{"id":"https://openalex.org/W4417231741","doi":"https://doi.org/10.1109/iccv51701.2025.00625","title":"Geometrycrafter: Consistent Geometry Estimation for Open-World Videos With Diffusion Priors","display_name":"Geometrycrafter: Consistent Geometry Estimation for Open-World Videos With Diffusion Priors","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417231741","doi":"https://doi.org/10.1109/iccv51701.2025.00625"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.01016","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058414523","display_name":"Tian-Xing Xu","orcid":"https://orcid.org/0000-0002-9433-1980"},"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":"Tian-Xing Xu","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/A5102890606","display_name":"Xiangjun Gao","orcid":"https://orcid.org/0009-0003-6177-4413"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiangjun Gao","raw_affiliation_strings":["HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011995971","display_name":"Wenbo Hu","orcid":"https://orcid.org/0000-0002-8482-9400"},"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":"Wenbo Hu","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449145","display_name":"Xiaoyu Li","orcid":"https://orcid.org/0000-0002-1141-735X"},"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":"Xiaoyu Li","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049883689","display_name":"Song\u2013Hai Zhang","orcid":"https://orcid.org/0000-0003-0460-1586"},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song-Hai Zhang","raw_affiliation_strings":["Qinghai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qinghai University","institution_ids":["https://openalex.org/I116265982"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"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":"Ying Shan","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.8967000246047974,"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":0.8967000246047974,"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":0.027000000700354576,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.01360000018030405,"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/generalization","display_name":"Generalization","score":0.6700000166893005},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5874000191688538},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5735999941825867},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4916999936103821},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.47769999504089355},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4632999897003174},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4494999945163727},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4147999882698059},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.35269999504089355}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6700000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6528000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5963000059127808},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5874000191688538},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5819000005722046},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5735999941825867},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.47769999504089355},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41449999809265137},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3303999900817871},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3276999890804291},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C55128770","wikidata":"https://www.wikidata.org/wiki/Q5275440","display_name":"Diffusion map","level":4,"score":0.29170000553131104},{"id":"https://openalex.org/C118317068","wikidata":"https://www.wikidata.org/wiki/Q2100760","display_name":"Point distribution model","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C88871306","wikidata":"https://www.wikidata.org/wiki/Q7208287","display_name":"Point process","level":2,"score":0.26010000705718994}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.01016","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.01016","pdf_url":"https://arxiv.org/pdf/2504.01016","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.01016","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.01016","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.01016","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.01016","pdf_url":"https://arxiv.org/pdf/2504.01016","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6809841984","display_name":null,"funder_award_id":"62495061,62361146854","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"remarkable":[1],"advancements":[2],"in":[3,12,23],"video":[4,80,96],"depth":[5],"estimation,":[6,55],"existing":[7],"methods":[8],"exhibit":[9],"inherent":[10],"limitations":[11],"achieving":[13],"geometric":[14],"fidelity":[15],"through":[16],"the":[17,61,91,101,109],"affine-invariant":[18],"predictions,":[19],"limiting":[20],"their":[21],"applicability":[22],"reconstruction":[24],"and":[25,56,88,126],"other":[26,57],"metrically":[27],"grounded":[28],"downstream":[29],"tasks.":[30],"We":[31],"propose":[32],"GeometryCrafter,":[33],"a":[34,67,75,95],"novel":[35],"framework":[36],"that":[37,73,118],"recovers":[38],"high-fidelity":[39],"point":[40,68,85,104],"map":[41,69,86,105],"sequences":[42,106],"with":[43],"temporal":[44,124],"coherence":[45],"from":[46],"open-world":[47],"videos,":[48],"enabling":[49],"accurate":[50],"3D/4D":[51],"reconstruction,":[52],"camera":[53],"parameter":[54],"depth-based":[58],"applications.":[59],"At":[60],"core":[62],"of":[63,103],"our":[64],"approach":[65],"lies":[66],"Variational":[70],"Autoencoder":[71],"(VAE)":[72],"learns":[74],"latent":[76,81],"space":[77],"agnostic":[78],"to":[79,99],"distributions":[82],"for":[83],"effective":[84],"encoding":[87],"decoding.":[89],"Leveraging":[90],"VAE,":[92],"we":[93],"train":[94],"diffusion":[97],"model":[98,100],"distribution":[102],"conditioned":[107],"on":[108,114],"input":[110],"videos.":[111],"Extensive":[112],"evaluations":[113],"diverse":[115],"datasets":[116],"demonstrate":[117],"GeometryCrafter":[119],"achieves":[120],"state-of-the-art":[121],"3D":[122],"accuracy,":[123],"consistency,":[125],"generalization":[127],"capability.":[128]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}