{"id":"https://openalex.org/W7214728202","doi":"https://doi.org/10.48550/arxiv.2609.35023","title":"Proxy2World: Learning to Generate Worlds From Lightweight Proxies without Seeing Them","display_name":"Proxy2World: Learning to Generate Worlds From Lightweight Proxies without Seeing Them","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214728202","doi":"https://doi.org/10.48550/arxiv.2609.35023"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.35023","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35023","pdf_url":"https://arxiv.org/pdf/2609.35023","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.35023","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153430864","display_name":"Hongli Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Hongli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153413022","display_name":"Weilong Yan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Weilong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153432215","display_name":"Anbang Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Anbang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018187280","display_name":"Chunyu Zou","orcid":"https://orcid.org/0000-0001-5728-5287","observed_orcids":["https://orcid.org/0000-0001-5728-5287"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Chunyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037514382","display_name":"Siyu Hong","orcid":"https://orcid.org/0009-0007-2347-9631","observed_orcids":["https://orcid.org/0009-0007-2347-9631","https://orcid.org/0009-0004-8054-8136"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Siyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101529571","display_name":"Jingwei Huang","orcid":"https://orcid.org/0000-0003-0356-6002","observed_orcids":["https://orcid.org/0000-0003-0356-6002"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jingwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.8838000297546387,"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":0.8838000297546387,"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":0.05810000002384186,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.03420000150799751,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/rgb-d-video","display_name":"RGB-D video","score":0.41999998688697815},{"id":"https://openalex.org/keywords/controllable-image-generation","display_name":"controllable image generation","score":0.47999998927116394},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530999779701233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6474999785423279},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6212000250816345},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4088999927043915},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39070001244544983},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3815000057220459},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3125},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29260000586509705},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.35023","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35023","pdf_url":"https://arxiv.org/pdf/2609.35023","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.35023","doi":"https://doi.org/10.48550/arxiv.2609.35023","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.35023","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.35023","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35023","pdf_url":"https://arxiv.org/pdf/2609.35023","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214728202.pdf","grobid_xml":"https://content.openalex.org/works/W7214728202.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2963557767","https://openalex.org/W4378506819","https://openalex.org/W4385965594","https://openalex.org/W4389115686","https://openalex.org/W4390041933","https://openalex.org/W4393967358","https://openalex.org/W4399424705","https://openalex.org/W4399759407","https://openalex.org/W4404260636","https://openalex.org/W4405096483","https://openalex.org/W4409092337","https://openalex.org/W4414432428","https://openalex.org/W4415089914","https://openalex.org/W4416288893","https://openalex.org/W7075993779","https://openalex.org/W7105740705","https://openalex.org/W7127121255","https://openalex.org/W7154502205","https://openalex.org/W7155397894","https://openalex.org/W7160291278","https://openalex.org/W7164484796","https://openalex.org/W7164810819","https://openalex.org/W7166113584","https://openalex.org/W7172384888","https://openalex.org/W7203640516","https://openalex.org/W7204440733","https://openalex.org/W7212146656"],"related_works":["https://openalex.org/W7204530983","https://openalex.org/W7167601905","https://openalex.org/W4383097608","https://openalex.org/W7203707334","https://openalex.org/W4417009953","https://openalex.org/W4417232068","https://openalex.org/W7164883443","https://openalex.org/W4416510402","https://openalex.org/W2949907962","https://openalex.org/W7212275598"],"abstract_inverted_index":{"Lightweight":[0],"scene":[1,6],"proxies":[2],"let":[3],"creators":[4],"control":[5],"layout":[7],"and":[8,18,69,112,128,133,144],"motion":[9],"while":[10,91],"leaving":[11],"room":[12],"for":[13],"imagination":[14],"in":[15],"appearance,":[16],"lighting,":[17],"visual":[19,129],"effects.":[20],"However,":[21],"a":[22,42,105,122],"suitable":[23],"proxy":[24,89],"is":[25],"not":[26],"uniquely":[27],"defined,":[28],"making":[29],"paired":[30],"proxy-video":[31,60],"data":[32],"difficult":[33],"to":[34,86,100],"construct":[35],"automatically":[36],"at":[37,84],"scale.":[38],"We":[39,96],"present":[40],"Proxy2World,":[41],"controllable":[43],"world":[44],"model":[45,63],"that":[46,119],"learns":[47,65],"these":[48],"complementary":[49],"capabilities":[50],"from":[51],"ordinary":[52],"posed":[53],"RGBD":[54,71],"videos,":[55],"without":[56],"training":[57],"on":[58,116],"authored":[59],"pairs.":[61],"The":[62],"jointly":[64],"depth-conditioned":[66],"RGB":[67],"generation":[68,72],"joint":[70],"through":[73],"cross-modal":[74],"flow":[75],"matching.":[76],"Learning":[77],"both":[78],"tasks":[79],"enables":[80],"proxy-camera":[81],"hybrid":[82],"denoising":[83],"inference":[85],"follow":[87],"the":[88],"structure":[90],"producing":[92],"natural,":[93],"detailed":[94],"visuals.":[95],"further":[97],"introduce":[98],"ProxyBench":[99,117],"evaluate":[101],"this":[102],"capability":[103],"across":[104],"diverse":[106,145],"set":[107],"of":[108],"scenes,":[109],"camera":[110],"trajectories,":[111],"subject":[113],"motions.":[114],"Experiments":[115],"show":[118],"Proxy2World":[120],"achieves":[121],"better":[123],"balance":[124],"between":[125],"structural":[126],"adherence":[127],"quality":[130],"than":[131],"camera-controlled":[132],"geometry-conditioned":[134],"methods,":[135],"supported":[136],"by":[137],"quantitative":[138],"metrics,":[139],"VLM":[140],"assessments,":[141],"human":[142],"evaluations":[143],"qualitative":[146],"results.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-09-30T00:00:00"}