{"id":"https://openalex.org/W4403791473","doi":"https://doi.org/10.1145/3664647.3680845","title":"ImageBind3D: Image as Binding Step for Controllable 3D Generation","display_name":"ImageBind3D: Image as Binding Step for Controllable 3D Generation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791473","doi":"https://doi.org/10.1145/3664647.3680845"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5107859057","display_name":"Z. Li","orcid":"https://orcid.org/0009-0006-7378-1313"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenqiang Li","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, Henan, China"],"affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, Henan, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679241","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-4974-6116"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072419341","display_name":"Yangjie Cao","orcid":"https://orcid.org/0000-0002-1170-4340"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangjie Cao","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, Henan, China"],"affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, Henan, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112970682","display_name":"Jiayi Wang","orcid":"https://orcid.org/0009-0007-1493-5113"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Wang","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, Henan, China"],"affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, Henan, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110330999","display_name":"Rongfu Lv","orcid":"https://orcid.org/0009-0008-9709-2613"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runfeng Lv","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, Henan, China"],"affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, Henan, China","institution_ids":["https://openalex.org/I38877650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5107859057"],"corresponding_institution_ids":["https://openalex.org/I38877650"],"apc_list":null,"apc_paid":null,"fwci":3.8581,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.96290257,"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":"3362","last_page":"3371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9995999932289124,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.595051646232605},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4568295478820801},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41953346133232117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36248907446861267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.595051646232605},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4568295478820801},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41953346133232117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36248907446861267}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2582734987","https://openalex.org/W2962770929","https://openalex.org/W2962849139","https://openalex.org/W2963926543","https://openalex.org/W2986615800","https://openalex.org/W3008102851","https://openalex.org/W3109585842","https://openalex.org/W3141954417","https://openalex.org/W3174831820","https://openalex.org/W3175047242","https://openalex.org/W3176179930","https://openalex.org/W3188353775","https://openalex.org/W3215807011","https://openalex.org/W4221151978","https://openalex.org/W4235375376","https://openalex.org/W4281485151","https://openalex.org/W4312325284","https://openalex.org/W4312453532","https://openalex.org/W4312638666","https://openalex.org/W4312708649","https://openalex.org/W4312933868","https://openalex.org/W4385318467","https://openalex.org/W4386065887","https://openalex.org/W4386071682","https://openalex.org/W4386071707","https://openalex.org/W4386075768","https://openalex.org/W4386075859","https://openalex.org/W4386083066","https://openalex.org/W4388191573","https://openalex.org/W4390872862","https://openalex.org/W4390873054"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,22,156],"3D":[3,38,52,76,92,100,107,145,171],"generation":[4,53,77],"have":[5],"garnered":[6],"considerable":[7],"interest":[8],"due":[9,26],"to":[10,27,62,115],"their":[11,176],"potential":[12],"applications.":[13],"Despite":[14],"these":[15,42],"advancements,":[16],"the":[17,28,34,103,119,136],"field":[18],"faces":[19],"persistent":[20],"challenges":[21],"multi-conditional":[23],"control,":[24],"primarily":[25],"lack":[29],"of":[30,37,106],"paired":[31,80],"datasets":[32],"and":[33,59,121,143,159],"inherent":[35],"complexity":[36],"structures.":[39],"To":[40],"address":[41],"challenges,":[43],"we":[44,110],"introduce":[45],"ImageBind3D,":[46],"a":[47,86,91],"novel":[48],"framework":[49],"for":[50,168],"controllable":[51,75,144],"that":[54,95,150],"integrates":[55],"text,":[56],"hand-drawn":[57],"sketches,":[58],"depth":[60],"maps":[61],"enhance":[63],"user":[64],"controllability.":[65,160,177],"Our":[66],"innovative":[67],"contribution":[68],"is":[69],"adopting":[70],"an":[71],"inversion-align":[72],"strategy,":[73],"facilitating":[74],"without":[78],"requiring":[79],"datasets.":[81],"Firstly,":[82],"utilizing":[83],"GET3D":[84],"as":[85,113],"baseline,":[87],"our":[88,125,162],"method":[89],"innovates":[90],"inversion":[93],"technique":[94],"synchronizes":[96],"2D":[97],"images":[98,112],"with":[99,135],"shapes":[101,120],"within":[102],"latent":[104,139],"space":[105],"GAN.":[108],"Subsequently,":[109],"leverage":[111],"intermediaries":[114],"facilitate":[116],"pseudo-pairing":[117],"between":[118],"various":[122],"modalities.":[123],"Moreover,":[124],"multi-modal":[126],"diffusion":[127],"model":[128],"design":[129],"strategically":[130],"aligns":[131],"external":[132],"control":[133],"signals":[134],"generative":[137,172],"model's":[138],"knowledge,":[140],"enabling":[141],"precise":[142],"generation.":[146],"Extensive":[147],"experiments":[148],"validate":[149],"ImageBind3D":[151],"surpasses":[152],"existing":[153],"state-of-the-art":[154],"methods":[155],"both":[157],"fidelity":[158],"Additionally,":[161],"approach":[163],"can":[164],"offer":[165],"composable":[166],"guidance":[167],"any":[169],"feed-forward":[170],"models,":[173],"significantly":[174],"enhancing":[175]},"counts_by_year":[{"year":2025,"cited_by_count":6}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}