{"id":"https://openalex.org/W4413144353","doi":"https://doi.org/10.1109/cvpr52734.2025.02055","title":"Robust Multi-Object 4D Generation for In-the-wild Videos","display_name":"Robust Multi-Object 4D Generation for In-the-wild Videos","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144353","doi":"https://doi.org/10.1109/cvpr52734.2025.02055"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5000324321","display_name":"Wen-Hsuan Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-Hsuan Chu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077165692","display_name":"Lei Ke","orcid":"https://orcid.org/0000-0002-1978-2562"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Ke","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004017185","display_name":"Jianmeng Liu","orcid":"https://orcid.org/0000-0002-3220-6084"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianmeng Liu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001015558","display_name":"Mingxiao Huo","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingxiao Huo","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040760890","display_name":"Pavel Tokmakov","orcid":"https://orcid.org/0000-0003-2043-6242"},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Pavel Tokmakov","raw_affiliation_strings":["Toyota Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Research Institute","institution_ids":["https://openalex.org/I4391768151"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008661738","display_name":"Katerina Fragkiadaki","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katerina Fragkiadaki","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"22067","last_page":"22077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9995999932289124,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9995999932289124,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9965000152587891,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9905999898910522,"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/computer-science","display_name":"Computer science","score":0.6813375949859619},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5332735776901245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5094051957130432},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4383890628814697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6813375949859619},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5332735776901245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5094051957130432},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4383890628814697}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.4300000071525574},{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,103,117,123,129,137,173,179,182,193],"challenge":[3],"of":[4,72,105,128,152,175,181,192,219],"generating":[5,153],"dynamic":[6],"4D":[7,154],"scenes":[8,51,64,220],"from":[9,81,167],"monocular":[10,168],"multi-object":[11,185],"videos":[12],"with":[13,29,49,200],"heavy":[14],"occlusions":[15,80],"and":[16,56,122,139,158,163,178,207,221],"introduce":[17,188],"GenMOJO,":[18],"a":[19,69,82,143,149,190],"novel":[20,41,217],"approach":[21],"that":[22,212],"integrates":[23],"rendering-based":[24],"deformable":[25,73],"3D":[26,83,164],"Gaussian":[27,87],"optimization":[28],"generative":[30,140],"priors":[31,121],"for":[32,44,109],"view":[33,42],"synthesis.":[34],"While":[35],"existing":[36,229],"view-synthesis":[37],"models":[38,108],"excel":[39],"at":[40],"generation":[43,177],"isolated":[45],"objects,":[46,67],"they":[47],"struggle":[48],"full":[50],"due":[52],"to":[53,135,228],"their":[54],"complexity":[55],"data":[57],"demands.":[58],"To":[59,115,170],"overcome":[60],"this,":[61],"GenMOJO":[62,131,213],"decomposes":[63],"into":[65],"individual":[66],"optimizing":[68],"differentiable":[70,133],"set":[71],"Gaussians":[74],"per":[75],"object":[76,100,110],"while":[77,98,160],"capturing":[78],"2D":[79,162,202],"perspective":[84],"through":[85],"joint":[86],"splatting.":[88],"Joint":[89],"splatting":[90],"ensures":[91],"occlusion-aware":[92],"rendering":[93,138],"losses":[94],"in":[95,112],"observed":[96],"frames,":[97],"explicit":[99],"decomposition":[101],"allows":[102],"usage":[104],"object-centric":[106,120],"diffusion":[107],"completion":[111],"unobserved":[113],"viewpoints.":[114],"reconcile":[116],"differences":[118],"between":[119],"global":[124],"frame-centric":[125],"coordinate":[126],"system":[127],"video,":[130],"employs":[132],"transformations":[134],"unify":[136],"constraints":[141],"within":[142],"single":[144],"framework.":[145],"The":[146],"result":[147],"is":[148],"model":[150],"capable":[151],"objects":[155],"across":[156],"space":[157],"time":[159],"producing":[161],"point":[165,203,225],"tracks":[166,226],"videos.":[169],"rigorously":[171],"evaluate":[172],"quality":[174],"scene":[176],"accuracy":[180],"motion":[183],"under":[184],"occlusions,":[186],"we":[187,198],"MOSE-PTS,":[189],"subset":[191],"challenging":[194],"MOSE":[195],"benchmark,":[196],"which":[197],"annotated":[199],"high-quality":[201],"tracks.":[204],"Quantitative":[205],"evaluations":[206],"perceptual":[208],"human":[209],"studies":[210],"confirm":[211],"generates":[214],"more":[215,223],"realistic":[216],"views":[218],"produces":[222],"accurate":[224],"compared":[227],"approaches.":[230],"Project":[231],"page:":[232],"https://genmojo.github.io/.":[233]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}