{"id":"https://openalex.org/W4412596223","doi":"https://doi.org/10.1145/3721238.3730631","title":"Be Decisive: Noise-Induced Layouts for Multi-Subject Generation","display_name":"Be Decisive: Noise-Induced Layouts for Multi-Subject Generation","publication_year":2025,"publication_date":"2025-07-23","ids":{"openalex":"https://openalex.org/W4412596223","doi":"https://doi.org/10.1145/3721238.3730631"},"language":"en","primary_location":{"id":"doi:10.1145/3721238.3730631","doi":"https://doi.org/10.1145/3721238.3730631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721238.3730631","pdf_url":null,"source":{"id":"https://openalex.org/S7407086393","display_name":"ACM SIGGRAPH Conference (SIGGRAPH)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3721238.3730631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006738834","display_name":"Omer Dahary","orcid":"https://orcid.org/0000-0003-0448-9301","observed_orcids":["https://orcid.org/0000-0003-0448-9301"]},"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":"Omer Dahary","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel and Snap Research, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0003-0448-9301","affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel and Snap Research, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089633683","display_name":"Yonni Cohen","orcid":"https://orcid.org/0009-0007-7919-4301","observed_orcids":["https://orcid.org/0009-0007-7919-4301"]},"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":"Yehonathan Cohen","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0009-0007-7919-4301","affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076541595","display_name":"Or Patashnik","orcid":"https://orcid.org/0000-0001-7757-6137","observed_orcids":["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 and Snap Research, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0001-7757-6137","affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel and Snap Research, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022318529","display_name":"Kfir Aberman","orcid":"https://orcid.org/0000-0002-4958-601X","observed_orcids":["https://orcid.org/0000-0002-4958-601X","https://orcid.org/0000-0001-6028-6600"]},"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 Research, Palo Alto, USA"],"raw_orcid":"https://orcid.org/0000-0002-4958-601X","affiliations":[{"raw_affiliation_string":"Snap Research, Palo Alto, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036688260","display_name":"Daniel Cohen\u2010Or","orcid":"https://orcid.org/0000-0001-6777-7445","observed_orcids":["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 and Snap Research, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0001-6777-7445","affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel and Snap Research, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1477,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.90809736,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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":1.0,"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":1.0,"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":0.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/text-to-image-generation","display_name":"text-to-image generation","score":0.8460000157356262},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.6859999895095825},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.7020000219345093},{"id":"https://openalex.org/keywords/image-text-alignment","display_name":"image-text alignment","score":0.8619999885559082}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5971431732177734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5823653340339661},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.571204423904419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17049893736839294},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07008746266365051},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3721238.3730631","doi":"https://doi.org/10.1145/3721238.3730631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721238.3730631","pdf_url":null,"source":{"id":"https://openalex.org/S7407086393","display_name":"ACM SIGGRAPH Conference (SIGGRAPH)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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:2505.21488","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.21488","pdf_url":"https://arxiv.org/pdf/2505.21488","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.21488","doi":"https://doi.org/10.48550/arxiv.2505.21488","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.21488","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":"doi:10.1145/3721238.3730631","doi":"https://doi.org/10.1145/3721238.3730631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721238.3730631","pdf_url":null,"source":{"id":"https://openalex.org/S7407086393","display_name":"ACM SIGGRAPH Conference (SIGGRAPH)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2373914695","display_name":null,"funder_award_id":"3441/21","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412596223.pdf","grobid_xml":"https://content.openalex.org/works/W4412596223.