{"id":"https://openalex.org/W4417300228","doi":"https://doi.org/10.1109/iccv51701.2025.02580","title":"SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations","display_name":"SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417300228","doi":"https://doi.org/10.1109/iccv51701.2025.02580"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02580","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/2505.11992","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059916557","display_name":"Songchun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songchun Zhang","raw_affiliation_strings":["ZJU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108722567","display_name":"Huiyao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huiyao Xu","raw_affiliation_strings":["ZJU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020373369","display_name":"Guo Sitong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sitong Guo","raw_affiliation_strings":["ZJU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038310950","display_name":"Zhongwei Xie","orcid":"https://orcid.org/0009-0008-7503-7488"},"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":"Zhongwei Xie","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/A5059021869","display_name":"Hujun Bao","orcid":"https://orcid.org/0000-0002-2662-0334"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hujun Bao","raw_affiliation_strings":["ZJU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101844050","display_name":"Weiwei Xu","orcid":"https://orcid.org/0000-0003-3756-3539"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiwei Xu","raw_affiliation_strings":["ZJU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100604564","display_name":"Changqing Zou","orcid":"https://orcid.org/0000-0001-8264-6849"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changqing Zou","raw_affiliation_strings":["ZJU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46142047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27794","last_page":"27805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.6412000060081482,"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":0.6412000060081482,"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":0.1518000066280365,"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":0.09989999979734421,"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/epipolar-geometry","display_name":"Epipolar geometry","score":0.8755999803543091},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5630999803543091},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5213000178337097},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.5142999887466431},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.49239999055862427},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.49050000309944153},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4115000069141388},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.40049999952316284}],"concepts":[{"id":"https://openalex.org/C23379248","wikidata":"https://www.wikidata.org/wiki/Q200904","display_name":"Epipolar geometry","level":3,"score":0.8755999803543091},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7433000206947327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7318000197410583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.73089998960495},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5213000178337097},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.5142999887466431},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.49050000309944153},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4115000069141388},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.29179999232292175},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02580","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:2505.11992","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11992","pdf_url":"https://arxiv.org/pdf/2505.11992","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,"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.2505.11992","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.11992","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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.11992","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11992","pdf_url":"https://arxiv.org/pdf/2505.11992","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,"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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Novel":[0],"view":[1,137],"synthesis":[2],"(NVS)":[3],"boosts":[4],"immersive":[5],"experiences":[6],"in":[7,50,108],"computer":[8],"vision":[9],"and":[10,68,82,120,139],"graphics.":[11],"Existing":[12],"techniques,":[13],"though":[14],"progressed,":[15],"rely":[16],"on":[17,27],"dense":[18],"multi-view":[19],"observations,":[20,58],"restricting":[21],"their":[22],"application.":[23],"This":[24],"work":[25],"takes":[26],"the":[28,47,109,141],"challenge":[29],"of":[30,144],"reconstructing":[31],"photorealistic":[32],"3D":[33,83,117,145],"scenes":[34],"from":[35],"sparse":[36,136],"or":[37],"single-view":[38],"inputs.":[39],"We":[40],"introduce":[41],"SpatialCrafter,":[42],"a":[43,64,88,126],"framework":[44,114],"that":[45],"leverages":[46],"rich":[48],"knowledge":[49],"video":[51,110],"diffusion":[52],"models":[53],"to":[54,93],"generate":[55],"plausible":[56],"additional":[57],"thereby":[59],"alleviating":[60],"reconstruction":[61,138],"ambiguity.":[62],"Through":[63],"trainable":[65],"camera":[66,80],"encoder":[67],"an":[69],"epipolar":[70],"attention":[71],"mechanism":[72],"for":[73],"explicit":[74],"geometric":[75],"constraints,":[76],"we":[77],"achieve":[78],"precise":[79],"control":[81],"consistency,":[84],"further":[85],"reinforced":[86],"by":[87,100],"unified":[89],"scale":[90,95],"estimation":[91],"strategy":[92],"handle":[94],"discrepancies":[96],"across":[97],"datasets.":[98],"Furthermore,":[99],"integrating":[101],"monocular":[102],"depth":[103],"priors":[104],"with":[105],"semantic":[106],"features":[107,124],"latent":[111],"space,":[112],"our":[113,133],"directly":[115],"regresses":[116],"Gaussian":[118],"primitives":[119],"efficiently":[121],"processes":[122],"long-sequence":[123],"using":[125],"hybrid":[127],"network":[128],"structure.":[129],"Extensive":[130],"experiments":[131],"show":[132],"method":[134],"enhances":[135],"restores":[140],"realistic":[142],"appearance":[143],"scenes.":[146]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}