{"id":"https://openalex.org/W2787219183","doi":null,"title":"Flat2Sphere: Learning Spherical Convolution for Fast Features from 360\u00b0 Imagery","display_name":"Flat2Sphere: Learning Spherical Convolution for Fast Features from 360\u00b0 Imagery","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2787219183","mag":"2787219183"},"language":"en","primary_location":{"id":"mag:2787219183","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1708.00919.pdf","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1708.00919.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103041770","display_name":"Yu-Chuan Su","orcid":"https://orcid.org/0000-0002-2711-6738","observed_orcids":["https://orcid.org/0000-0002-2711-6738"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-Chuan Su","raw_affiliation_strings":["The University of Texas at Austin, Austin, United States"],"raw_orcid":"https://orcid.org/0000-0002-2711-6738","affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012765543","display_name":"Kristen Lorraine Grauman","orcid":"https://orcid.org/0000-0002-9591-5873","observed_orcids":["https://orcid.org/0000-0002-9591-5873"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristen Grauman","raw_affiliation_strings":["The University of Texas at Austin, Austin, United States"],"raw_orcid":"https://orcid.org/0000-0002-9591-5873","affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"529","last_page":"539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8970000147819519,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8970000147819519,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.07010000199079514,"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"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.014700000174343586,"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/spherical-convolution","display_name":"spherical convolution","score":0.9409999847412109},{"id":"https://openalex.org/keywords/equirectangular-projection","display_name":"equirectangular projection","score":0.9679999947547913},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"feature extraction","score":0.7229999899864197},{"id":"https://openalex.org/keywords/spherical-convolutional-neural-networks","display_name":"spherical convolutional neural networks","score":0.5699999928474426},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.4309999942779541}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7774876356124878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415264844894409},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6698167324066162},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6433859467506409},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.46984046697616577},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4438645541667938},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.43635720014572144},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4165852665901184},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2856770157814026},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2787219183","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1708.00919.pdf","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2787219183","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1708.00919.pdf","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W566730006","https://openalex.org/W639708223","https://openalex.org/W753847829","https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1903029394","https://openalex.org/W2037227137","https://openalex.org/W2102605133","https://openalex.org/W2103189262","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2134670479","https://openalex.org/W2134797427","https://openalex.org/W2155893237","https://openalex.org/W2156303437","https://openalex.org/W2160398734","https://openalex.org/W2194775991","https://openalex.org/W2286929393","https://openalex.org/W2294370754","https://openalex.org/W2342662179","https://openalex.org/W2519882289","https://openalex.org/W2565955132","https://openalex.org/W2593745480","https://openalex.org/W2963983744"],"related_works":["https://openalex.org/W2963609011","https://openalex.org/W2744613173","https://openalex.org/W3201136692","https://openalex.org/W3089993621","https://openalex.org/W2969261403","https://openalex.org/W2807732111","https://openalex.org/W3088126257","https://openalex.org/W3090355507","https://openalex.org/W2995635588","https://openalex.org/W2982308754"],"abstract_inverted_index":{"While":[0],"360\u00b0":[1,37,87,104,125,179],"cameras":[2,32],"offer":[3],"tremendous":[4],"new":[5],"possibilities":[6],"in":[7,90,161,193],"vision,":[8],"graphics,":[9],"and":[10,127,129],"augmented":[11],"reality,":[12],"the":[13,55,99,108,113,131,184,196],"spherical":[14,77],"images":[15,29,38,126],"they":[16],"produce":[17],"make":[18],"core":[19],"feature":[20,122],"extraction":[21,123],"non-trivial.":[22],"Convolutional":[23],"neural":[24],"networks":[25,137],"(CNNs)":[26],"trained":[27],"on":[28,103],"from":[30],"perspective":[31,150],"yield":[33],"\u201cflat":[34,175],"filters,":[35],"yet":[36],"cannot":[39],"be":[40],"projected":[41],"to":[42,58,74,85,97,107,133,157,178],"a":[43,76,82,173],"single":[44],"plane":[45],"without":[46],"significant":[47],"distortion.":[48],"A":[49],"naive":[50],"solution":[51],"that":[52,80],"repeatedly":[53],"projects":[54],"viewing":[56,114],"sphere":[57],"all":[59],"tangent":[60],"planes":[61],"is":[62],"accurate,":[63],"but":[64],"much":[65],"too":[66],"computationally":[67],"intensive":[68],"for":[69,124,149],"real":[70],"problems.":[71],"We":[72,152],"propose":[73],"learn":[75],"convolutional":[78],"network":[79],"translates":[81],"planar":[83],"CNN":[84,166],"process":[86],"imagery":[88],"directly":[89],"its":[91],"equirectangular":[92],"projection.":[93],"Our":[94,181],"approach":[95,155],"learns":[96],"reproduce":[98],"flat":[100],"filter":[101],"outputs":[102],"data,":[105],"sensitive":[106],"varying":[109],"distortion":[110],"effects":[111],"across":[112],"sphere.":[115],"The":[116],"key":[117],"benefits":[118],"are":[119],"1)":[120],"efficient":[121],"video,":[128],"2)":[130],"ability":[132],"leverage":[134],"powerful":[135],"pre-trained":[136],"researchers":[138],"have":[139],"carefully":[140],"honed":[141],"(together":[142],"with":[143],"massive":[144],"labeled":[145],"image":[146],"training":[147],"sets)":[148],"images.":[151],"validate":[153],"our":[154],"compared":[156],"several":[158],"alternative":[159],"methods":[160],"terms":[162],"of":[163,191],"both":[164],"raw":[165],"output":[167],"accuracy":[168],"as":[169,171],"well":[170],"applying":[172],"state-of-the-art":[174],"object":[176],"detector":[177],"data.":[180],"method":[182],"yields":[183],"most":[185],"accurate":[186],"results":[187],"while":[188],"saving":[189],"orders":[190],"magnitude":[192],"computation":[194],"versus":[195],"existing":[197],"exact":[198],"reprojection":[199],"solution.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-02-23T00:00:00"}