{"id":"https://openalex.org/W7147556209","doi":"https://doi.org/10.1109/tvcg.2026.3679097","title":"ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies","display_name":"ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7147556209","doi":"https://doi.org/10.1109/tvcg.2026.3679097","pmid":"https://pubmed.ncbi.nlm.nih.gov/41915498"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2026.3679097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3679097","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5132549654","display_name":"Jinyan Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyan Yuan","raw_affiliation_strings":["Bytedance, China"],"raw_orcid":"https://orcid.org/0009-0001-3139-7616","affiliations":[{"raw_affiliation_string":"Bytedance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132709958","display_name":"Bangbang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bangbang Yang","raw_affiliation_strings":["Bytedance, China"],"raw_orcid":"https://orcid.org/0000-0001-7604-5553","affiliations":[{"raw_affiliation_string":"Bytedance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132714723","display_name":"Keke Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keke Wang","raw_affiliation_strings":["Bytedance, China"],"raw_orcid":"https://orcid.org/0009-0006-1854-2539","affiliations":[{"raw_affiliation_string":"Bytedance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132729123","display_name":"Panwang Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Panwang Pan","raw_affiliation_strings":["Bytedance, China"],"raw_orcid":"https://orcid.org/0000-0001-8631-012X","affiliations":[{"raw_affiliation_string":"Bytedance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132632985","display_name":"Lin Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Bytedance, China"],"raw_orcid":"https://orcid.org/0009-0005-2568-2735","affiliations":[{"raw_affiliation_string":"Bytedance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132681349","display_name":"Xuehai Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuehai Zhang","raw_affiliation_strings":["Bytedance, China"],"raw_orcid":"https://orcid.org/0009-0000-9972-2916","affiliations":[{"raw_affiliation_string":"Bytedance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132577275","display_name":"Xiao Yan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Liu","raw_affiliation_strings":["Bytedance, China"],"raw_orcid":"https://orcid.org/0000-0002-6073-030X","affiliations":[{"raw_affiliation_string":"Bytedance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075311772","display_name":"Zhaopeng Cui","orcid":"https://orcid.org/0000-0002-7130-439X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaopeng Cui","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-7130-439X","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132709715","display_name":"Yuewen Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuewen Ma","raw_affiliation_strings":["Bytedance, China"],"raw_orcid":"https://orcid.org/0009-0003-7734-7053","affiliations":[{"raw_affiliation_string":"Bytedance, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"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":0.48124718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"5","first_page":"3530","last_page":"3540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.3312000036239624,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.3312000036239624,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.31220000982284546,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1103999987244606,"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/rendering","display_name":"Rendering (computer graphics)","score":0.7605000138282776},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4562999904155731},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.41290000081062317},{"id":"https://openalex.org/keywords/non-photorealistic-rendering","display_name":"Non-photorealistic rendering","score":0.39079999923706055},{"id":"https://openalex.org/keywords/solid-modeling","display_name":"Solid modeling","score":0.35600000619888306},{"id":"https://openalex.org/keywords/graphics-pipeline","display_name":"Graphics pipeline","score":0.3321000039577484},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.329800009727478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353999853134155},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7605000138282776},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5613999962806702},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3928999900817871},{"id":"https://openalex.org/C155650255","wikidata":"https://www.wikidata.org/wiki/Q259326","display_name":"Non-photorealistic rendering","level":5,"score":0.39079999923706055},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.367000013589859},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.364300012588501},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C173552908","wikidata":"https://www.wikidata.org/wiki/Q1366289","display_name":"Graphics pipeline","level":4,"score":0.3321000039577484},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C44185422","wikidata":"https://www.wikidata.org/wiki/Q6002064","display_name":"Image-based modeling and rendering","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.2671000063419342}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2026.3679097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3679097","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:41915498","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41915498","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null}],"best_oa_location":null,"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":{"Automating":[0],"immersive":[1],"VR":[2,73,122],"scene":[3],"creation":[4],"remains":[5],"a":[6,37],"primary":[7],"research":[8],"challenge.":[9],"Existing":[10],"methods":[11],"typically":[12],"rely":[13],"on":[14,71],"complex":[15],"geometry":[16],"with":[17,64,84,109],"post-simplification,":[18],"resulting":[19],"in":[20],"inefficient":[21],"pi":[22],"pelines":[23],"or":[24],"li":[25],"mited":[26],"re":[27],"alism.":[28],"In":[29],"th":[30],"is":[31],"paper,":[32],"we":[33],"introduce":[34],"Im":[35],"merseGen,":[36],"novel":[38],"agent-guided":[39],"framework":[40],"for":[41,79,87,102],"compact":[42],"and":[43,92,106,116,120,132],"photorealistic":[44],"world":[45,81],"generation":[46],"that":[47,125],"decouples":[48],"realism":[49],"from":[50],"exhaustive":[51],"geometric":[52,62],"modeling.":[53],"ImmerseGen":[54,126],"represents":[55],"scenes":[56,108],"as":[57,113],"hierarchical":[58],"compositions":[59],"of":[60],"lightweight":[61],"proxies":[63],"synthesized":[65],"RGBA":[66],"textures,":[67],"facilitating":[68],"real-time":[69,121],"rendering":[70,133],"mobile":[72],"headsets.":[74],"We":[75],"propose":[76],"terrain-conditioned":[77],"texturing":[78,86],"base":[80],"generation,":[82],"combined":[83],"context-aware":[85],"scenery,":[88],"to":[89,136],"produce":[90],"diverse":[91],"visually":[93],"coherent":[94],"worlds.":[95],"VLM-based":[96],"agents":[97],"employ":[98],"semantic":[99],"grid-based":[100],"analysis":[101],"precise":[103],"asset":[104],"placement":[105],"enrich":[107],"multimodal":[110],"enhancements":[111],"such":[112],"visual":[114],"dynamics":[115],"ambient":[117],"sound.":[118],"Experiments":[119],"applications":[123],"demonstrate":[124],"achieves":[127],"superior":[128],"photorealism,":[129],"spatial":[130],"coherence,":[131],"efficiency":[134],"compared":[135],"existing":[137],"methods.":[138]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-02T00:00:00"}
