{"id":"https://openalex.org/W4406857575","doi":"https://doi.org/10.1109/tmm.2025.3535389","title":"ShapeGPT: 3D Shape Generation With a Unified Multi-Modal Language Model","display_name":"ShapeGPT: 3D Shape Generation With a Unified Multi-Modal Language Model","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406857575","doi":"https://doi.org/10.1109/tmm.2025.3535389"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535389","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5076278944","display_name":"Fukun Yin","orcid":"https://orcid.org/0000-0003-2623-1619"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fukun Yin","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638657","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0002-0747-1361"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["Tencent PCG, Shanghai, China","Tencent PCG, China"],"affiliations":[{"raw_affiliation_string":"Tencent PCG, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent PCG, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009276628","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0003-4072-580X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["Tencent PCG, Shanghai, China","Tencent PCG, China"],"affiliations":[{"raw_affiliation_string":"Tencent PCG, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent PCG, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109335984","display_name":"Biao Jiang","orcid":"https://orcid.org/0000-0002-4292-7811"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Jiang","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039427876","display_name":"Zibo Zhao","orcid":"https://orcid.org/0000-0003-1089-2375"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zibo Zhao","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China","ShanghaiTech University, China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"ShanghaiTech University, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085927257","display_name":"Wenzhao Liu","orcid":"https://orcid.org/0000-0001-7506-0663"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Liu","raw_affiliation_strings":["Tencent PCG, Shanghai, China","Deepseek, China"],"affiliations":[{"raw_affiliation_string":"Tencent PCG, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Deepseek, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040261755","display_name":"Gang Yu","orcid":"https://orcid.org/0000-0003-1376-7959"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Yu","raw_affiliation_strings":["Tencent PCG, Shanghai, China","Tencent PCG, China"],"affiliations":[{"raw_affiliation_string":"Tencent PCG, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent PCG, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021220108","display_name":"Tao Chen","orcid":"https://orcid.org/0000-0002-0779-9818"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Chen","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5076278944"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":10.5524,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98226756,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"4107","last_page":"4120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.973800003528595,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.973800003528595,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9703999757766724,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9501000046730042,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8647238612174988},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6032269597053528},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37173357605934143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3299352526664734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8647238612174988},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6032269597053528},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37173357605934143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3299352526664734},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3535389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535389","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3977413633","display_name":null,"funder_award_id":"62071127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5491202952","display_name":null,"funder_award_id":"23ZR1402900","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"},{"id":"https://openalex.org/G7626924423","display_name":null,"funder_award_id":"62101137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W172260869","https://openalex.org/W2165290582","https://openalex.org/W2752796333","https://openalex.org/W2896457183","https://openalex.org/W2911758669","https://openalex.org/W2954298866","https://openalex.org/W2962766617","https://openalex.org/W2963979492","https://openalex.org/W2964078384","https://openalex.org/W2964110616","https://openalex.org/W2965741640","https://openalex.org/W2995795169","https://openalex.org/W3093319304","https://openalex.org/W3097606102","https://openalex.org/W3106531402","https://openalex.org/W3141954417","https://openalex.org/W3176445421","https://openalex.org/W3176481196","https://openalex.org/W3196231425","https://openalex.org/W3201927751","https://openalex.org/W3203711169","https://openalex.org/W3215807011","https://openalex.org/W4205403018","https://openalex.org/W4226020718","https://openalex.org/W4294959213","https://openalex.org/W4312741694","https://openalex.org/W4312910764","https://openalex.org/W4313484934","https://openalex.org/W4316661142","https://openalex.org/W4319300992","https://openalex.org/W4385275714","https://openalex.org/W4386071477","https://openalex.org/W4386071707","https://openalex.org/W4386076002","https://openalex.org/W4386076097","https://openalex.org/W4389519587","https://openalex.org/W4390871736","https://openalex.org/W4390872054","https://openalex.org/W4390872205","https://openalex.org/W4390873294","https://openalex.org/W4393207111","https://openalex.org/W4402727885","https://openalex.org/W4402753669","https://openalex.org/W4402753917","https://openalex.org/W4402772377","https://openalex.org/W6687484953","https://openalex.org/W6757817989","https://openalex.org/W6763236253","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6790830454","https://openalex.org/W6791353385","https://openalex.org/W6793508835","https://openalex.org/W6798033281","https://openalex.org/W6810334672","https://openalex.org/W6810738896","https://openalex.org/W6811013733","https://openalex.org/W6811340617","https://openalex.org/W6839091850","https://openalex.org/W6840192972","https://openalex.org/W6842542540","https://openalex.org/W6846181243","https://openalex.org/W6846560892","https://openalex.org/W6847076894","https://openalex.org/W6847671982","https://openalex.org/W6849177959","https://openalex.org/W6850011192","https://openalex.org/W6850015000","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6852060543","https://openalex.org/W6853450284","https://openalex.org/W6854003956","https://openalex.org/W6854866820","https://openalex.org/W6855425132"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2],"large":[3,19],"language":[4,73],"models,":[5],"which":[6],"enable":[7],"flexibility":[8],"through":[9],"instruction-driven":[10],"approaches,":[11],"has":[12],"revolutionized":[13],"many":[14],"traditional":[15],"generative":[16,43],"tasks,":[17,150],"but":[18],"models":[20,45,74],"for":[21,106],"3D":[22,28,53],"data,":[23],"particularly":[24],"in":[25],"comprehensively":[26],"handling":[27],"shapes":[29,89],"with":[30,103],"other":[31],"modalities,":[32],"are":[33],"still":[34],"under-explored.":[35],"By":[36],"achieving":[37],"instruction-based":[38,126],"shape":[39,44,91,98,102,121,154,157],"generation,":[40,127],"versatile":[41],"multi-modal":[42,67,107,123],"can":[46],"significantly":[47],"benefit":[48],"various":[49],"fields,":[50],"such":[51],"as":[52],"virtual":[54],"construction":[55],"and":[56,100,125,132,156],"network-aided":[57],"design.":[58],"In":[59],"this":[60,111],"article,":[61],"we":[62,114],"present":[63],"ShapeGPT,":[64],"a":[65,83,116],"shape-included":[66],"framework":[68,85],"to":[69,75,86,128],"leverage":[70],"strong":[71],"pre-trained":[72],"address":[76],"multiple":[77],"shape-relevant":[78,149],"tasks.":[79],"Specifically,":[80],"ShapeGPT":[81,144],"employs":[82],"\u201cword-sentence-paragraph\u201d":[84],"discretize":[87],"continuous":[88],"into":[90,97],"words,":[92],"further":[93],"assembles":[94],"these":[95,138],"words":[96],"sentences,":[99],"integrates":[101],"instructional":[104],"text":[105],"paragraphs.":[108],"To":[109],"learn":[110,133],"shape-language":[112,130],"model,":[113],"use":[115],"three-stage":[117],"training":[118],"scheme,":[119],"including":[120,151],"representation,":[122],"alignment,":[124],"align":[129],"codebooks":[131],"the":[134],"intricate":[135],"correlations":[136],"among":[137],"modalities.":[139],"Extensive":[140],"experiments":[141],"demonstrate":[142],"that":[143],"achieves":[145],"comparable":[146],"performance":[147],"across":[148],"text-to-shape,":[152],"shape-to-text,":[153],"completion,":[155],"editing.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":8}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}