{"id":"https://openalex.org/W4415540083","doi":"https://doi.org/10.1145/3746027.3754704","title":"TiP4GEN: Text to Immersive Panorama 4D Scene Generation","display_name":"TiP4GEN: Text to Immersive Panorama 4D Scene Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540083","doi":"https://doi.org/10.1145/3746027.3754704"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754704","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5006059190","display_name":"Ke Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Xing","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2626-9072","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hanwen Liang","orcid":"https://orcid.org/0000-0002-9892-752X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hanwen Liang","raw_affiliation_strings":["University of Toronto, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9892-752X","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084521327","display_name":"Dejia Xu","orcid":"https://orcid.org/0000-0001-8474-3095"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dejia Xu","raw_affiliation_strings":["The University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0001-8474-3095","affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101595849","display_name":"Yuyang Yin","orcid":"https://orcid.org/0009-0005-7443-6194"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Yin","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-7443-6194","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059152392","display_name":"Konstantinos N. Plataniotis","orcid":"https://orcid.org/0000-0003-3647-5473"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Konstantinos N. Plataniotis","raw_affiliation_strings":["University of Toronto, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3647-5473","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362745","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0002-8581-9554"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8581-9554","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087043856","display_name":"Yunchao Wei","orcid":"https://orcid.org/0000-0002-2812-8781"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunchao Wei","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2812-8781","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9267","last_page":"9276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9918000102043152,"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":0.9918000102043152,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9836999773979187,"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/panorama","display_name":"Panorama","score":0.9258000254631042},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.48069998621940613},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.46810001134872437},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.4675999879837036},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.4431999921798706},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.3847000002861023},{"id":"https://openalex.org/keywords/epipolar-geometry","display_name":"Epipolar geometry","score":0.382099986076355},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.3677999973297119}],"concepts":[{"id":"https://openalex.org/C2780580889","wikidata":"https://www.wikidata.org/wiki/Q41363","display_name":"Panorama","level":2,"score":0.9258000254631042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7994999885559082},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7019000053405762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6159999966621399},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5687999725341797},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.48069998621940613},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.4675999879837036},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C23379248","wikidata":"https://www.wikidata.org/wiki/Q200904","display_name":"Epipolar geometry","level":3,"score":0.382099986076355},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C44185422","wikidata":"https://www.wikidata.org/wiki/Q6002064","display_name":"Image-based modeling and rendering","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754704","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4316271325","display_name":null,"funder_award_id":"2024XKRC082","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6750931159","display_name":null,"funder_award_id":"No.92470203","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W4214520160","https://openalex.org/W4312933868","https://openalex.org/W4385318467","https://openalex.org/W4386071957","https://openalex.org/W4388191297","https://openalex.org/W4390872132","https://openalex.org/W4394597526","https://openalex.org/W4402660110","https://openalex.org/W4402753874"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,16,30,127,168,174,181],"rapid":[2],"advancement":[3],"and":[4,70,82,106,113,152,164,180,189],"widespread":[5],"adoption":[6],"of":[7,18,32,42,102,176,183],"VR/AR":[8],"technologies,":[9],"there":[10],"is":[11],"a":[12,44,97,103,107,134],"growing":[13],"demand":[14],"for":[15,111,167],"creation":[17,31],"high-quality,":[19],"immersive":[20,47,89],"dynamic":[21,38,83,191],"scenes.":[22,76,170,193],"However,":[23],"existing":[24],"generation":[25,63,81],"works":[26],"predominantly":[27],"concentrate":[28],"on":[29,139],"static":[33],"scenes":[34],"or":[35],"narrow":[36],"perspective-view":[37],"scenes,":[39],"falling":[40],"short":[41],"delivering":[43],"truly":[45],"360-degree":[46,88],"experience":[48],"from":[49],"any":[50],"viewpoint.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,95,132],"introduce":[56,96],"TiP4GEN,":[57],"an":[58],"advanced":[59],"text-to-dynamic":[60],"panorama":[61,79,104],"scene":[62,84,130,154],"framework":[64],"that":[65],"enables":[66],"fine-grained":[67],"content":[68],"control":[69],"synthesizes":[71],"motion-rich,":[72],"geometry-consistent":[73],"panoramic":[74,192],"4D":[75],"TiP4GEN":[77,184],"integrates":[78],"video":[80,93],"reconstruction":[85],"to":[86],"create":[87],"virtual":[90],"environments.":[91],"For":[92,129],"generation,":[94,116],"Dual-branch":[98],"Generation":[99],"Model":[100,137],"consisting":[101],"branch":[105],"perspective":[108],"branch,":[109],"responsible":[110],"global":[112],"local":[114],"view":[115],"respectively.":[117],"A":[118],"bidirectional":[119],"cross-attention":[120],"mechanism":[121],"facilitates":[122],"comprehensive":[123],"information":[124],"exchange":[125],"between":[126],"branches.":[128],"reconstruction,":[131],"propose":[133],"Geometry-aligned":[135],"Reconstruction":[136],"based":[138],"3D":[140],"Gaussian":[141],"Splatting.":[142],"By":[143],"aligning":[144],"spatial-temporal":[145],"point":[146],"clouds":[147],"using":[148],"metric":[149],"depth":[150],"maps":[151],"initializing":[153],"cameras":[155],"with":[156],"estimated":[157],"poses,":[158],"our":[159,177],"method":[160],"ensures":[161],"geometric":[162],"consistency":[163],"temporal":[165],"coherence":[166],"reconstructed":[169],"Extensive":[171],"experiments":[172],"demonstrate":[173],"effectiveness":[175],"proposed":[178],"designs":[179],"superiority":[182],"in":[185],"generating":[186],"visually":[187],"compelling":[188],"motion-coherent":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-25T00:00:00"}