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2432481613","https://openalex.org/W4224035735","https://openalex.org/W4289785045","https://openalex.org/W4311252447","https://openalex.org/W4312933868","https://openalex.org/W4378446358","https://openalex.org/W4383472654","https://openalex.org/W4385005290","https://openalex.org/W4385270985","https://openalex.org/W4385537492","https://openalex.org/W4386066731","https://openalex.org/W4386075631","https://openalex.org/W4386076027","https://openalex.org/W4386076403","https://openalex.org/W4386113271","https://openalex.org/W4387596318","https://openalex.org/W4388187930","https://openalex.org/W4389217124","https://openalex.org/W4390872387","https://openalex.org/W4390872477","https://openalex.org/W4390872671","https://openalex.org/W4390873054","https://openalex.org/W4390873211","https://openalex.org/W4390873875","https://openalex.org/W4390874089","https://openalex.org/W4391272787","https://openalex.org/W4393942901","https://openalex.org/W4394625750","https://openalex.org/W4396945437","https://openalex.org/W4399414064","https://openalex.org/W4399597888","https://openalex.org/W4400580465","https://openalex.org/W4402623742","https://openalex.org/W4402702908","https://openalex.org/W4402702967","https://openalex.org/W4402716119","https://openalex.org/W4402727440","https://openalex.org/W4402733577","https://openalex.org/W4402754201","https://openalex.org/W4405003032","https://openalex.org/W4409264082","https://openalex.org/W4412596348","https://openalex.org/W4413147601","https://openalex.org/W6604801084","https://openalex.org/W7133204405"],"related_works":["https://openalex.org/W4396821602","https://openalex.org/W4405003032","https://openalex.org/W4399597888","https://openalex.org/W7117646132","https://openalex.org/W4406676827","https://openalex.org/W4414680040","https://openalex.org/W4415708040","https://openalex.org/W4415014699","https://openalex.org/W7166561534","https://openalex.org/W7115932494"],"abstract_inverted_index":{"Generating":[0],"multiple":[1],"distinct":[2],"subjects":[3,30,145],"remains":[4],"a":[5,52,79,84,125],"challenge":[6],"for":[7],"existing":[8,167],"text-to-image":[9],"diffusion":[10],"models.":[11],"Complex":[12],"prompts":[13],"often":[14,55],"lead":[15],"to":[16,68,129,166],"subject":[17],"leakage,":[18],"causing":[19],"inaccuracies":[20],"in":[21],"quantities,":[22],"attributes,":[23],"and":[24,96,116,131,160],"visual":[25],"features.":[26],"Preventing":[27],"leakage":[28],"among":[29],"necessitates":[31],"knowledge":[32],"of":[33,175],"each":[34,138],"subject's":[35],"spatial":[36,42,85],"location.":[37],"Recent":[38],"methods":[39],"provide":[40],"these":[41],"locations":[43],"via":[44],"an":[45],"external":[46],"layout":[47,54,60,86,136],"control.":[48],"However,":[49],"enforcing":[50],"such":[51],"prescribed":[53],"conflicts":[56,111],"with":[57,70,88,112],"the":[58,63,71,89,93,100,119,133,172,176],"innate":[59],"dictated":[61],"by":[62],"sampled":[64],"initial":[65,94],"noise,":[66,95],"leading":[67],"misalignment":[69],"model's":[72,120,177],"prior.":[73,121],"In":[74],"this":[75,106,153],"work,":[76],"we":[77,109],"introduce":[78],"new":[80],"approach":[81],"that":[82,152],"predicts":[83],"aligned":[87],"prompt,":[90],"derived":[91],"from":[92],"refines":[97],"it":[98],"throughout":[99],"denoising":[101,139],"process.":[102],"By":[103],"relying":[104],"on":[105],"noise-induced":[107,135],"layout,":[108],"avoid":[110],"externally":[113],"imposed":[114],"layouts":[115],"better":[117],"preserve":[118],"Our":[122],"method":[123],"employs":[124],"small":[126],"neural":[127],"network":[128],"predict":[130],"refine":[132],"evolving":[134],"at":[137],"step,":[140],"ensuring":[141],"clear":[142],"boundaries":[143],"between":[144],"while":[146,170],"maintaining":[147],"consistency.":[148],"Experimental":[149],"results":[150],"show":[151],"noise-aligned":[154],"strategy":[155],"achieves":[156],"improved":[157],"text-image":[158],"alignment":[159],"more":[161],"stable":[162],"multi-subject":[163],"generation":[164],"compared":[165],"layout-guided":[168],"techniques,":[169],"preserving":[171],"rich":[173],"diversity":[174],"original":[178],"distribution.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":6}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}