{"id":"https://openalex.org/W4405254196","doi":"https://doi.org/10.48550/arxiv.2412.06488","title":"Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential Information","display_name":"Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential Information","publication_year":2024,"publication_date":"2024-12-09","ids":{"openalex":"https://openalex.org/W4405254196","doi":"https://doi.org/10.48550/arxiv.2412.06488"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2412.06488","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.06488","pdf_url":"https://arxiv.org/pdf/2412.06488","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.06488","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100576907","display_name":"Kuan Xu","orcid":"https://orcid.org/0000-0001-8682-0824"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xu, Kuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101529111","display_name":"Zeyu Jiang","orcid":"https://orcid.org/0000-0002-4151-9496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Zeyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062455018","display_name":"Haozhi Cao","orcid":"https://orcid.org/0000-0001-7703-3490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Haozhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050656216","display_name":"Shenghai Yuan","orcid":"https://orcid.org/0009-0000-4850-2278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Shenghai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337649","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0003-0985-3221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100531722","display_name":"Lihua Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Lihua","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100576907"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962999820709229,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962999820709229,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.979200005531311,"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/encoding","display_name":"Encoding (memory)","score":0.7528181076049805},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5735893249511719},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48110431432724},{"id":"https://openalex.org/keywords/coordinate-system","display_name":"Coordinate system","score":0.4309769570827484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3927536606788635}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7528181076049805},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5735893249511719},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48110431432724},{"id":"https://openalex.org/C80551277","wikidata":"https://www.wikidata.org/wiki/Q11210","display_name":"Coordinate system","level":2,"score":0.4309769570827484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3927536606788635}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2412.06488","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.06488","pdf_url":"https://arxiv.org/pdf/2412.06488","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.06488","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.06488","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":"pmh:oai:arXiv.org:2412.06488","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.06488","pdf_url":"https://arxiv.org/pdf/2412.06488","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405254196.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Scene":[0],"Coordinate":[1],"Regression":[2],"(SCR)":[3],"is":[4],"a":[5,63,93],"visual":[6],"localization":[7],"technique":[8],"that":[9,95,126],"utilizes":[10,96],"deep":[11],"neural":[12],"networks":[13],"(DNN)":[14],"to":[15,39,57,77,155],"directly":[16],"regress":[17],"2D-3D":[18],"correspondences":[19],"for":[20,66],"camera":[21],"pose":[22],"estimation.":[23],"However,":[24],"current":[25],"SCR":[26,54,59,133],"methods":[27],"often":[28],"face":[29],"challenges":[30],"in":[31,112],"handling":[32],"repetitive":[33,115],"textures":[34],"and":[35,52,70,102,122,148],"meaningless":[36],"areas":[37],"due":[38],"their":[40],"reliance":[41],"on":[42],"implicit":[43,109],"triangulation.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,61,91],"propose":[49,62],"an":[50],"efficient":[51],"accurate":[53],"system.":[55],"Compared":[56],"existing":[58],"methods,":[60],"unified":[64],"architecture":[65],"both":[67,100],"scene":[68],"encoding":[69,80],"salient":[71],"keypoint":[72],"detection,":[73],"allowing":[74],"our":[75,144,158],"system":[76,129],"prioritize":[78],"the":[79,108,127,140,150,162,169],"of":[81,143],"informative":[82],"regions.":[83],"This":[84],"design":[85],"significantly":[86],"improves":[87,139],"computational":[88],"efficiency.":[89,171],"Additionally,":[90],"introduce":[92],"mechanism":[94],"sequential":[97],"information":[98],"during":[99],"mapping":[101],"relocalization.":[103],"The":[104],"proposed":[105,128],"method":[106],"enhances":[107],"triangulation,":[110],"especially":[111],"environments":[113],"with":[114],"textures.":[116],"Comprehensive":[117],"experiments":[118],"conducted":[119],"across":[120],"indoor":[121],"outdoor":[123],"datasets":[124],"demonstrate":[125],"outperforms":[130],"state-of-the-art":[131],"(SOTA)":[132],"methods.":[134],"Our":[135],"single-frame":[136],"relocalization":[137],"mode":[138,160],"recall":[141,163],"rate":[142,164],"baseline":[145],"by":[146,165],"6.4%":[147],"increases":[149,161],"running":[151],"speed":[152],"from":[153],"56Hz":[154],"90Hz.":[156],"Furthermore,":[157],"sequence-based":[159],"11%":[166],"while":[167],"maintaining":[168],"original":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2024-12-12T00:00:00"}