{"id":"https://openalex.org/W4407213336","doi":"https://doi.org/10.1109/tpami.2025.3539866","title":"Dynamic Scene Understanding Through Object-Centric Voxelization and Neural Rendering","display_name":"Dynamic Scene Understanding Through Object-Centric Voxelization and Neural Rendering","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407213336","doi":"https://doi.org/10.1109/tpami.2025.3539866","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031593"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3539866","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3539866","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tpami.2025.3539866","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yanpeng Zhao","orcid":"https://orcid.org/0009-0002-1498-383X"},"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":true,"raw_author_name":"Yanpeng Zhao","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiwei Hao","orcid":"https://orcid.org/0009-0002-5995-2770"},"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":"Yiwei Hao","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101978561","display_name":"Siyu Gao","orcid":"https://orcid.org/0009-0001-5210-6435"},"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":"Siyu Gao","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100713555","display_name":"Yunbo Wang","orcid":"https://orcid.org/0000-0002-6224-2481"},"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":"Yunbo Wang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"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":"Xiaokang Yang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":6.0904,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.95861305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"47","issue":"5","first_page":"4215","last_page":"4231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9223999977111816,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9223999977111816,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7762607336044312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7625224590301514},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7572436332702637},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.642875075340271},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5934212803840637},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4641019105911255},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4152202308177948},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3891080617904663}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7762607336044312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7625224590301514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7572436332702637},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.642875075340271},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5934212803840637},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4641019105911255},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4152202308177948},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3891080617904663}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3539866","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3539866","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40031593","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031593","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tpami.2025.3539866","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3539866","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2331728944","display_name":null,"funder_award_id":"62250062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6193193764","display_name":null,"funder_award_id":"62106144","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":50,"referenced_works":["https://openalex.org/W2122572959","https://openalex.org/W2133665775","https://openalex.org/W2950635152","https://openalex.org/W3094502228","https://openalex.org/W3109585842","https://openalex.org/W3153220274","https://openalex.org/W3159481202","https://openalex.org/W3174752334","https://openalex.org/W3206993488","https://openalex.org/W3215589927","https://openalex.org/W4200382072","https://openalex.org/W4235169531","https://openalex.org/W4244030505","https://openalex.org/W4281651265","https://openalex.org/W4312339971","https://openalex.org/W4312420092","https://openalex.org/W4386065885","https://openalex.org/W4386075614","https://openalex.org/W4386075997","https://openalex.org/W4386083092","https://openalex.org/W4386113270","https://openalex.org/W4390874575","https://openalex.org/W4402754274","https://openalex.org/W6686008357","https://openalex.org/W6718986230","https://openalex.org/W6738893770","https://openalex.org/W6758420182","https://openalex.org/W6759669191","https://openalex.org/W6766312635","https://openalex.org/W6779809370","https://openalex.org/W6787728148","https://openalex.org/W6791353385","https://openalex.org/W6792316553","https://openalex.org/W6796561920","https://openalex.org/W6798683696","https://openalex.org/W6804342959","https://openalex.org/W6804682106","https://openalex.org/W6809898026","https://openalex.org/W6810902373","https://openalex.org/W6838432089","https://openalex.org/W6838531999","https://openalex.org/W6838538827","https://openalex.org/W6838619012","https://openalex.org/W6838825371","https://openalex.org/W6839270766","https://openalex.org/W6849401246","https://openalex.org/W6850229484","https://openalex.org/W6851800889","https://openalex.org/W6852629184","https://openalex.org/W6862451131"],"related_works":["https://openalex.org/W291250033","https://openalex.org/W2035757446","https://openalex.org/W3137044537","https://openalex.org/W2008385118","https://openalex.org/W880955280","https://openalex.org/W2106647072","https://openalex.org/W2172753644","https://openalex.org/W2170209930","https://openalex.org/W4246858109","https://openalex.org/W54172855"],"abstract_inverted_index":{"Learning":[0],"object-centric":[1,31,45],"representations":[2],"from":[3],"unsupervised":[4,116],"videos":[5],"is":[6,42],"challenging.":[7],"Unlike":[8],"most":[9],"previous":[10],"approaches":[11],"that":[12,29,151],"focus":[13],"on":[14],"decomposing":[15],"2D":[16,89,152],"images,":[17],"we":[18],"present":[19],"a":[20,34,69,82],"3D":[21,50,94],"generative":[22],"model":[23],"named":[24],"DynaVol-S":[25,105],"for":[26,119],"dynamic":[27,120],"scenes":[28],"enables":[30],"learning":[32],"within":[33],"differentiable":[35],"volume":[36],"rendering":[37,79],"framework.":[38],"The":[39],"key":[40],"idea":[41],"to":[43,47,92],"perform":[44],"voxelization":[46],"capture":[48],"the":[49,53,98,143,169],"nature":[51],"of":[52,172],"scene,":[54],"which":[55],"infers":[56],"per-object":[57],"occupancy":[58],"probabilities":[59],"at":[60],"individual":[61],"spatial":[62],"locations.":[63],"These":[64],"voxel":[65,103,146],"features":[66,91,147],"evolve":[67],"through":[68,100,163],"canonical-space":[70],"deformation":[71],"function":[72],"and":[73,115,127],"are":[74],"optimized":[75],"in":[76,110],"an":[77],"inverse":[78],"pipeline":[80],"with":[81],"compositional":[83],"NeRF.":[84],"Additionally,":[85],"our":[86],"approach":[87],"integrates":[88],"semantic":[90,95,128],"create":[93],"grids,":[96],"representing":[97],"scene":[99,153,161],"multiple":[101],"disentangled":[102],"grids.":[104],"significantly":[106],"outperforms":[107],"existing":[108],"models":[109],"both":[111],"novel":[112,160],"view":[113],"synthesis":[114],"decomposition":[117,154],"tasks":[118],"scenes.":[121],"By":[122],"jointly":[123],"considering":[124],"geometric":[125,165],"structures":[126],"features,":[129],"it":[130],"effectively":[131],"addresses":[132],"challenging":[133],"real-world":[134],"scenarios":[135],"involving":[136],"complex":[137],"object":[138],"interactions.":[139],"Furthermore,":[140],"once":[141],"trained,":[142],"explicitly":[144],"meaningful":[145],"enable":[148],"additional":[149],"capabilities":[150],"methods":[155],"cannot":[156],"achieve,":[157],"such":[158],"as":[159],"generation":[162],"editing":[164],"shapes":[166],"or":[167],"manipulating":[168],"motion":[170],"trajectories":[171],"objects.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
