{"id":"https://openalex.org/W4413145208","doi":"https://doi.org/10.1109/cvpr52734.2025.00552","title":"PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models","display_name":"PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145208","doi":"https://doi.org/10.1109/cvpr52734.2025.00552"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00552","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/A5100730800","display_name":"Minghao Chen","orcid":"https://orcid.org/0000-0001-8718-8541"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Minghao Chen","raw_affiliation_strings":["University of Oxford,Visual Geometry Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050994666","display_name":"\u0420\u043e\u043c\u0430\u043d \u0428\u0430\u043f\u043e\u0432\u0430\u043b\u043e\u0432","orcid":"https://orcid.org/0000-0002-3359-8649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roman Shapovalov","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062808708","display_name":"Iro Laina","orcid":"https://orcid.org/0000-0001-8857-7709"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iro Laina","raw_affiliation_strings":["University of Oxford,Visual Geometry Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075666099","display_name":"Tom Monnier","orcid":"https://orcid.org/0009-0008-1937-6506"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Monnier","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021424","display_name":"Jianyuan Wang","orcid":"https://orcid.org/0000-0002-6467-4018"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianyuan Wang","raw_affiliation_strings":["University of Oxford,Visual Geometry Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103131633","display_name":"David Novotn\u00fd","orcid":"https://orcid.org/0000-0002-9517-1464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Novotny","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060511349","display_name":"Andrea Vedaldi","orcid":"https://orcid.org/0000-0003-1374-2858"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrea Vedaldi","raw_affiliation_strings":["University of Oxford,Visual Geometry Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5881","last_page":"5892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9751999974250793,"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":0.9751999974250793,"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":0.9732999801635742,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9296000003814697,"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":0.6111775636672974},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6069774627685547},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07842123508453369},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.04941853880882263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6111775636672974},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6069774627685547},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07842123508453369},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.04941853880882263}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00552","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":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W4396696052"],"abstract_inverted_index":{"Text-":[0],"or":[1,62],"image-to-3D":[2],"generators":[3],"and":[4,15,29,82,111,167,176],"3D":[5,10,33,64,66,91,121,169,188],"scanners":[6],"can":[7,43],"now":[8],"produce":[9],"assets":[11,34],"with":[12],"high-quality":[13],"shapes":[14],"textures,":[16],"but":[17],"as":[18,186],"single,":[19],"fused":[20],"entities":[21],"lacking":[22],"meaningful":[23,40,70,96],"structure.":[24],"In":[25],"contrast,":[26],"most":[27],"applications":[28,184],"creative":[30],"workflows":[31],"require":[32],"to":[35,79,119],"be":[36,44],"composed":[37,68],"of":[38,69,89,138],"distinct,":[39],"parts":[41,131,156],"that":[42,128],"independently":[45],"manipulated.":[46],"To":[47],"bridge":[48],"this":[49],"gap,":[50],"we":[51],"introduce":[52],"PartGen,":[53],"a":[54,75,90,120],"novel":[55],"approach":[56],"for":[57,143],"generating,":[58],"from":[59,86],"text,":[60],"images,":[61],"unstructured":[63],"objects,":[65],"objects":[67],"parts.":[71],"Our":[72],"method":[73],"leverages":[74],"multi-view":[76,100],"diffusion":[77,101],"model":[78,102],"extract":[80],"plausible":[81],"view-consistent":[83],"part":[84,106,177,189],"segmentations":[85],"multiple":[87],"views":[88],"object,":[92,141],"dividing":[93],"it":[94],"into":[95],"components.":[97],"A":[98],"second":[99],"then":[103],"processes":[104],"each":[105],"individually,":[107],"filling":[108],"in":[109,150],"occlusions":[110,148],"generating":[112],"completed":[113],"views,":[114],"which":[115],"are":[116],"subsequently":[117],"passed":[118],"reconstruction":[122],"network.":[123],"The":[124],"completion":[125,178],"process":[126],"ensures":[127],"the":[129,136,139],"reconstructed":[130],"integrate":[132],"cohesively":[133],"by":[134,147],"considering":[135],"context":[137],"entire":[140],"compensating":[142],"missing":[144],"information":[145],"caused":[146],"and,":[149],"extreme":[151],"cases,":[152],"hallucinating":[153],"entirely":[154],"invisible":[155],"based":[157],"on":[158,164],"contextual":[159],"cues.":[160],"We":[161,180],"evaluate":[162],"PartGen":[163],"both":[165],"generated":[166],"real":[168],"assets,":[170],"demonstrating":[171],"significant":[172],"improvements":[173],"over":[174],"segmentation":[175],"baselines.":[179],"also":[181],"showcase":[182],"downstream":[183],"such":[185],"text-guided":[187],"editing.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}