{"id":"https://openalex.org/W4414902929","doi":"https://doi.org/10.1109/iccv51701.2025.02528","title":"DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation","display_name":"DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414902929","doi":"https://doi.org/10.1109/iccv51701.2025.02528"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02528","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.15208","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012933809","display_name":"J. Guo","orcid":"https://orcid.org/0009-0006-4724-0804"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiazhe Guo","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013886309","display_name":"Yikang Ding","orcid":"https://orcid.org/0000-0001-6916-9371"},"institutions":[{"id":"https://openalex.org/I4210160780","display_name":"National Institute Of Veterinary Epidemiology And Disease Informatics","ror":"https://ror.org/04s9fyw02","country_code":"IN","type":"facility","lineage":["https://openalex.org/I179420787","https://openalex.org/I4210160780"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yikang Ding","raw_affiliation_strings":["MEGVII"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MEGVII","institution_ids":["https://openalex.org/I4210160780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiwu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiwu Chen","raw_affiliation_strings":["Mach Drive"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mach Drive","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366890","display_name":"Shuo Chen","orcid":"https://orcid.org/0000-0003-3893-715X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Chen","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443974","display_name":"Bohan Li","orcid":"https://orcid.org/0000-0002-3408-9037"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Li","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077722799","display_name":"Yingshuang Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingshuang Zou","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105783543","display_name":"X. R. Lyu","orcid":"https://orcid.org/0000-0003-1318-4905"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaoyang Lyu","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feiyang Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feiyang Tan","raw_affiliation_strings":["Mach Drive"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mach Drive","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102498323","display_name":"Xiaojuan Qi","orcid":"https://orcid.org/0000-0002-4285-1626"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaojuan Qi","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114911316","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-9428-1960"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Li","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108132369","display_name":"Hao Zhao","orcid":"https://orcid.org/0009-0003-0193-0453"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5012933809"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24736026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27231","last_page":"27241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9908000230789185,"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":0.9908000230789185,"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":0.9896000027656555,"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":0.9745000004768372,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6251000165939331},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5806000232696533},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5236999988555908},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.5196999907493591},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44369998574256897},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.42590001225471497},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4185999929904938},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.3718000054359436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6873999834060669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6305999755859375},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6251000165939331},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5806000232696533},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5236999988555908},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5131000280380249},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.42590001225471497},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34880000352859497},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C181095308","wikidata":"https://www.wikidata.org/wiki/Q1541599","display_name":"Geometric primitive","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2777634741","wikidata":"https://www.wikidata.org/wiki/Q768993","display_name":"Wasserstein metric","level":2,"score":0.26089999079704285}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02528","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:2503.15208","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.15208","pdf_url":"https://arxiv.org/pdf/2503.15208","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.2503.15208","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.15208","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.15208","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.15208","pdf_url":"https://arxiv.org/pdf/2503.15208","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":[{"id":"https://openalex.org/G1279384389","display_name":null,"funder_award_id":"2024YFB2505105","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"generative":[1],"models":[2],"struggle":[3],"to":[4,148],"synthesize":[5],"dynamic":[6],"4D":[7,56],"driving":[8,57],"scenes":[9],"that":[10,36,145,153],"simultaneously":[11],"support":[12],"temporal":[13,39,160],"extrapolation":[14],"and":[15,32,40,83,91,122,134,162],"spatial":[16,41,95,136],"novel":[17],"view":[18],"synthesis":[19],"(NVS)":[20],"without":[21],"per-scene":[22],"optimization.":[23],"A":[24],"key":[25],"challenge":[26],"lies":[27],"in":[28,158,170],"finding":[29],"an":[30],"efficient":[31],"generalizable":[33],"geometric":[34,67,143],"representation":[35,144],"seamlessly":[37],"connects":[38],"synthesis.":[42],"To":[43],"address":[44],"this,":[45],"we":[46],"propose":[47],"DiST-4D,":[48],"the":[49,65,71,117],"first":[50],"disentangled":[51],"spatiotemporal":[52],"diffusion":[53,75],"framework":[54],"for":[55,129],"scene":[58],"generation,":[59],"which":[60,78,93],"leverages":[61],"metric":[62,81],"depth":[63,82,126],"as":[64,138],"core":[66],"representation.":[68],"DiST-4D":[69,154],"decomposes":[70],"problem":[72],"into":[73],"two":[74],"processes:":[76],"DiST-T,":[77],"predicts":[79],"future":[80],"multi-view":[84],"RGB":[85],"sequences":[86],"directly":[87],"from":[88],"past":[89],"observations,":[90],"DiST-S,":[92],"enables":[94],"NVS":[96,163],"by":[97],"training":[98],"only":[99],"on":[100],"existing":[101],"viewpoints":[102],"while":[103,165],"enforcing":[104],"cycle":[105,108],"consistency.":[106],"This":[107],"consistency":[109],"mechanism":[110],"introduces":[111],"a":[112,141],"forward-backward":[113],"rendering":[114],"constraint,":[115],"reducing":[116],"generalization":[118],"gap":[119],"between":[120],"observed":[121],"unseen":[123,149],"viewpoints.":[124],"Metric":[125],"is":[127],"essential":[128],"both":[130,159],"accurate":[131,135],"reliable":[132],"forecasting":[133],"NVS,":[137],"it":[139],"provides":[140],"view-consistent":[142],"generalizes":[146],"well":[147],"perspectives.":[150],"Experiments":[151],"demonstrate":[152],"achieves":[155],"state-of-the-art":[156],"performance":[157,169],"prediction":[161],"tasks,":[164],"also":[166],"delivering":[167],"competitive":[168],"planning-related":[171],"evaluations.":[172]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}