{"id":"https://openalex.org/W7164848027","doi":"https://doi.org/10.1145/3805622.3810834","title":"RainbowDreamer: Taming Semantic Controls for Attribute-Consistent Text-to-3D Generation","display_name":"RainbowDreamer: Taming Semantic Controls for Attribute-Consistent Text-to-3D Generation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164848027","doi":"https://doi.org/10.1145/3805622.3810834"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810834","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810834","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067211836","display_name":"Weiyi Bu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiyi Bu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-8246-7177","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058799911","display_name":"Xiaodong Cun","orcid":"https://orcid.org/0000-0003-3607-2236"},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":null,"type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Cun","raw_affiliation_strings":["Great Bay University, Dongguan, China"],"raw_orcid":"https://orcid.org/0000-0003-3607-2236","affiliations":[{"raw_affiliation_string":"Great Bay University, Dongguan, China","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015239198","display_name":"Rui Yin","orcid":"https://orcid.org/0000-0003-0252-9664"},"institutions":[{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Rui Yin","raw_affiliation_strings":["Hangzhou City University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0252-9664","affiliations":[{"raw_affiliation_string":"Hangzhou City University, Hangzhou, China","institution_ids":["https://openalex.org/I6469544","https://openalex.org/I4400573310"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010051284","display_name":"Jiantao Yuan","orcid":"https://orcid.org/0000-0002-8269-6501"},"institutions":[{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Jiantao Yuan","raw_affiliation_strings":["Hangzhou City University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8269-6501","affiliations":[{"raw_affiliation_string":"Hangzhou City University, Hangzhou, China","institution_ids":["https://openalex.org/I6469544","https://openalex.org/I4400573310"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011540295","display_name":"Wei Qi","orcid":"https://orcid.org/0000-0002-6629-1264"},"institutions":[{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Wei Qi","raw_affiliation_strings":["Hangzhou City University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6629-1264","affiliations":[{"raw_affiliation_string":"Hangzhou City University, Hangzhou, China","institution_ids":["https://openalex.org/I6469544","https://openalex.org/I4400573310"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.93875196,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1015","last_page":"1024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.47519999742507935,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.47519999742507935,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.25920000672340393,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.0649000033736229,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6031000018119812},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5909000039100647},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4551999866962433},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4498000144958496},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44209998846054077},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.423799991607666},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.359499990940094},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.3027999997138977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7172999978065491},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6031000018119812},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5909000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5522000193595886},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4551999866962433},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4498000144958496},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4117000102996826},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3668000102043152},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810834","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810834","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W3109585842","https://openalex.org/W4312933868","https://openalex.org/W4385270985","https://openalex.org/W4386065887","https://openalex.org/W4386072096","https://openalex.org/W4390873054","https://openalex.org/W4390873331","https://openalex.org/W4390873542","https://openalex.org/W4393154018","https://openalex.org/W4393154693","https://openalex.org/W4399563697","https://openalex.org/W4400580465","https://openalex.org/W4402716105","https://openalex.org/W4402716438","https://openalex.org/W4402727236","https://openalex.org/W4402727440","https://openalex.org/W4402727474","https://openalex.org/W4402727912","https://openalex.org/W4402753842","https://openalex.org/W4402753870","https://openalex.org/W4402754301","https://openalex.org/W4415796806"],"related_works":[],"abstract_inverted_index":{"Text-to-3D":[0],"generation":[1],"has":[2],"made":[3],"significant":[4],"progress":[5],"in":[6,48,158],"terms":[7],"of":[8,83,123],"fidelity":[9],"and":[10,70,144,161],"geometric":[11],"consistency.":[12,111],"However,":[13],"current":[14],"methods":[15],"still":[16],"struggle":[17],"to":[18,39,107],"generate":[19,40],"complex":[20,145],"attributes":[21],"from":[22,137],"the":[23,36,49,61,81,99,109,120,124,133],"text":[24],"prompts.":[25],"We":[26,131],"thus":[27],"present":[28],"RainbowDreamer,":[29],"a":[30,54,66,75,93,116],"three-stage":[31],"framework":[32],"that":[33,153],"builds":[34],"up":[35],"semantic":[37,110],"controls":[38],"attribute-consistent":[41],"3D":[42,125,135],"Gaussian":[43],"Splattings":[44],"(3DGS).":[45],"In":[46],"detail,":[47],"first":[50],"stage,":[51],"we":[52,87,113],"optimize":[53,88],"3DGS":[55],"for":[56,119],"geometry":[57,82],"reference":[58,85],"by":[59,65],"removing":[60],"attribute":[62],"prompts":[63],"optimized":[64],"hybrid":[67],"stable":[68],"diffusion":[69,72],"multi-view":[71],"models":[73],"with":[74],"view-dependent":[76],"rescaling":[77],"strategy.":[78],"Then,":[79],"utilizing":[80],"this":[84],"3DGS,":[86],"their":[89],"color":[90],"only":[91],"via":[92,127],"diffusion-based":[94],"full":[95],"prompt":[96],"lifting,":[97],"where":[98],"attention":[100],"restriction":[101],"between":[102],"two":[103],"stages":[104],"is":[105],"utilized":[106],"measure":[108],"Finally,":[112],"further":[114],"introduce":[115],"refinement":[117],"stage":[118],"overall":[121],"quality":[122],"assets":[126,136],"Bootstrapped":[128],"Score":[129],"Distillation.":[130],"evaluate":[132],"generated":[134],"multiple":[138],"aspects":[139],"using":[140],"both":[141,159],"CLIP":[142],"similarity":[143],"vision":[146],"language":[147],"model":[148],"understanding":[149],"abilities.":[150],"Results":[151],"demonstrate":[152],"RainbowDreamer":[154],"achieves":[155],"state-of-the-art":[156],"performance":[157],"quantitative":[160],"qualitative":[162],"evaluations.":[163]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}