{"id":"https://openalex.org/W4413147533","doi":"https://doi.org/10.1109/cvpr52734.2025.00759","title":"MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation","display_name":"MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147533","doi":"https://doi.org/10.1109/cvpr52734.2025.00759"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5067569032","display_name":"S. N. Sinha","orcid":"https://orcid.org/0009-0009-6820-3633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sankalp Sinha","raw_affiliation_strings":["DFKI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000341735","display_name":"Mohammad Sadil Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Sadil Khan","raw_affiliation_strings":["DFKI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086703267","display_name":"Muhammad Usama","orcid":"https://orcid.org/0000-0001-5015-8605"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhammad Usama","raw_affiliation_strings":["DFKI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108406043","display_name":"S. Dilip Sam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shino Sam","raw_affiliation_strings":["DFKI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051650277","display_name":"Didier Stricker","orcid":"https://orcid.org/0009-0004-8794-6858"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Didier Stricker","raw_affiliation_strings":["DFKI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001411256","display_name":"Sk Aziz Ali","orcid":"https://orcid.org/0000-0002-6396-8436"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sk Aziz Ali","raw_affiliation_strings":["DFKI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086894159","display_name":"Muhammad Zeshan Afzal","orcid":"https://orcid.org/0000-0002-0536-6867"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhammad Zeshan Afzal","raw_affiliation_strings":["DFKI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.24847203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8105","last_page":"8116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9241999983787537,"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":0.9241999983787537,"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":0.9175999760627747,"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/elaboration","display_name":"Elaboration","score":0.9404071569442749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6774045825004578},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5625273585319519},{"id":"https://openalex.org/keywords/content-creation","display_name":"Content creation","score":0.4708673059940338},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4013158679008484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3676484525203705},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32487553358078003},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.28208670020103455},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.11029687523841858},{"id":"https://openalex.org/keywords/humanities","display_name":"Humanities","score":0.059810519218444824},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05753287672996521}],"concepts":[{"id":"https://openalex.org/C2779192218","wikidata":"https://www.wikidata.org/wiki/Q16944486","display_name":"Elaboration","level":2,"score":0.9404071569442749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6774045825004578},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5625273585319519},{"id":"https://openalex.org/C2776509796","wikidata":"https://www.wikidata.org/wiki/Q5276056","display_name":"Content creation","level":2,"score":0.4708673059940338},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4013158679008484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3676484525203705},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32487553358078003},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.28208670020103455},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.11029687523841858},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.059810519218444824},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05753287672996521},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2360463189","https://openalex.org/W2243483294","https://openalex.org/W2737431228","https://openalex.org/W4404990334","https://openalex.org/W4400441967","https://openalex.org/W4390017791","https://openalex.org/W223854805","https://openalex.org/W4408552758","https://openalex.org/W4401545295","https://openalex.org/W4404990619"],"abstract_inverted_index":{"Generating":[0],"high-fidelity":[1],"3D":[2,45,51,90,141],"content":[3],"from":[4,48,75,100],"text":[5,39],"prompts":[6],"remains":[7],"a":[8,56,122,135],"significant":[9],"challenge":[10],"in":[11,111,155],"computer":[12],"vision":[13],"due":[14],"to":[15,69,79,107,139],"the":[16,24],"limited":[17],"size,":[18],"diversity,":[19,160],"and":[20,67,92,114,133,158,168],"annotation":[21,59,105,113,156],"depth":[22],"of":[23,164],"existing":[25,153],"datasets.":[26,52],"To":[27],"address":[28],"this,":[29],"we":[30,96,119],"introduce":[31],"MARVEL-40M+,":[32],"an":[33],"extensive":[34],"dataset":[35],"with":[36,130],"40":[37],"million":[38,44],"annotations":[40,132],"for":[41],"over":[42],"8.9":[43],"assets":[46],"aggregated":[47],"seven":[49],"major":[50],"Our":[53],"contribution":[54],"is":[55,175],"novel":[57],"multi-stage":[58],"pipeline":[60,106],"that":[61,149],"integrates":[62],"open-source":[63],"pretrained":[64,136],"multi-view":[65],"VLMs":[66],"LLMs":[68],"automatically":[70],"produce":[71],"multi-level":[72],"descriptions,":[73],"ranging":[74],"detailed":[76],"(150-200":[77],"words)":[78],"concise":[80],"semantic":[81],"tags":[82],"(10-20":[83],"words).":[84],"This":[85],"structure":[86],"supports":[87],"both":[88],"fine-grained":[89],"reconstruction":[91],"rapid":[93],"prototyping.":[94],"Furthermore,":[95],"incorporate":[97],"human":[98,171],"metadata":[99],"source":[101],"datasets":[102,154],"into":[103],"our":[104,112,131],"add":[108],"domain-specific":[109],"information":[110],"reduce":[115],"VLM":[116],"hallucinations.":[117],"Additionally,":[118],"develop":[120],"MARVEL-FX3D,":[121],"two-stage":[123],"text-to-3D":[124],"pipeline.":[125],"We":[126],"fine-tune":[127],"Stable":[128],"Diffusion":[129],"use":[134],"image-to-3D":[137],"network":[138],"generate":[140],"textured":[142],"meshes":[143],"within":[144],"15s.":[145],"Extensive":[146],"evaluations":[147],"show":[148],"MARVEL-40M+":[150],"significantly":[151],"outperforms":[152],"quality":[157],"linguistic":[159],"achieving":[161],"win":[162],"rates":[163],"72.41%":[165],"by":[166,170],"GPT-4":[167],"73.40%":[169],"evaluators.":[172],"Project":[173],"page":[174],"available":[176],"at":[177],"https://sankalpsinha-cmos.github.io/MARVEL/.":[178]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
