{"id":"https://openalex.org/W4415287434","doi":"https://doi.org/10.1109/iccv51701.2025.02479","title":"VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling","display_name":"VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415287434","doi":"https://doi.org/10.1109/iccv51701.2025.02479"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02479","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.15855","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025530723","display_name":"Hyojun Go","orcid":"https://orcid.org/0000-0002-5470-042X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyojun Go","raw_affiliation_strings":["EverEx"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EverEx","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051368302","display_name":"Byeongjun Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byeongjun Park","raw_affiliation_strings":["EverEx"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EverEx","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080675802","display_name":"Hyelin Nam","orcid":"https://orcid.org/0009-0008-0505-8929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyelin Nam","raw_affiliation_strings":["EverEx"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EverEx","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007457176","display_name":"Byung\u2010Hoon Kim","orcid":"https://orcid.org/0000-0001-8949-4833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byung-Hoon Kim","raw_affiliation_strings":["EverEx"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EverEx","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006604581","display_name":"Hyungjin Chung","orcid":"https://orcid.org/0000-0003-3202-0893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyungjin Chung","raw_affiliation_strings":["EverEx"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EverEx","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069759184","display_name":"Changick Kim","orcid":"https://orcid.org/0000-0001-9323-8488"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Changick Kim","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.24746024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9977999925613403,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9977999925613403,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9954000115394592,"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/T11448","display_name":"Face recognition and analysis","score":0.9911999702453613,"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/margin","display_name":"Margin (machine learning)","score":0.45890000462532043},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4426000118255615},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.41749998927116394},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4092000126838684},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4050999879837036},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.40130001306533813},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.39430001378059387},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.37599998712539673},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.878000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6643999814987183},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6435999870300293},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4426000118255615},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.39430001378059387},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.3398999869823456},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C110898773","wikidata":"https://www.wikidata.org/wiki/Q2933935","display_name":"Camera resectioning","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.2583000063896179}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02479","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:2503.15855","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.15855","pdf_url":"https://arxiv.org/pdf/2503.15855","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2503.15855","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.15855","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.15855","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.15855","pdf_url":"https://arxiv.org/pdf/2503.15855","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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],"propose":[1,88,153],"VideoRFSplat,":[2],"a":[3,8,92,105,113,118,124],"direct":[4,195],"text-to-3D":[5,194],"model":[6,11,50,97,122,128],"leveraging":[7],"video":[9,106,126],"generation":[10,107,121,127,196],"to":[12,38,48,67,71,79,95,170],"generate":[13,24],"realistic":[14],"3D":[15],"Gaussian":[16],"Splatting":[17],"(3DGS)":[18],"for":[19],"unbounded":[20,29],"real-world":[21,33,185],"scenes.":[22],"To":[23],"diverse":[25],"camera":[26,51,101,136,160],"poses":[27,52,102,137,161,169],"and":[28,53,82,91,100,135,148,177],"spatial":[30],"extent":[31],"of":[32],"scenes,":[34],"while":[35],"ensuring":[36],"generalization":[37],"arbitrary":[39],"text":[40],"prompts,":[41],"previous":[42],"methods":[43,58,197],"fine-tune":[44],"2D":[45,64],"generative":[46,65],"models":[47,66,78],"jointly":[49,96],"multi-view":[54,98,133,164,172],"images.":[55],"However,":[56],"these":[57],"suffer":[59],"from":[60],"instability":[61],"when":[62,103],"extending":[63],"joint":[68],"modeling":[69],"due":[70],"the":[72,146],"modality":[73],"gap,":[74],"which":[75],"necessitates":[76],"additional":[77],"stabilize":[80],"training":[81],"inference.":[83],"In":[84],"this":[85],"work,":[86],"we":[87,152],"an":[89,154],"architecture":[90,115],"sampling":[93,156],"strategy":[94,157],"images":[99,134],"fine-tuning":[104],"model.":[108],"Our":[109],"core":[110],"idea":[111],"is":[112],"dual-stream":[114],"that":[116,158,198],"attaches":[117],"dedicated":[119],"pose":[120,147],"alongside":[123],"pre-trained":[125],"via":[129,204],"communication":[130],"blocks,":[131],"generating":[132],"through":[138],"separate":[139],"streams.":[140],"This":[141],"design":[142],"reduces":[143],"interference":[144],"between":[145],"image":[149],"modalities.":[150],"Additionally,":[151],"asynchronous":[155],"denoises":[159],"faster":[162],"than":[163],"images,":[165],"allowing":[166],"rapidly":[167],"denoised":[168],"condition":[171],"generation,":[173],"reducing":[174],"mutual":[175],"ambiguity":[176],"enhancing":[178],"cross-modal":[179],"consistency.":[180],"Trained":[181],"on":[182,201],"multiple":[183],"large-scale":[184],"datasets":[186],"(RealEstate10K,":[187],"MVImgNet,":[188],"DL3DV-10K,":[189],"ACID),":[190],"VideoRFSplat":[191],"outperforms":[192],"existing":[193],"heavily":[199],"depend":[200],"post-hoc":[202],"refinement":[203],"score":[205],"distillation":[206],"sampling,":[207],"achieving":[208],"superior":[209],"results":[210],"without":[211],"such":[212],"refinement.":[213]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-17T00:00:00"}