{"id":"https://openalex.org/W4415707782","doi":"https://doi.org/10.1109/icme59968.2025.11209975","title":"NOVA3D: Normal Aligned Video Diffusion Model for Single Image to 3D Generation","display_name":"NOVA3D: Normal Aligned Video Diffusion Model for Single Image to 3D Generation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707782","doi":"https://doi.org/10.1109/icme59968.2025.11209975"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101908109","display_name":"Yuxiao Yang","orcid":"https://orcid.org/0000-0003-1387-8464"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiao Yang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101701450","display_name":"Peihao Li","orcid":"https://orcid.org/0000-0001-5722-0977"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peihao Li","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779798","display_name":"Yuhong Zhang","orcid":"https://orcid.org/0000-0003-0942-9068"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhong Zhang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086306667","display_name":"Junzhe Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhe Lu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022458011","display_name":"Xianglong He","orcid":"https://orcid.org/0000-0001-5368-0765"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianglong He","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108889598","display_name":"Minghan Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghan Qin","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435174","display_name":"Weitao Wang","orcid":"https://orcid.org/0000-0002-0024-3593"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weitao Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028229824","display_name":"Haoqian Wang","orcid":"https://orcid.org/0000-0003-2792-8469"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqian Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34047497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.8906000256538391,"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":0.8906000256538391,"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":0.029200000688433647,"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/T11448","display_name":"Face recognition and analysis","score":0.014600000344216824,"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/leverage","display_name":"Leverage (statistics)","score":0.7179999947547913},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5846999883651733},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5817000269889832},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5078999996185303},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.426800012588501},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.4097000062465668},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.3822000026702881},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3727000057697296},{"id":"https://openalex.org/keywords/image-texture","display_name":"Image texture","score":0.34599998593330383}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.728600025177002},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7179999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117000222206116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.704800009727478},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5846999883651733},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5817000269889832},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5078999996185303},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.4097000062465668},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.3822000026702881},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.34599998593330383},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C3018868555","wikidata":"https://www.wikidata.org/wiki/Q2918907","display_name":"Single camera","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.30880001187324524},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C200585589","wikidata":"https://www.wikidata.org/wiki/Q752176","display_name":"Texture mapping","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C207183524","wikidata":"https://www.wikidata.org/wiki/Q7708528","display_name":"Texture atlas","level":5,"score":0.2922999858856201},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2962785568","https://openalex.org/W4200150166","https://openalex.org/W4221151978","https://openalex.org/W4285102264","https://openalex.org/W4312933868","https://openalex.org/W4313153331","https://openalex.org/W4386065887","https://openalex.org/W4386071957","https://openalex.org/W4386075660","https://openalex.org/W4390873331","https://openalex.org/W4402733585","https://openalex.org/W4402951568","https://openalex.org/W4403770461","https://openalex.org/W4411726008"],"related_works":[],"abstract_inverted_index":{"3D":[0,14,26,38,63],"AI-generated":[1],"content":[2,15],"(AIGC)":[3],"has":[4],"made":[5],"it":[6],"increasingly":[7],"accessible":[8],"for":[9],"anyone":[10],"to":[11,24,41],"become":[12],"a":[13,66],"creator.":[16],"While":[17],"recent":[18],"methods":[19],"leverage":[20],"Score":[21],"Distillation":[22],"Sampling":[23],"distill":[25],"objects":[27],"from":[28,36,65],"pretrained":[29,67],"image":[30],"diffusion":[31,69],"models,":[32],"they":[33],"often":[34],"suffer":[35],"inadequate":[37],"priors,":[39],"leading":[40],"insufficient":[42],"multi-view":[43,76,100,116],"consistency.":[44,101],"In":[45],"this":[46],"work,":[47],"we":[48,88,103],"introduce":[49,104],"NOVA3D,":[50],"an":[51],"innovative":[52],"single-image-to-3D":[53],"generation":[54],"framework.":[55],"Our":[56],"key":[57],"insight":[58],"lies":[59],"in":[60,121],"leveraging":[61],"strong":[62],"priors":[64],"video":[68,77],"model":[70],"and":[71,85,99,118],"integrating":[72],"geometric":[73,86],"information":[74,81],"during":[75],"fine-tuning.":[78],"To":[79],"facilitate":[80],"exchange":[82],"between":[83],"color":[84],"domains,":[87],"propose":[89],"the":[90,105,127],"Geometry-Temporal":[91],"Alignment":[92],"(GTA)":[93],"attention":[94],"mechanism,":[95],"thereby":[96],"improving":[97],"generalization":[98],"Moreover,":[102],"deconflict":[106],"geometry":[107],"fusion":[108],"algorithm,":[109],"which":[110],"improves":[111],"texture":[112],"fidelity":[113],"by":[114],"addressing":[115],"inaccuracies":[117],"resolving":[119],"discrepancies":[120],"pose":[122],"alignment.":[123],"Extensive":[124],"experiments":[125],"validate":[126],"superiority":[128],"of":[129],"NOVA3D":[130],"over":[131],"existing":[132],"baselines.":[133]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}