{"id":"https://openalex.org/W7155071755","doi":"https://doi.org/10.48550/arxiv.2604.16976","title":"UGD: An Unsupervised Geometric Distance for Evaluating Real-world Noisy Point Cloud Denoising","display_name":"UGD: An Unsupervised Geometric Distance for Evaluating Real-world Noisy Point Cloud Denoising","publication_year":2026,"publication_date":"2026-04-18","ids":{"openalex":"https://openalex.org/W7155071755","doi":"https://doi.org/10.48550/arxiv.2604.16976"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.16976","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16976","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.16976","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134115273","display_name":"Zhiyong Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Su, Zhiyong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125976360","display_name":"Jincan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jincan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134182871","display_name":"Yonghui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yonghui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134119975","display_name":"Zheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134099621","display_name":"Weiqing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Weiqing","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5134115273"],"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":0.8355000019073486,"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":0.8355000019073486,"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/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.01640000008046627,"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/T11115","display_name":"Topology Optimization in Engineering","score":0.012199999764561653,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"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/point-cloud","display_name":"Point cloud","score":0.8992999792098999},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5572999715805054},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5145000219345093},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5115000009536743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5020999908447266},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4821999967098236},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47209998965263367},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4092000126838684}],"concepts":[{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.8992999792098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122999787330627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6071000099182129},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5572999715805054},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5145000219345093},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5115000009536743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5020999908447266},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4821999967098236},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4336000084877014},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25999999046325684},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2529999911785126},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.16976","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16976","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":"doi:10.48550/arxiv.2604.16976","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16976","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Point":[0],"cloud":[1,12,20,35,42,82,190,262],"denoising":[2,21,263],"is":[3,51,95,175],"a":[4,26,45,70,98,103,138,150,158,211],"fundamental":[5],"and":[6,36,109,191,225],"crucial":[7],"challenge":[8],"in":[9,25,54,197],"real-world":[10,55,79,250],"point":[11,19,34,41,60,81,88,107,130,155,189,261,269],"applications.":[13],"Existing":[14],"quantitative":[15,170],"evaluation":[16,259],"metrics":[17],"for":[18,78,168],"methods":[22,264],"are":[23,62],"implemented":[24],"supervised":[27,243],"manner,":[28],"which":[29,163,218],"requires":[30],"both":[31],"the":[32,37,116,120,124,128,166,169,173,178,187,192,198,203,236,254],"denoised":[33,129,188],"corresponding":[38],"ground-truth":[39,58,117,167],"clean":[40,59,106,154],"to":[43,96,118,242],"compute":[44],"representative":[46],"geometric":[47,75,125],"distance.":[48],"This":[49],"requirement":[50],"highly":[52],"problematic":[53],"scenarios,":[56],"where":[57],"clouds":[61,108,156],"often":[63],"unavailable.":[64],"In":[65],"this":[66,112,133],"paper,":[67],"we":[68,135,209],"propose":[69,210],"simple":[71],"yet":[72],"effective":[73],"unsupervised":[74,258],"distance":[76],"(UGD)":[77],"noisy":[80,87,268],"denoising,":[83],"calculated":[84],"solely":[85],"from":[86,102,149],"clouds.":[89,270],"The":[90],"core":[91],"idea":[92],"of":[93,105,127,152,181,186,260],"UGD":[94,174,238,256],"learn":[97,137],"patch-wise":[99,146,159,205],"prior":[100,113],"model":[101,114,196],"set":[104,151],"then":[110],"employ":[111],"as":[115,165,177],"quantify":[119],"degradation":[121],"by":[122,157],"measuring":[123],"variations":[126],"cloud.":[131],"To":[132,201],"end,":[134],"first":[136],"pristine":[139,153,194],"Gaussian":[140],"Mixture":[141],"Model":[142],"(GMM)":[143],"with":[144,231],"extracted":[145],"quality-aware":[147],"features":[148],"feature":[160,206],"extraction":[161,207],"network,":[162,208],"serves":[164],"evaluation.":[171],"Then,":[172],"defined":[176],"weighted":[179],"sum":[180],"distances":[182],"between":[183],"each":[184],"patch":[185,199],"learned":[193],"GMM":[195],"space.":[200],"train":[202],"employed":[204],"self-supervised":[212],"training":[213],"framework":[214],"through":[215],"multi-task":[216],"learning,":[217],"includes":[219],"pair-wise":[220],"quality":[221],"ranking,":[222],"distortion":[223,226],"classification,":[224],"distribution":[227],"prediction.":[228],"Quantitative":[229],"experiments":[230],"synthetic":[232],"noise":[233],"confirm":[234],"that":[235,253],"proposed":[237,255],"achieves":[239],"comparable":[240],"performance":[241],"full-reference":[244],"metrics.":[245],"Moreover,":[246],"experimental":[247],"results":[248],"on":[249,267],"data":[251],"demonstrate":[252],"enables":[257],"based":[265],"exclusively":[266]},"counts_by_year":[],"updated_date":"2026-04-22T06:07:44.442478","created_date":"2026-04-22T00:00:00"}