{"id":"https://openalex.org/W4387635239","doi":"https://doi.org/10.48550/arxiv.2310.08092","title":"Consistent123: Improve Consistency for One Image to 3D Object Synthesis","display_name":"Consistent123: Improve Consistency for One Image to 3D Object Synthesis","publication_year":2023,"publication_date":"2023-10-12","ids":{"openalex":"https://openalex.org/W4387635239","doi":"https://doi.org/10.48550/arxiv.2310.08092"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.08092","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08092","pdf_url":"https://arxiv.org/pdf/2310.08092","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.08092","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007678458","display_name":"Haohan Weng","orcid":"https://orcid.org/0000-0003-4954-4546","observed_orcids":["https://orcid.org/0000-0003-4954-4546"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weng, Haohan","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087641779","display_name":"Tianyu Yang","orcid":"https://orcid.org/0000-0002-9674-5220","observed_orcids":["https://orcid.org/0000-0002-9674-5220"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Tianyu","raw_affiliation_strings":["International Digital Economy Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458008","display_name":"Jianan Wang","orcid":"https://orcid.org/0000-0003-4161-1687","observed_orcids":["https://orcid.org/0000-0003-4161-1687"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jianan","raw_affiliation_strings":["International Digital Economy Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345915","display_name":"Yu Li","orcid":"https://orcid.org/0000-0003-1865-8276","observed_orcids":["https://orcid.org/0000-0003-1865-8276"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yu","raw_affiliation_strings":["International Digital Economy Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Tong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Tong","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643265","display_name":"C. L. Philip Chen","orcid":"https://orcid.org/0000-0001-5451-7230","observed_orcids":["https://orcid.org/0000-0001-5451-7230","https://orcid.org/0000-0002-2158-7969","https://orcid.org/0009-0009-1588-3460"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, C. L. Philip","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029338358","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0001-5879-514X","observed_orcids":["https://orcid.org/0000-0001-5879-514X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lei","raw_affiliation_strings":["International Digital Economy Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy","institution_ids":[]}]}],"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":true,"cited_by_count":83,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9843999743461609,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9843999743461609,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.015200000256299973,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":9.999999747378752e-05,"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/view-consistency","display_name":"view consistency","score":0.8080000281333923},{"id":"https://openalex.org/keywords/image-diffusion-models","display_name":"image diffusion models","score":0.796999990940094},{"id":"https://openalex.org/keywords/novel-view-synthesis","display_name":"novel view synthesis","score":0.8840000033378601},{"id":"https://openalex.org/keywords/cross-view-attention","display_name":"cross-view attention","score":0.972000002861023},{"id":"https://openalex.org/keywords/classifier-free-guidance","display_name":"classifier-free guidance","score":0.8539999723434448},{"id":"https://openalex.org/keywords/3d-object-generation","display_name":"3D object generation","score":0.7620000243186951},{"id":"https://openalex.org/keywords/image-to-image-translation","display_name":"image-to-image translation","score":0.7820000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7844022512435913},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7377060651779175},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5957449674606323},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.5754894614219666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5082680583000183},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5080950260162354},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5037674307823181},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.464141309261322},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4542364478111267},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44490060210227966},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41736263036727905},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.324604332447052},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2767714858055115},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.1624217927455902},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.08092","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08092","pdf_url":"https://arxiv.org/pdf/2310.08092","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.08092","doi":"https://doi.org/10.48550/arxiv.2310.08092","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.08092","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.08092","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08092","pdf_url":"https://arxiv.org/pdf/2310.08092","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387635239.pdf","grobid_xml":"https://content.openalex.org/works/W4387635239.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2908510526","https://openalex.org/W3154159596","https://openalex.org/W3173522942","https://openalex.org/W3215926197","https://openalex.org/W4280645263","https://openalex.org/W4288099666","https://openalex.org/W4312045746","https://openalex.org/W4312796674","https://openalex.org/W7133204056","https://openalex.org/W7133220370"],"related_works":["https://openalex.org/W4399574601","https://openalex.org/W4320539074","https://openalex.org/W4416172869","https://openalex.org/W4402754182","https://openalex.org/W7134583938","https://openalex.org/W4404970983","https://openalex.org/W4413513701","https://openalex.org/W4400381527","https://openalex.org/W4396813792","https://openalex.org/W4312594784"],"abstract_inverted_index":{"Large":[0],"image":[1],"diffusion":[2],"models":[3,17],"enable":[4],"novel":[5,48,83],"view":[6,26,81,135],"synthesis":[7],"with":[8],"high":[9],"quality":[10],"and":[11,37,57,82,119,126],"excellent":[12],"zero-shot":[13],"capability.":[14],"However,":[15],"such":[16,89],"based":[18],"on":[19,149],"image-to-image":[20],"translation":[21],"have":[22],"no":[23],"guarantee":[24],"of":[25,97,147],"consistency,":[27,42],"limiting":[28],"the":[29,58,67,76,79,86,115,158],"performance":[30],"for":[31,121],"downstream":[32,151],"tasks":[33],"like":[34],"3D":[35,159],"reconstruction":[36],"image-to-3D":[38],"generation.":[39],"To":[40],"empower":[41],"we":[43,142],"propose":[44],"Consistent123":[45,131,148],"to":[46,113],"synthesize":[47],"views":[49,98],"simultaneously":[50,92],"by":[51,137],"incorporating":[52],"additional":[53],"cross-view":[54],"attention":[55,64],"layers":[56],"shared":[59],"self-attention":[60],"mechanism.":[61],"The":[62,162],"proposed":[63],"mechanism":[65],"improves":[66],"interaction":[68],"across":[69],"all":[70],"synthesized":[71,122],"views,":[72],"as":[73,75],"well":[74],"alignment":[77],"between":[78,117],"condition":[80],"views.":[84,124],"In":[85],"sampling":[87],"stage,":[88],"architecture":[90],"supports":[91],"generating":[93],"an":[94],"arbitrary":[95],"number":[96],"while":[99],"training":[100],"at":[101,167],"a":[102,108,138,144],"fixed":[103],"length.":[104],"We":[105],"also":[106],"introduce":[107],"progressive":[109],"classifier-free":[110],"guidance":[111],"strategy":[112],"achieve":[114],"trade-off":[116],"texture":[118],"geometry":[120],"object":[123],"Qualitative":[125],"quantitative":[127],"experiments":[128],"show":[129],"that":[130],"outperforms":[132],"baselines":[133],"in":[134,157],"consistency":[136],"large":[139],"margin.":[140],"Furthermore,":[141],"demonstrate":[143],"significant":[145],"improvement":[146],"varying":[150],"tasks,":[152],"showing":[153],"its":[154],"great":[155],"potential":[156],"generation":[160],"field.":[161],"project":[163],"page":[164],"is":[165],"available":[166],"consistent-123.github.io.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-10-14T00:00:00"}