{"id":"https://openalex.org/W7161910729","doi":"https://doi.org/10.48550/arxiv.2605.19539","title":"Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R","display_name":"Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161910729","doi":"https://doi.org/10.48550/arxiv.2605.19539"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.19539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19539","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.19539","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136529786","display_name":"Zihao Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136599908","display_name":"Wenyuan Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Wenyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136517312","display_name":"Nuo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Nuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136522793","display_name":"Chao Tian","orcid":"https://orcid.org/0000-0001-8752-6141"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136570456","display_name":"Zhiwen Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Zhiwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.29010000824928284,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.29010000824928284,"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"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.19869999587535858,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10531","display_name":"Advanced Vision and Imaging","score":0.10930000245571136,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.5968999862670898},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5076000094413757},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.49079999327659607},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.49079999327659607},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.4691999852657318},{"id":"https://openalex.org/keywords/heteroscedasticity","display_name":"Heteroscedasticity","score":0.4643999934196472},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.43540000915527344},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.4323999881744385},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4309000074863434}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5968999862670898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105000138282776},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.49079999327659607},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47530001401901245},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C101104100","wikidata":"https://www.wikidata.org/wiki/Q1063540","display_name":"Heteroscedasticity","level":2,"score":0.4643999934196472},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46149998903274536},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.4323999881744385},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C95167961","wikidata":"https://www.wikidata.org/wiki/Q4483495","display_name":"Fiducial inference","level":5,"score":0.3763999938964844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.361299991607666},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.35600000619888306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C156201811","wikidata":"https://www.wikidata.org/wiki/Q5418360","display_name":"Evidential reasoning approach","level":4,"score":0.3287000060081482},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.3125},{"id":"https://openalex.org/C177384507","wikidata":"https://www.wikidata.org/wiki/Q1149000","display_name":"Multivariate normal distribution","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.2957000136375427},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C39947850","wikidata":"https://www.wikidata.org/wiki/Q729523","display_name":"Geometric distribution","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.19539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19539","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.19539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19539","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Geometric":[0],"foundation":[1],"models":[2],"hold":[3],"promise":[4],"for":[5,54,75,167],"unconstrained":[6],"dense":[7],"geometry":[8,38,172],"prediction":[9],"from":[10],"uncalibrated":[11],"images.":[12],"However,":[13],"in":[14,146,170],"current":[15],"feed-forward":[16,55],"designs,":[17],"their":[18],"predicted":[19,37],"confidence":[20,105],"scores":[21],"are":[22,144,179],"heuristic,":[23],"lack":[24],"probabilistic":[25],"interpretation,":[26],"and":[27,33,97,100,117,124,135,137,156,177],"often":[28],"fail":[29],"to":[30],"indicate":[31],"where":[32],"how":[34],"much":[35],"the":[36],"can":[39],"be":[40],"trusted.":[41],"To":[42],"address":[43],"this":[44],"gap,":[45],"we":[46],"present":[47],"Trust3R,":[48],"a":[49,65,70,163],"lightweight":[50],"evidential":[51,67],"uncertainty":[52,85,148],"framework":[53],"3D":[56],"reconstruction.":[57],"Trust3R":[58,131],"combines":[59],"gated":[60],"residual":[61],"mean":[62],"refinement":[63],"with":[64,152],"Normal-Inverse-Wishart":[66],"head,":[68],"yielding":[69],"closed-form":[71],"multivariate":[72],"Student-t":[73],"distribution":[74],"per-point":[76],"geometric":[77,140],"uncertainty.":[78],"This":[79],"design":[80],"provides":[81],"probabilistically":[82],"grounded":[83],"pointmap":[84],"estimates":[86],"while":[87],"adding":[88],"moderate":[89],"inference":[90],"overhead.":[91],"We":[92],"evaluate":[93],"on":[94,160],"diverse":[95],"indoor":[96],"outdoor":[98],"benchmarks":[99],"compare":[101],"against":[102],"MASt3R's":[103],"built-in":[104],"map":[106],"as":[107,109,121],"well":[108],"common":[110],"uncertainty-aware":[111,168],"baselines":[112],"spanning":[113],"single-pass":[114],"heteroscedastic":[115],"regression":[116],"sampling-based":[118],"methods":[119],"such":[120],"MC":[122],"dropout":[123],"deep":[125],"ensembles.":[126],"Experimental":[127],"results":[128],"show":[129],"that":[130],"consistently":[132],"improves":[133,139],"risk-coverage":[134],"sparsification,":[136],"generally":[138],"accuracy.":[141],"These":[142],"gains":[143],"reflected":[145],"stronger":[147],"ranking":[149],"across":[150],"benchmarks,":[151],"25%":[153],"lower":[154,158],"AURC":[155],"41%":[157],"AUSE":[159],"ScanNet++,":[161],"providing":[162],"practical":[164],"reliability":[165],"signal":[166],"weighting":[169],"downstream":[171],"pipelines.":[173],"The":[174],"project":[175],"page":[176],"code":[178],"available":[180],"at":[181],"https://trust3r-z.github.io/.":[182]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-21T00:00:00"}