{"id":"https://openalex.org/W4417150047","doi":"https://doi.org/10.1109/iccv51701.2025.00336","title":"A Recipe for Generating 3D Worlds from a Single Image","display_name":"A Recipe for Generating 3D Worlds from a Single Image","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417150047","doi":"https://doi.org/10.1109/iccv51701.2025.00336"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00336","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/2503.16611","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114034225","display_name":"K Schwarz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katja Schwarz","raw_affiliation_strings":["Meta Reality Labs,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,Zurich,Switzerland","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059736596","display_name":"Denys Rozumnyi","orcid":"https://orcid.org/0000-0001-9874-1349"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Denis Rozumny","raw_affiliation_strings":["Meta Reality Labs,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,Zurich,Switzerland","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073916921","display_name":"Samuel Rota Bul\u00f2","orcid":"https://orcid.org/0000-0002-2372-1367"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Rota Bul\u00f2","raw_affiliation_strings":["Meta Reality Labs,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,Zurich,Switzerland","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082732256","display_name":"Lorenzo Porzi","orcid":"https://orcid.org/0000-0001-9331-2908"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lorenzo Porzi","raw_affiliation_strings":["Meta Reality Labs,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,Zurich,Switzerland","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017062041","display_name":"Peter Kontschieder","orcid":"https://orcid.org/0000-0002-9809-664X"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Kontschieder","raw_affiliation_strings":["Meta Reality Labs,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,Zurich,Switzerland","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210128585"],"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":"3520","last_page":"3530"},"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":0.44670000672340393,"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":0.44670000672340393,"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":0.25380000472068787,"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":0.09099999815225601,"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/inpainting","display_name":"Inpainting","score":0.7583000063896179},{"id":"https://openalex.org/keywords/recipe","display_name":"Recipe","score":0.6833000183105469},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4618000090122223},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.414900004863739},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4108000099658966},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.39899998903274536},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.39399999380111694},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.3935000002384186},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3837999999523163}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.7583000063896179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6862000226974487},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.6833000183105469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6759999990463257},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.632099986076355},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4618000090122223},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.39399999380111694},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3837999999523163},{"id":"https://openalex.org/C84824328","wikidata":"https://www.wikidata.org/wiki/Q4633097","display_name":"2D to 3D conversion","level":3,"score":0.38089999556541443},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32190001010894775},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C53332860","wikidata":"https://www.wikidata.org/wiki/Q2632041","display_name":"Metaverse","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00336","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:2503.16611","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16611","pdf_url":"https://arxiv.org/pdf/2503.16611","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.2503.16611","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.16611","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":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:2503.16611","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16611","pdf_url":"https://arxiv.org/pdf/2503.16611","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,59],"introduce":[1],"a":[2,10,45,55],"recipe":[3],"for":[4,22,90],"generating":[5,41],"immersive":[6],"3D":[7,53,87,97],"worlds":[8],"from":[9,103],"single":[11],"image":[12,117],"by":[13,64],"framing":[14],"the":[15,66,96,100,104],"task":[16],"as":[17],"an":[18],"in-context":[19],"learning":[20],"problem":[21],"2D":[23],"inpainting":[24,67],"models.":[25,35],"This":[26],"approach":[27,107],"requires":[28],"minimal":[29,74],"training":[30],"and":[31,49,80],"uses":[32],"existing":[33],"generative":[34],"Our":[36],"process":[37],"involves":[38],"two":[39],"steps:":[40],"coherent":[42],"panoramas":[43],"using":[44],"pre-trained":[46],"diffusion":[47],"model":[48,68],"lifting":[50],"these":[51],"into":[52],"with":[54],"metric":[56],"depth":[57],"estimator.":[58],"then":[60],"fill":[61],"unobserved":[62],"regions":[63],"conditioning":[65],"on":[69,77],"rendered":[70],"point":[71],"clouds,":[72],"requiring":[73],"fine-tuning.":[75],"Tested":[76],"both":[78],"synthetic":[79],"real":[81],"images,":[82],"our":[83,106],"method":[84],"produces":[85],"high-quality":[86],"environments":[88],"suitable":[89],"VR":[91],"display.":[92],"By":[93],"explicitly":[94],"modeling":[95],"structure":[98],"of":[99],"generated":[101],"environment":[102],"start,":[105],"consistently":[108],"outperforms":[109],"state-of-the-art,":[110],"video":[111],"synthesis-based":[112],"methods":[113],"along":[114],"multiple":[115],"quantitative":[116],"quality":[118],"metrics.":[119],"Project":[120],"Page:":[121],"https://katjaschwarz.github.io/worlds/":[122]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}