{"id":"https://openalex.org/W4406857339","doi":"https://doi.org/10.1109/tmm.2025.3535325","title":"Learning Shape-Color Diffusion Priors for Text-Guided 3D Object Generation","display_name":"Learning Shape-Color Diffusion Priors for Text-Guided 3D Object Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406857339","doi":"https://doi.org/10.1109/tmm.2025.3535325"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535325","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/A5107555183","display_name":"Sheng-Yu Huang","orcid":"https://orcid.org/0000-0002-3149-9620"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sheng-Yu Huang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-3149-9620","affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104259508","display_name":"Chi-Pin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Pin Huang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"raw_orcid":"https://orcid.org/0009-0003-7738-3054","affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101827449","display_name":"Kai-Po Chang","orcid":"https://orcid.org/0009-0008-5182-2019"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai-Po Chang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"raw_orcid":"https://orcid.org/0009-0008-5182-2019","affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113395518","display_name":"Zi-Ting Chou","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Zi-Ting Chou","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111224541","display_name":"I-Jieh Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"I-Jieh Liu","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"raw_orcid":"https://orcid.org/0009-0007-0155-6608","affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090045508","display_name":"Yu-Chiang Frank Wang","orcid":"https://orcid.org/0000-0002-2333-157X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Chiang Frank Wang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-2333-157X","affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01160692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"3294","last_page":"3306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9660999774932861,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9660999774932861,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9621000289916992,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9552000164985657,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.826351523399353},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6267151236534119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.622454822063446},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5236577391624451},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4956003427505493},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39748406410217285},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.32043325901031494},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.19350281357765198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826351523399353},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6267151236534119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.622454822063446},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5236577391624451},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4956003427505493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39748406410217285},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32043325901031494},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.19350281357765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3535325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535325","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1569530544","https://openalex.org/W2016589492","https://openalex.org/W2211722331","https://openalex.org/W2251329024","https://openalex.org/W2560609797","https://openalex.org/W2752796333","https://openalex.org/W2760103357","https://openalex.org/W2886499109","https://openalex.org/W2896457183","https://openalex.org/W2962770929","https://openalex.org/W2963627347","https://openalex.org/W2963926543","https://openalex.org/W2964078384","https://openalex.org/W2979750740","https://openalex.org/W2985683375","https://openalex.org/W3021962567","https://openalex.org/W3091123787","https://openalex.org/W3097606102","https://openalex.org/W3109585842","https://openalex.org/W3192240783","https://openalex.org/W3199693760","https://openalex.org/W3203898101","https://openalex.org/W3216352822","https://openalex.org/W4221151978","https://openalex.org/W4239863109","https://openalex.org/W4312500989","https