{"id":"https://openalex.org/W7161540820","doi":"https://doi.org/10.48550/arxiv.2605.15923","title":"Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction","display_name":"Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161540820","doi":"https://doi.org/10.48550/arxiv.2605.15923"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.15923","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15923","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":"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.2605.15923","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113135621","display_name":"Chun-Peng Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Chun-Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107875707","display_name":"Shaoxiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shaoxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046969927","display_name":"Alain Pagani","orcid":"https://orcid.org/0000-0002-5136-0837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pagani, Alain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136360825","display_name":"Dariu Gavrila","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gavrila, Dariu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001917215","display_name":"Holger Caesar","orcid":"https://orcid.org/0000-0001-5099-6297"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caesar, Holger","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":0.8431000113487244,"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":0.8431000113487244,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.020800000056624413,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.018300000578165054,"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/encoder","display_name":"Encoder","score":0.6270999908447266},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5473999977111816},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.510699987411499},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.4643000066280365},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4244999885559082},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4194999933242798},{"id":"https://openalex.org/keywords/scale-invariance","display_name":"Scale invariance","score":0.3813999891281128},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3725999891757965},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.3650999963283539}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6270999908447266},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5288000106811523},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.510699987411499},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44620001316070557},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41200000047683716},{"id":"https://openalex.org/C135593079","wikidata":"https://www.wikidata.org/wiki/Q1750766","display_name":"Scale invariance","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3018999993801117},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C2777894999","wikidata":"https://www.wikidata.org/wiki/Q4781758","display_name":"Approx","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.15923","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15923","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":"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.2605.15923","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15923","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":"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":{"Modern":[0],"image":[1],"encoders":[2,31],"achieve":[3,33],"high":[4,146],"generalization":[5,35],"by":[6,180],"decoupling":[7],"semantic":[8,82],"meaning":[9],"from":[10],"resolution,":[11],"an":[12,196],"ability":[13],"yet":[14],"to":[15,32,44,51,71,129],"be":[16],"fully":[17],"realized":[18],"in":[19,64,201],"the":[20,25,113,127,175],"3D":[21,28],"domain.":[22],"We":[23],"investigate":[24],"failure":[26],"of":[27,116,183,199],"point":[29,92,118],"cloud":[30,93],"similar":[34],"and":[36,47,75,98,104,153,170,195],"find":[37,121],"that":[38,95,122],"existing":[39],"models":[40,69],"are":[41,187],"highly":[42],"sensitive":[43],"sampling":[45],"resolution":[46,142,169],"scale":[48,97,177],"changes,":[49],"leading":[50],"significant":[52,138],"performance":[53,139],"degradation.":[54],"This":[55],"sensitivity":[56],"is":[57,111,178],"a":[58,91,149,162,171,181,190],"major":[59],"bottleneck":[60],"for":[61],"real-world":[62],"deployment":[63],"robotics,":[65],"as":[66],"it":[67],"suggests":[68],"overfit":[70],"specific":[72],"quantization":[73],"densities":[74],"object":[76],"scales":[77],"rather":[78],"than":[79],"learning":[80],"invariant":[81],"features.":[83],"To":[84],"mitigate":[85],"this":[86,123],"dependency,":[87],"we":[88,120],"propose":[89],"Invaria,":[90],"encoder":[94,136],"achieves":[96,137,161],"density":[99],"invariance":[100],"through":[101,148],"next-resolution":[102],"prediction":[103],"receptive":[105],"field":[106],"calibration.":[107],"While":[108],"our":[109],"objective":[110,125],"not":[112],"explicit":[114],"generation":[115],"high-resolution":[117],"clouds,":[119],"training":[124],"encourages":[126],"model":[128,151,193],"learn":[130],"robust,":[131],"structural":[132],"invariants.":[133],"The":[134],"resulting":[135],"gains":[140,186],"during":[141],"shifts":[143],"while":[144],"maintaining":[145],"efficiency":[147],"compact":[150],"size":[152,194],"reduced":[154,179],"token":[155],"requirements.":[156],"Specifically,":[157],"on":[158],"ScanNet,":[159],"Invaria":[160],"56.0\\%":[163],"higher":[164],"mIoU":[165],"at":[166],"3$\\times$":[167],"lower":[168],"20\\%":[172],"improvement":[173],"when":[174],"objects":[176],"factor":[182],"3.":[184],"These":[185],"achieved":[188],"with":[189],"45\\%":[191],"smaller":[192],"average":[197],"reduction":[198],"40\\%":[200],"input":[202],"tokens.":[203]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-19T00:00:00"}