{"id":"https://openalex.org/W4388191573","doi":"https://doi.org/10.1145/3581783.3612489","title":"Control3D: Towards Controllable Text-to-3D Generation","display_name":"Control3D: Towards Controllable Text-to-3D Generation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388191573","doi":"https://doi.org/10.1145/3581783.3612489"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612489","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083113249","display_name":"Yang Chen","orcid":"https://orcid.org/0009-0001-9058-5051"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0001-9058-5051","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085403640","display_name":"Yingwei Pan","orcid":"https://orcid.org/0000-0002-4344-8898"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingwei Pan","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4344-8898","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041154840","display_name":"Yehao Li","orcid":"https://orcid.org/0000-0002-9603-1113"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yehao Li","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9603-1113","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["HiDream.ai Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7587-101X","affiliations":[{"raw_affiliation_string":"HiDream.ai Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101517779","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0002-5990-7307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["HiDream.ai Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5990-7307","affiliations":[{"raw_affiliation_string":"HiDream.ai Inc., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083113249"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":5.0631,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96704602,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1148","last_page":"1156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9977999925613403,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9977999925613403,"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/T12290","display_name":"Human Motion and Animation","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.9481494426727295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7482353448867798},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5801985263824463},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5063871145248413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4905966818332672},{"id":"https://openalex.org/keywords/3d-model","display_name":"3d model","score":0.4561570882797241},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4434100091457367},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.4291859269142151},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4243232309818268},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4143294394016266},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3415372371673584},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15036991238594055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09609633684158325},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07585608959197998},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.07502824068069458}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.9481494426727295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7482353448867798},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5801985263824463},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5063871145248413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4905966818332672},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.4561570882797241},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4434100091457367},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4291859269142151},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4243232309818268},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4143294394016266},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3415372371673584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15036991238594055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09609633684158325},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07585608959197998},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.07502824068069458},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612489","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1987398446","https://openalex.org/W2122572959","https://openalex.org/W2981876524","https://openalex.org/W2982192816","https://openalex.org/W3034566390","https://openalex.org/W3109585842","https://openalex.org/W3173531806","https://openalex.org/W3183430956","https://openalex.org/W3200461691","https://openalex.org/W3202995573","https://openalex.org/W4294959213","https://openalex.org/W4312708649","https://openalex.org/W4312933868","https://openalex.org/W4312969460","https://openalex.org/W4366352791","https://openalex.org/W4386075859","https://openalex.org/W4386075992","https://openalex.org/W4390874122"],"related_works":["https://openalex.org/W2036697162","https://openalex.org/W2332386680","https://openalex.org/W2378994405","https://openalex.org/W2248621902","https://openalex.org/W2003779889","https://openalex.org/W2385974820","https://openalex.org/W2561315646","https://openalex.org/W17155033","https://openalex.org/W2035403512","https://openalex.org/W4367665542"],"abstract_inverted_index":{"Recent":[0],"remarkable":[1],"advances":[2],"in":[3,13,34],"large-scale":[4],"text-to-image":[5],"diffusion":[6,83],"models":[7],"have":[8],"inspired":[9],"a":[10,22,31,80,116],"significant":[11],"breakthrough":[12],"text-to-3D":[14,28,63,156],"generation,":[15],"pursuing":[16,153],"3D":[17,44,93,102,132,171],"content":[18],"creation":[19],"solely":[20],"from":[21],"given":[23,107,151],"text":[24,108,179],"prompt.":[25],"However,":[26],"existing":[27],"techniques":[29],"lack":[30],"crucial":[32],"ability":[33],"the":[35,42,59,67,90,106,124,127,150,177],"creative":[36],"process:":[37],"interactively":[38],"control":[39],"and":[40,110,169,181],"shape":[41],"synthetic":[43,131],"contents":[45],"according":[46],"to":[47,88,121,145],"users'":[48],"desired":[49],"specifications":[50],"(e.g.,":[51],"sketch).":[52],"To":[53],"alleviate":[54],"this":[55],"issue,":[56],"we":[57,114,161],"present":[58],"first":[60],"attempt":[61],"for":[62,76],"generation":[64],"conditioning":[65],"on":[66],"additional":[68],"hand-drawn":[69,111],"sketch,":[70,152],"namely":[71],"Control3D,":[72],"which":[73],"enhances":[74],"controllability":[75],"users.":[77],"In":[78],"particular,":[79],"2D":[81],"conditioned":[82],"model":[84,120],"(ControlNet)":[85],"is":[86,142],"remoulded":[87],"guide":[89],"learning":[91],"of":[92,101,126],"scene":[94,103],"parameterized":[95],"as":[96],"NeRF,":[97],"encouraging":[98],"each":[99,139],"view":[100,141],"aligned":[104],"with":[105,138,149,176],"prompt":[109],"sketch.":[112],"Moreover,":[113],"exploit":[115],"pre-trained":[117],"differentiable":[118],"photo-to-sketch":[119],"directly":[122],"estimate":[123],"sketch":[125,136],"rendered":[128],"image":[129],"over":[130],"scene.":[133],"Such":[134],"estimated":[135],"along":[137],"sampled":[140],"further":[143],"enforced":[144],"be":[146],"geometrically":[147],"consistent":[148],"better":[154],"controllable":[155],"generation.":[157],"Through":[158],"extensive":[159],"experiments,":[160],"demonstrate":[162],"that":[163,173],"our":[164],"proposal":[165],"can":[166],"generate":[167],"accurate":[168],"faithful":[170],"scenes":[172],"align":[174],"closely":[175],"input":[178],"prompts":[180],"sketches.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
