{"id":"https://openalex.org/W7117470873","doi":"https://doi.org/10.1109/dicta68720.2025.11302454","title":"Consistent3D: Diffusion-Driven Sparse View Completion and 3D Reconstruction with Geometric Priors","display_name":"Consistent3D: Diffusion-Driven Sparse View Completion and 3D Reconstruction with Geometric Priors","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7117470873","doi":"https://doi.org/10.1109/dicta68720.2025.11302454"},"language":null,"primary_location":{"id":"doi:10.1109/dicta68720.2025.11302454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","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/A5121452840","display_name":"Qi Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Tan","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121495495","display_name":"Rong Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Wei","raw_affiliation_strings":["Academy for Advanced Interdisciplinary Studies, Peking University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Academy for Advanced Interdisciplinary Studies, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069287187","display_name":"Zhiyu Xi","orcid":"https://orcid.org/0000-0003-0258-0486"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Xi","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057685126","display_name":"Jingqing Yang","orcid":"https://orcid.org/0000-0002-7507-6929"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqing Yang","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5121452840"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.659464,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.6876999735832214,"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":0.6876999735832214,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.17640000581741333,"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":0.03200000151991844,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-hull","display_name":"Visual hull","score":0.694599986076355},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6209999918937683},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6060000061988831},{"id":"https://openalex.org/keywords/reprojection-error","display_name":"Reprojection error","score":0.5667999982833862},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5623999834060669},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5432999730110168},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.5062999725341797},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.46860000491142273},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4359000027179718}],"concepts":[{"id":"https://openalex.org/C2776863239","wikidata":"https://www.wikidata.org/wiki/Q7936601","display_name":"Visual hull","level":3,"score":0.694599986076355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6638000011444092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6226000189781189},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6209999918937683},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6060000061988831},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5784000158309937},{"id":"https://openalex.org/C23903533","wikidata":"https://www.wikidata.org/wiki/Q17122739","display_name":"Reprojection error","level":3,"score":0.5667999982833862},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5623999834060669},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.41999998688697815},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.37040001153945923},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3416000008583069},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3375000059604645},{"id":"https://openalex.org/C141297171","wikidata":"https://www.wikidata.org/wiki/Q1143237","display_name":"Octree","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C20885615","wikidata":"https://www.wikidata.org/wiki/Q825595","display_name":"Surface reconstruction","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29670000076293945},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C193581530","wikidata":"https://www.wikidata.org/wiki/Q683778","display_name":"Structured light","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dicta68720.2025.11302454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","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":39,"referenced_works":["https://openalex.org/W2034392969","https://openalex.org/W2105303354","https://openalex.org/W2519683295","https://openalex.org/W3215769467","https://openalex.org/W3216476011","https://openalex.org/W4200150166","https://openalex.org/W4206760982","https://openalex.org/W4312933868","https://openalex.org/W4312969460","https://openalex.org/W4367359398","https://openalex.org/W4385318467","https://openalex.org/W4386065784","https://openalex.org/W4386066388","https://openalex.org/W4386075859","https://openalex.org/W4390872170","https://openalex.org/W4390872336","https://openalex.org/W4390873101","https://openalex.org/W4390873331","https://openalex.org/W4390873915","https://openalex.org/W4390874099","https://openalex.org/W4390889720","https://openalex.org/W4402667896","https://openalex.org/W4402727359","https://openalex.org/W4402727792","https://openalex.org/W4402733576","https://openalex.org/W4402753888","https://openalex.org/W4402754045","https://openalex.org/W4402775760","https://openalex.org/W4402816534","https://openalex.org/W4403069195","https://openalex.org/W4404612590","https://openalex.org/W4404970983","https://openalex.org/W4411726008","https://openalex.org/W4413145529","https://openalex.org/W4413145795","https://openalex.org/W4413146238","https://openalex.org/W4414432428","https://openalex.org/W4415796308","https://openalex.org/W4415798746"],"related_works":[],"abstract_inverted_index":{"We":[0,117],"present":[1],"Consistent3D,":[2],"a":[3,43,81,93,120,147,176],"training-free":[4],"framework":[5,210],"for":[6,24],"high-fidelity":[7,196],"3D":[8,25,56,130,149,168,231],"reconstruction":[9,201],"from":[10,52,202],"sparse":[11,53,103,203],"views,":[12,134],"leveraging":[13],"point-cloud-guided":[14,171],"video":[15,61,172],"diffusion":[16,62,173,217],"model":[17,174,207],"to":[18,58,74,101],"generate":[19],"geometrically":[20,66,76,226],"consistent":[21,77,227],"novel":[22,38,70],"views":[23,139],"Gaussian":[26,150],"Splatting.":[27],"To":[28],"address":[29],"the":[30,49,60,102,109,213,220],"severe":[31],"multi-view":[32],"inconsistency":[33],"commonly":[34],"observed":[35],"in":[36,113],"diffusion-based":[37],"view":[39,71],"synthesis,":[40],"we":[41,47,79],"introduce":[42,80],"geometry-guided":[44],"pipeline.":[45],"Specifically,":[46],"leverage":[48],"point":[50,105],"cloud-estimated":[51],"input":[54,104],"images-as":[55],"priors":[57],"guide":[59],"process,":[63],"enabling":[64],"both":[65],"plausible":[67],"and":[68,129,163,175,191,197,228],"frame-consistent":[69],"synthesis.":[72],"Furthermore,":[73],"achieve":[75],"depth,":[78],"Local":[82],"Depth":[83],"Alignment":[84],"(LDA)":[85],"strategy":[86,97],"that":[87,124],"adjusts":[88],"monocular":[89,114],"depth":[90,115,131,164,182],"estimates":[91],"into":[92,146],"scale-aware":[94],"representation.":[95],"This":[96],"is":[98],"performed":[99],"relative":[100],"cloud":[106],"prior,":[107],"resolving":[108],"inherent":[110],"scale":[111],"ambiguity":[112],"prediction.":[116],"then":[118],"propose":[119],"consistency":[121,169],"evaluation":[122],"module":[123],"computes":[125],"2D":[126],"reprojection":[127],"error":[128],"discrepancy":[132],"across":[133],"yielding":[135],"confidence":[136,142,184],"scores.":[137],"These":[138],"with":[140,219],"high":[141],"scores":[143],"are":[144,158],"fused":[145],"regularized":[148],"Splatting":[151],"(3DGS)":[152],"pipeline,":[153],"where":[154],"parameters":[155],"of":[156,216,223],"Gaussians":[157],"optimized":[159],"under":[160],"confidenceweighted":[161],"RGB":[162],"constraints.":[165],"By":[166],"enforcing":[167],"through":[170],"comprehensive":[177],"confidence-weighted":[178],"3DGS":[179,200],"optimization-which":[180],"integrates":[181],"alignment,":[183],"prediction,":[185],"incremental":[186],"fusion,":[187],"soft":[188],"constraint":[189],"optimization,":[190],"real-time":[192],"visual":[193],"refinement-Consistent3D":[194],"achieves":[195],"visually":[198,229],"smooth":[199],"observations":[204],"without":[205],"requiring":[206],"training.":[208],"Our":[209],"effectively":[211],"bridges":[212],"generative":[214],"power":[215],"models":[218],"representational":[221],"efficiency":[222],"3DGS,":[224],"delivering":[225],"compelling":[230],"scenes.":[232]},"counts_by_year":[],"updated_date":"2025-12-30T23:08:21.542490","created_date":"2025-12-29T00:00:00"}