{"id":"https://openalex.org/W4402754182","doi":"https://doi.org/10.1109/cvpr52733.2024.00676","title":"ConsistNet: Enforcing 3D Consistency for Multi-View Images Diffusion","display_name":"ConsistNet: Enforcing 3D Consistency for Multi-View Images Diffusion","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402754182","doi":"https://doi.org/10.1109/cvpr52733.2024.00676"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.00676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5100759136","display_name":"Jiayu Yang","orcid":"https://orcid.org/0000-0001-7475-1286"},"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":"Jiayu Yang","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101091631","display_name":"Ziang Cheng","orcid":null},"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":"Ziang Cheng","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104184391","display_name":"Yunfei Duan","orcid":null},"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":"Yunfei Duan","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063587709","display_name":"Pan Ji","orcid":"https://orcid.org/0000-0001-6213-554X"},"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":"Pan Ji","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101819061","display_name":"Hongdong Li","orcid":"https://orcid.org/0000-0003-4125-1554"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hongdong Li","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9057,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97257137,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7079","last_page":"7088"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9993000030517578,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9976000189781189,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.7324026823043823},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6887922883033752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6418365836143494},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3659617304801941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.332833468914032},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05718645453453064}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7324026823043823},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6887922883033752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6418365836143494},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3659617304801941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.332833468914032},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05718645453453064},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr52733.2024.00676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/733751312","is_oa":false,"landing_page_url":"https://hdl.handle.net/1885/733751312","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W2133665775","https://openalex.org/W2908510526","https://openalex.org/W2962785568","https://openalex.org/W3036167779","https://openalex.org/W3110257065","https://openalex.org/W3121370741","https://openalex.org/W3162926177","https://openalex.org/W3168867926","https://openalex.org/W3180808523","https://openalex.org/W4200150166","https://openalex.org/W4281485151","https://openalex.org/W4285102264","https://openalex.org/W4289785095","https://openalex.org/W4298185919","https://openalex.org/W4298187450","https://openalex.org/W4303440777","https://openalex.org/W4312933868","https://openalex.org/W4367000534","https://openalex.org/W4377864980","https://openalex.org/W4383180531","https://openalex.org/W4383994075","https://openalex.org/W4384261892","https://openalex.org/W4385483498","https://openalex.org/W4385490091","https://openalex.org/W4386071613","https://openalex.org/W4386071957","https://openalex.org/W4386072096","https://openalex.org/W4386075660","https://openalex.org/W4386075666","https://openalex.org/W4386076368","https://openalex.org/W4386273470","https://openalex.org/W4386395766","https://openalex.org/W4390873054","https://openalex.org/W4390873331","https://openalex.org/W4393148049","https://openalex.org/W6637373629","https://openalex.org/W6757817989","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6791386187","https://openalex.org/W6793108805","https://openalex.org/W6795288823","https://openalex.org/W6810240078","https://openalex.org/W6838639034","https://openalex.org/W6841755765","https://openalex.org/W6844305113","https://openalex.org/W6845281891","https://openalex.org/W6851229918","https://openalex.org/W6851972558","https://openalex.org/W6852614764","https://openalex.org/W6854266301","https://openalex.org/W6854377825","https://openalex.org/W6854463369","https://openalex.org/W6856304189","https://openalex.org/W6856545948"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Given":[0],"a":[1,5,11,50,88,105,161,178],"single":[2,179],"image":[3,131],"of":[4,21,84,171],"3D":[6,34,98,113,158],"object,":[7,24],"this":[8],"paper":[9],"proposes":[10],"novel":[12],"method":[13,48,155],"(named":[14],"ConsistNet)":[15],"that":[16,55,92,109,134,153],"can":[17,136,166],"generate":[18,167],"multiple":[19,39,60],"images":[20,41],"the":[22,33,66,76,172],"same":[23],"as":[25],"if":[26],"they":[27],"are":[28,42],"capturedfrom":[29],"different":[30],"viewpoints,":[31],"while":[32],"(multi-view)":[35],"consistencies":[36],"among":[37],"those":[38],"generated":[40],"effectively":[43,156],"exploited.":[44],"Central":[45],"to":[46,75,117,120],"our":[47,154],"is":[49,72],"lightweight":[51],"multi-view":[52,68,94,130],"consistency":[53,159],"block":[54],"enables":[56],"information":[57],"exchange":[58],"across":[59],"single-view":[61],"diffusion":[62,79],"processes":[63],"based":[64],"on":[65,177,188],"underlying":[67],"geometry":[69],"principles.":[70],"ConsistNet":[71],"an":[73],"extension":[74],"standard":[77],"latent":[78],"model":[80],"and":[81,100,103,111,165],"it":[82,135],"consists":[83],"two":[85],"submodules:":[86],"(a)":[87],"view":[89,119],"aggregation":[90,107],"module":[91,108],"unprojects":[93],"features":[95,115],"into":[96],"global":[97],"volumes":[99],"infers":[101],"consistency,":[102],"(b)":[104],"ray":[106],"samples":[110],"aggregates":[112],"consistent":[114],"back":[116],"each":[118],"enforce":[121],"consistency.":[122],"Our":[123,182],"approach":[124],"departs":[125],"from":[126],"previous":[127],"methods":[128],"in":[129,133,140],"generation,":[132],"be":[137,185],"easily":[138],"dropped":[139],"pretrained":[141],"LDMs":[142],"without":[143],"requiring":[144],"explicit":[145],"pixel":[146],"correspondences":[147],"or":[148],"depth":[149],"prediction.":[150],"Experiments":[151],"show":[152],"learns":[157],"over":[160],"frozen":[162],"Zero123-XL":[163],"backbone":[164],"16":[168],"surrounding":[169],"views":[170],"object":[173],"within":[174],"11":[175],"seconds":[176],"A100":[180],"GPU.":[181],"code":[183],"will":[184],"made":[186],"available":[187],"https://github.com/JiayuYANG/ConsistNet.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