://openalex.org/W4312638666","https://openalex.org/W4312784800","https://openalex.org/W4312910764","https://openalex.org/W4312933868","https://openalex.org/W4323022503","https://openalex.org/W4382457527","https://openalex.org/W4385245566","https://openalex.org/W4386065887","https://openalex.org/W4386071840","https://openalex.org/W4386076002","https://openalex.org/W4386083014","https://openalex.org/W4386973810","https://openalex.org/W4388191573","https://openalex.org/W4389494893","https://openalex.org/W4390871705","https://openalex.org/W4391019999","https://openalex.org/W4404782964","https://openalex.org/W6631190155","https://openalex.org/W6687484953","https://openalex.org/W6739778489","https://openalex.org/W6741832134","https://openalex.org/W6755234996","https://openalex.org/W6761551260","https://openalex.org/W6765779288","https://openalex.org/W6766978945","https://openalex.org/W6779823529","https://openalex.org/W6791353385","https://openalex.org/W6811340617","https://openalex.org/W6838639034","https://openalex.org/W6840192972","https://openalex.org/W6843813467","https://openalex.org/W6846176957","https://openalex.org/W6847671982","https://openalex.org/W6850625674","https://openalex.org/W6856304189"],"related_works":["https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W2580650124","https://openalex.org/W3122088529","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W2085259108","https://openalex.org/W3123087812","https://openalex.org/W2071416974"],"abstract_inverted_index":{"Generating":[0],"3D":[1,39,117,123,129,256],"shapes":[2],"according":[3],"to":[4,20,31,56,65,96,120,168,199,210],"specific":[5],"textual":[6],"input":[7,142,171],"is":[8,94],"a":[9,44,86,107,111,115,163,174,178,229],"crucial":[10],"topic":[11],"in":[12,102,273],"the":[13,21,32,103,137,141,145,148,153,170,200,212,224,237,250,269],"multimedia":[14,274],"application,":[15],"with":[16],"its":[17],"potential":[18],"enhancement":[19],"VR/AR/XR":[22],"usage":[23],"that":[24,187],"enables":[25],"more":[26],"diverse":[27],"virtual":[28],"scenes.":[29],"Due":[30,198],"recent":[33],"success":[34],"of":[35,46,202,214,241,252,275],"diffusion":[36,131],"models,":[37],"text-guided":[38],"object":[40,83,118,216,257],"generation":[41,258],"has":[42],"drawn":[43],"lot":[45],"attention":[47],"recently.":[48],"However,":[49],"current":[50],"latent":[51,109,113,130,139],"diffusion-based":[52],"methods":[53],"are":[54,208],"restricted":[55],"shape-only":[57],"generation,":[58],"requiring":[59],"time-consuming":[60],"and":[61,99,105,110,144,177,204,234,239,259,271],"computationally":[62],"expensive":[63],"post-processing":[64],"obtain":[66],"colored":[67,81,122],"objects.":[68,124],"In":[69],"this":[70],"paper,":[71],"we":[72,160,207,248],"propose":[73],"an":[74,182,215,246],"end-to-endShape-Color":[75],"Diffusion":[76],"Prior":[77],"framework":[78],"(SCDiff)to":[79],"achieve":[80],"text-to-3D":[82],"generation.":[84],"Given":[85],"general":[87],"text":[88,104,143,172],"description":[89],"as":[90],"input,":[91],"our":[92,188,242,253,276],"SCDiff":[93,126,254],"able":[95,209],"distinguish":[97],"shape":[98,108,138,175,203],"color-related":[100],"priors":[101],"generate":[106],"color":[112,149,179,205,213,220],"for":[114],"pre-trained":[116],"auto-encoder":[119],"derive":[121],"Our":[125],"contains":[127],"two":[128,154],"models":[132],"(LDM),":[133],"where":[134],"one":[135],"generates":[136,147],"from":[140],"other":[146],"latent.":[150],"To":[151],"help":[152],"LDMs":[155],"focus":[156],"on":[157,228,255,262],"shape/color-related":[158],"information,":[159],"further":[161,267],"adopt":[162],"Large":[164],"Language":[165],"Model":[166],"(LLM)":[167],"separate":[169],"into":[173],"phrase":[176,180],"via":[181],"in-context":[183],"learning":[184],"technique":[185],"so":[186],"shape/color":[189],"LDM":[190],"would":[191,232],"not":[192],"be":[193],"influenced":[194],"by":[195,217],"irrelevant":[196],"information.":[197],"separation":[201],"latent,":[206],"manipulate":[211],"giving":[218],"different":[219],"phrases":[221],"while":[222],"maintaining":[223],"original":[225],"shape.":[226],"Experiments":[227],"benchmark":[230],"dataset":[231],"quantitatively":[233],"qualitatively":[235],"verify":[236],"effectiveness":[238],"practicality":[240],"proposed":[243,277],"model.":[244],"As":[245],"extension,":[247],"show":[249],"capability":[251],"manipulation":[260],"based":[261],"various":[263],"modality":[264],"conditions,":[265],"which":[266],"confirms":[268],"scalability":[270],"applications":[272],"framework.":[278]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}