0000-0003-3465-1592","affiliations":[{"raw_affiliation_string":"Snap, Santa Monica, California, USA","institution_ids":["https://openalex.org/I4210100321","https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016498717","display_name":"Pinar Yanardag","orcid":"https://orcid.org/0000-0003-0193-7818"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pinar Yanardag","raw_affiliation_strings":["Computer Science, Virginia Tech University, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0009-0003-3452-7417","affiliations":[{"raw_affiliation_string":"Computer Science, Virginia Tech University, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086597688","display_name":"Kuan-Chieh Wang","orcid":"https://orcid.org/0000-0002-6785-8146"},"institutions":[{"id":"https://openalex.org/I4210087851","display_name":"Sunnyvale Public Library","ror":"https://ror.org/006afd344","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210087851"]},{"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 Jackson Wang","raw_affiliation_strings":["Snap, Sunnyvale, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-6785-8146","affiliations":[{"raw_affiliation_string":"Snap, Sunnyvale, California, USA","institution_ids":["https://openalex.org/I4210087851","https://openalex.org/I4210142583"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.02595258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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":0.6251000165939331,"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":0.6251000165939331,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.23759999871253967,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.05009999871253967,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.7024000287055969},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5253000259399414},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.48820000886917114},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4781999886035919},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4763000011444092},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46889999508857727},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45669999718666077},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4309000074863434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123000264167786},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.7024000287055969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5260999798774719},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4781999886035919},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4309000074863434},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3889000117778778},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30799999833106995},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.26350000500679016}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3799902.3811219","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811219","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 Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.21691","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.21691","pdf_url":"https://arxiv.org/pdf/2511.21691","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,"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.2511.21691","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.21691","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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3799902.3811219","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811219","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 Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"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":{"While":[0],"modern":[1],"diffusion":[2,105],"models":[3],"excel":[4],"at":[5],"generating":[6],"high-quality":[7],"and":[8,17,33,95,110,139,160,173],"diverse":[9,68],"images,":[10],"they":[11],"still":[12],"struggle":[13],"with":[14],"high-fidelity":[15],"compositional":[16],"multimodal":[18],"control,":[19],"particularly":[20],"when":[21],"users":[22,53],"simultaneously":[23],"specify":[24],"text":[25],"prompts,":[26],"subject":[27],"references,":[28],"spatial":[29],"arrangements,":[30],"pose":[31],"constraints,":[32],"layout":[34],"annotations.":[35],"We":[36,87],"introduce":[37],"Canvas-to-Image,":[38],"a":[39,48,72,90,97,118],"unified":[40,119],"framework":[41],"that":[42,57,77,102,151],"consolidates":[43],"these":[44],"heterogeneous":[45,112],"controls":[46,113],"into":[47,71,114],"single":[49,73],"canvas":[50,75],"interface,":[51],"enabling":[52],"to":[54,66,107,127,143],"generate":[55],"images":[56],"faithfully":[58],"reflect":[59],"their":[60],"intent.":[61],"Our":[62],"key":[63],"idea":[64],"is":[65],"encode":[67],"control":[69,131,161],"signals":[70],"composite":[74],"image":[76],"the":[78,104],"model":[79,106],"can":[80],"directly":[81],"interpret":[82],"for":[83],"integrated":[84],"visual-spatial":[85],"reasoning.":[86],"further":[88],"curate":[89],"suite":[91],"of":[92],"multi-task":[93],"datasets":[94],"propose":[96],"Multi-Task":[98],"Canvas":[99],"Training":[100],"strategy":[101],"optimizes":[103],"jointly":[108],"understand":[109],"integrate":[111],"text-to-image":[115],"generation":[116],"within":[117],"learning":[120],"paradigm.":[121],"This":[122],"joint":[123],"training":[124],"enables":[125],"Canvas-to-Image":[126,152],"reason":[128],"across":[129,163],"multiple":[130],"modalities":[132],"rather":[133],"than":[134],"relying":[135],"on":[136],"task-specific":[137],"heuristics,":[138],"it":[140],"generalizes":[141],"well":[142],"multi-control":[144,174],"scenarios":[145],"during":[146],"inference.":[147],"Extensive":[148],"experiments":[149],"show":[150],"significantly":[153],"outperforms":[154],"state-of-the-art":[155],"methods":[156],"in":[157],"identity":[158],"preservation":[159],"adherence":[162],"challenging":[164],"benchmarks,":[165],"including":[166],"multi-person":[167],"composition,":[168,170],"pose-controlled":[169],"layout-constrained":[171],"generation,":[172],"generation.":[175]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}