{"id":"https://openalex.org/W7141470729","doi":"https://doi.org/10.1109/icce67443.2026.11449823","title":"DAG-PU: Density-Aware Gaussian Modeling for Robust Point Cloud Upsampling","display_name":"DAG-PU: Density-Aware Gaussian Modeling for Robust Point Cloud Upsampling","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7141470729","doi":"https://doi.org/10.1109/icce67443.2026.11449823"},"language":null,"primary_location":{"id":"doi:10.1109/icce67443.2026.11449823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce67443.2026.11449823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Consumer Electronics (ICCE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130736959","display_name":"Jihoon You","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jihoon You","raw_affiliation_strings":["Chung-Ang University,Department of Artificial Intelligence,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Artificial Intelligence,Seoul,South Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130759042","display_name":"Injae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Injae Lee","raw_affiliation_strings":["Chung-Ang University,Department of Artificial Intelligence,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Artificial Intelligence,Seoul,South Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5094189183","display_name":"Joonki Paik","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonki Paik","raw_affiliation_strings":["Chung-Ang University Chung-Ang University,Department of Artificial Intelligence Department of Image,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University Chung-Ang University,Department of Artificial Intelligence Department of Image,Seoul,South Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5130736959"],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92847307,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.4814999997615814,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.4814999997615814,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.1590999960899353,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.08129999786615372,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.4059000015258789},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4018000066280365},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3781999945640564},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.3483999967575073},{"id":"https://openalex.org/keywords/point-process","display_name":"Point process","score":0.3131999969482422},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.311599999666214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4903999865055084},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.489300012588501},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.4059000015258789},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3700000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3497999906539917},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3483999967575073},{"id":"https://openalex.org/C88871306","wikidata":"https://www.wikidata.org/wiki/Q7208287","display_name":"Point process","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C166550679","wikidata":"https://www.wikidata.org/wiki/Q263400","display_name":"Gaussian network model","level":3,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce67443.2026.11449823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce67443.2026.11449823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Consumer Electronics (ICCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6166117191314697,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2115579991","https://openalex.org/W2963390820","https://openalex.org/W2963680153","https://openalex.org/W2997337685","https://openalex.org/W3175676582","https://openalex.org/W3184736166","https://openalex.org/W4214755140","https://openalex.org/W4311728943","https://openalex.org/W4323057578","https://openalex.org/W4385318467","https://openalex.org/W4386075817","https://openalex.org/W4401021670","https://openalex.org/W7131128247"],"related_works":[],"abstract_inverted_index":{"Point":[0,40],"cloud":[1,258],"upsampling":[2,25,123],"is":[3,53,58,236],"crucial":[4],"for":[5,239],"3D":[6,118,250],"reconstruction":[7,141],"and":[8,19,33,39,55,64,72,106,120,161,170,202,210,230,249],"autonomous":[9,245],"perception,":[10],"where":[11,253],"sparse":[12,76],"inputs":[13],"must":[14],"be":[15],"transformed":[16],"into":[17],"dense":[18,70],"geometrically":[20],"faithful":[21],"structures.":[22],"However,":[23],"existing":[24],"approaches\u2014including":[26],"MLP-based":[27],"methods,":[28],"GAN-driven":[29],"PU-GAN,":[30],"graph-based":[31],"PU-GCN,":[32],"transformer-enhanced":[34],"models":[35],"such":[36,242],"as":[37,115,243],"CRN":[38],"Transformer\u2014remain":[41],"limited":[42],"by":[43],"their":[44],"reliance":[45],"on":[46,167],"the":[47,97,104,122,130,168,183,187,223],"Chamfer":[48,99],"Distance":[49,100],"(CD).":[50],"Although":[51],"CD":[52,95,184],"simple":[54],"differentiable,":[56],"it":[57],"highly":[59],"sensitive":[60],"to":[61,67,132,186],"density":[62],"imbalance":[63],"outliers,":[65],"leading":[66],"over-smoothing":[68],"in":[69,75,102,197],"regions":[71,144],"geometric":[73,136,155,228],"distortions":[74,209],"or":[77,255],"structurally":[78],"irregular":[79,256],"areas.":[80],"To":[81],"address":[82],"these":[83,192],"limitations,":[84],"we":[85],"propose":[86],"DAG-PU,":[87],"a":[88,126,153],"density-aware":[89,158,231],"extension":[90],"of":[91,152,191,226],"PU-Gaussian":[92,181],"that":[93,234],"replaces":[94],"with":[96,125,145,199],"Density-Aware":[98],"(DCD)":[101],"both":[103],"coarse":[105],"refinement":[107],"stages.":[108],"Our":[109],"method":[110],"represents":[111],"each":[112],"input":[113],"point":[114,257],"an":[116],"anisotropic":[117,213],"Gaussian":[119,227],"optimizes":[121],"process":[124],"density-sensitive":[127],"metric,":[128],"allowing":[129],"model":[131],"better":[133],"capture":[134],"local":[135],"anisotropy":[137],"while":[138,175],"adaptively":[139],"balancing":[140],"quality":[142],"across":[143],"heterogeneous":[146],"densities.":[147],"The":[148],"proposed":[149],"framework":[150],"consists":[151],"Gaussian-based":[154],"encoding":[156],"module,":[157],"hierarchical":[159],"upsampling,":[160],"dual-stage":[162],"DCD":[163],"optimization.":[164],"Experimental":[165],"results":[166],"PU-GAN":[169],"PU1K":[171],"benchmarks":[172],"demonstrate":[173],"that,":[174],"DAG-PU":[176,206,235],"does":[177],"not":[178],"necessarily":[179],"outperform":[180],"under":[182],"metric\u2014due":[185],"uniformly":[188],"sampled":[189],"nature":[190],"datasets\u2014it":[193],"achieves":[194],"improved":[195],"robustness":[196],"scenarios":[198],"non-uniform":[200],"sampling":[201],"structural":[203],"sparsity.":[204],"Notably,":[205],"reduces":[207],"density-induced":[208],"preserves":[211],"fine-scale":[212],"structures":[214],"more":[215],"effectively":[216],"than":[217],"CD-optimized":[218],"baselines.":[219],"These":[220],"findings":[221],"highlight":[222],"complementary":[224],"advantages":[225],"modeling":[229],"optimization,":[232],"suggesting":[233],"well":[237],"suited":[238],"real-world":[240],"applications":[241],"LiDAR-based":[244],"driving,":[246],"aerial":[247],"mapping,":[248],"digital-twin":[251],"reconstruction,":[252],"nonuniform":[254],"distributions":[259],"are":[260],"ubiquitous.":[261]},"counts_by_year":[],"updated_date":"2026-03-29T06:01:01.467347","created_date":"2026-03-28T00:00:00"}