{"id":"https://openalex.org/W7158984279","doi":"https://doi.org/10.48550/arxiv.2604.25936","title":"SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces","display_name":"SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces","publication_year":2026,"publication_date":"2026-04-15","ids":{"openalex":"https://openalex.org/W7158984279","doi":"https://doi.org/10.48550/arxiv.2604.25936"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.25936","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25936","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.25936","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134915972","display_name":"Chuanxiang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Chuanxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134886515","display_name":"Junhui Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Junhui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134885921","display_name":"Yuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134916367","display_name":"Siyu Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Siyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007389144","display_name":"Guangshun Wei","orcid":"https://orcid.org/0000-0002-6045-4392"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Guangshun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134897602","display_name":"Taku Komura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Komura, Taku","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134883927","display_name":"Yuanfeng Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yuanfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134925439","display_name":"Wenping Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenping","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":0.8568000197410583,"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":0.8568000197410583,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.025299999862909317,"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/T12417","display_name":"Morphological variations and asymmetry","score":0.013700000010430813,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6572999954223633},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5932999849319458},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.569599986076355},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.44850000739097595},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4196000099182129},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4178999960422516}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6572999954223633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6118999719619751},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5932999849319458},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.569599986076355},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5126000046730042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46299999952316284},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.44850000739097595},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4178999960422516},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.3580999970436096},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2831999957561493},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C29123130","wikidata":"https://www.wikidata.org/wiki/Q874709","display_name":"Computational geometry","level":2,"score":0.26660001277923584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.25936","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25936","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.25936","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25936","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":"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":{"Implicit":[0],"neural":[1,58,91,213],"representations":[2,27],"are":[3],"powerful":[4],"for":[5,124],"geometric":[6,54],"modeling,":[7],"but":[8],"their":[9],"practical":[10],"use":[11],"is":[12,139,162],"often":[13],"limited":[14],"by":[15,84],"the":[16,38,45,66,128,137,178,207],"high":[17],"computational":[18,71,81,183],"cost":[19],"of":[20,211],"network":[21,68,99,129,171,180],"evaluations.":[22],"We":[23],"observe":[24],"that":[25,42,201],"implicit":[26,59,92,117,146,212],"require":[28],"progressively":[29],"lower":[30],"accuracy":[31],"as":[32,149,159],"query":[33,63,209],"points":[34,64],"move":[35],"farther":[36],"from":[37],"target":[39],"surface,":[40],"and":[41,70,77,181,188],"even":[43],"within":[44],"same":[46,67],"iso-surface,":[47],"representation":[48,94],"difficulty":[49],"varies":[50],"spatially":[51,97],"with":[52,65,96,109],"local":[53],"complexity.":[55],"However,":[56],"conventional":[57],"models":[60],"evaluate":[61],"all":[62],"depth":[69,100,121,130],"cost,":[72],"ignoring":[73],"this":[74,85],"spatial":[75,126],"variation":[76],"thereby":[78],"incurring":[79],"substantial":[80],"waste.":[82],"Motivated":[83],"observation,":[86],"we":[87],"propose":[88],"an":[89,154],"efficient":[90],"geometry":[93],"framework":[95],"adaptive":[98],"(SAND).":[101],"SAND":[102],"leverages":[103],"a":[104,110,140,160],"volumetric":[105,120],"network-depth":[106],"map":[107,122],"together":[108],"tailed":[111],"multi-layer":[112],"perceptron":[113],"(T-MLP)":[114],"to":[115,132,144,158,164,173,185],"model":[116],"representation.":[118],"The":[119],"records,":[123],"each":[125,165],"region,":[127],"required":[131],"achieve":[133],"sufficient":[134],"accuracy,":[135],"while":[136,193],"T-MLP":[138],"modified":[141],"MLP":[142],"designed":[143],"learn":[145],"functions":[147],"such":[148],"signed":[150],"distance":[151],"functions,":[152],"where":[153],"output":[155],"branch,":[156],"referred":[157],"tail,":[161],"attached":[163],"hidden":[166],"layer.":[167],"This":[168],"design":[169],"allows":[170],"evaluation":[172],"terminate":[174],"adaptively":[175],"without":[176],"traversing":[177],"full":[179],"directs":[182],"resources":[184],"geometrically":[186],"important":[187],"complex":[189],"regions,":[190],"improving":[191],"efficiency":[192],"preserving":[194],"high-fidelity":[195],"representations.":[196,214],"Extensive":[197],"experimental":[198],"results":[199],"demonstrate":[200],"our":[202],"approach":[203],"can":[204],"significantly":[205],"improve":[206],"inference-time":[208],"speed":[210]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-01T00:00:00"}