{"id":"https://openalex.org/W4415307419","doi":"https://doi.org/10.1109/iccv51701.2025.00620","title":"Predict-Optimize-Distill: A Self-Improving Cycle for 4D Object Understanding","display_name":"Predict-Optimize-Distill: A Self-Improving Cycle for 4D Object Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415307419","doi":"https://doi.org/10.1109/iccv51701.2025.00620"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00620","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.17441","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101336240","display_name":"Mingxuan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingxuan Wu","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340336","display_name":"Huang Huang","orcid":"https://orcid.org/0000-0002-8377-4823"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang Huang","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022467361","display_name":"Justin Kerr","orcid":"https://orcid.org/0000-0002-0536-4853"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Kerr","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074509165","display_name":"Chung Min Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chung Min Kim","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075466372","display_name":"Anthony Lin Zhang","orcid":"https://orcid.org/0000-0002-0968-9380"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Zhang","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067921958","display_name":"Brent Yi","orcid":"https://orcid.org/0009-0009-8408-0717"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brent Yi","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031491881","display_name":"Angjoo Kanazawa","orcid":"https://orcid.org/0000-0003-2592-8430"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Angjoo Kanazawa","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6575","last_page":"6584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.2892000079154968,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.2892000079154968,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.2660999894142151,"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/object","display_name":"Object (grammar)","score":0.47999998927116394},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.4546999931335449},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.45100000500679016},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.3982999920845032},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38909998536109924},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.37470000982284546},{"id":"https://openalex.org/keywords/revolute-joint","display_name":"Revolute joint","score":0.37380000948905945},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.367000013589859},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.3668999969959259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724999785423279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6848000288009644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48339998722076416},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42340001463890076},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C5643039","wikidata":"https://www.wikidata.org/wiki/Q3819341","display_name":"Revolute joint","level":3,"score":0.37380000948905945},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3337000012397766},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00620","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:2504.17441","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.17441","pdf_url":"https://arxiv.org/pdf/2504.17441","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.17441","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.17441","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.17441","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.17441","pdf_url":"https://arxiv.org/pdf/2504.17441","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G119237539","display_name":null,"funder_award_id":"CNS-2235013","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3308580458","display_name":"Collaborative Research: CCRI: New: An Open Source Simulation Platform for AI Research on Autonomous Driving","funder_award_id":"2235013","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4415307419.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Humans":[0],"can":[1],"resort":[2],"to":[3,6,68,97,108,162,256],"long-form":[4,85],"inspection":[5],"build":[7],"intuition":[8],"on":[9,189],"predicting":[10,29],"the":[11,21,24,123,129,144,148,165,250],"3D":[12,31],"configurations":[13,167,209],"of":[14,88,125,168,249],"unseen":[15],"objects.":[16],"The":[17],"more":[18],"we":[19,26],"observe":[20],"object":[22,72,81],"motion,":[23],"better":[25,70],"get":[27],"at":[28],"its":[30,158,254],"state":[32],"immediately.":[33],"Existing":[34],"systems":[35],"either":[36],"optimize":[37],"underlying":[38],"representations":[39],"from":[40,48,102,137],"multi-view":[41,80],"observations":[42,261],"or":[43,213],"train":[44],"a":[45,55,64,79,84,94,110,153,174,221],"feed-forward":[46],"predictor":[47,107],"supervised":[49],"datasets.":[50],"We":[51,171,186,235],"introduce":[52,173],"Predict-Optimize-Distill":[53],"(POD),":[54],"self-improving":[56,251],"framework":[57],"that":[58,156,238],"interleaves":[59],"prediction":[60],"and":[61,83,147,192,202,246,262],"optimization":[62,112,126,223],"in":[63,228],"mutually":[65],"reinforcing":[66],"cycle":[67,155],"achieve":[69],"4D":[71],"understanding":[73],"with":[74,196,242,259],"increasing":[75],"observation":[76],"time.":[77],"Given":[78],"scan":[82],"monocular":[86],"video":[87,244],"human-object":[89],"interaction,":[90],"POD":[91,188,216],"iteratively":[92],"trains":[93],"neural":[95],"network":[96],"predict":[98],"local":[99,229],"part":[100],"poses":[101,116],"RGB":[103],"frames,":[104],"uses":[105],"this":[106],"initialize":[109],"global":[111],"which":[113,225],"refines":[114],"output":[115],"through":[117],"inverse":[118],"rendering,":[119],"then":[120],"finally":[121],"distills":[122],"results":[124],"back":[127],"into":[128],"model":[130,146],"by":[131,182],"generating":[132],"synthetic":[133,194],"self-labeled":[134],"training":[135,160],"data":[136,161],"novel":[138],"viewpoints.":[139],"Each":[140],"iteration":[141],"improves":[142,241],"both":[143,243],"predictive":[145],"optimized":[149],"motion":[150],"trajectory,":[151],"creating":[152],"virtuous":[154],"bootstraps":[157],"own":[159],"learn":[163],"about":[164],"pose":[166],"an":[169],"object.":[170],"also":[172,236],"quasi-multiview":[175],"mining":[176],"strategy":[177],"for":[178,232],"reducing":[179],"depth":[180],"ambiguity":[181],"leveraging":[183],"long":[184],"video.":[185],"evaluate":[187],"14":[190],"real-world":[191],"5":[193],"objects":[195],"various":[197],"joint":[198],"types,":[199],"including":[200],"revolute":[201],"prismatic":[203],"joints":[204],"as":[205,207],"well":[206],"multi-body":[208],"where":[210],"parts":[211],"detach":[212],"reattach":[214],"independently.":[215],"demonstrates":[217],"significant":[218],"improvement":[219],"over":[220],"pure":[222],"baseline":[224],"gets":[226],"stuck":[227],"minima,":[230],"particularly":[231],"longer":[233],"videos.":[234],"find":[237],"POD's":[239],"performance":[240,258],"length":[245],"successive":[247],"iterations":[248],"cycle,":[252],"highlighting":[253],"ability":[255],"scale":[257],"additional":[260],"looped":[263],"refinement.":[264]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-18T00:00:00"}