{"id":"https://openalex.org/W2581867180","doi":null,"title":"A Hybrid Approach to Wide-Baseline Image Matching.","display_name":"A Hybrid Approach to Wide-Baseline Image Matching.","publication_year":2017,"publication_date":"2017-01-24","ids":{"openalex":"https://openalex.org/W2581867180","mag":"2581867180"},"language":"en","primary_location":{"id":"mag:2581867180","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1701.06854","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":"submittedVersion","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/1701.06854","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102897810","display_name":"Rahul Mitra","orcid":"https://orcid.org/0009-0009-3506-7612","observed_orcids":["https://orcid.org/0009-0009-3506-7612"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahul Mitra","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0009-3506-7612","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072309171","display_name":"Jiakai Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiakai Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102706610","display_name":"Sharat Chandran","orcid":"https://orcid.org/0000-0002-2586-2032","observed_orcids":["https://orcid.org/0000-0002-2586-2032"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharat Chandran","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2586-2032","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113717585","display_name":"Arjun Jain","orcid":"https://orcid.org/0000-0003-4119-6217","observed_orcids":["https://orcid.org/0000-0003-4119-6217"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arjun Jain","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.00019999999494757503,"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":0.00019999999494757503,"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/correspondence-detection","display_name":"correspondence detection","score":0.5070000290870667},{"id":"https://openalex.org/keywords/siamese-convolutional-neural-network","display_name":"Siamese convolutional neural network","score":0.9010000228881836},{"id":"https://openalex.org/keywords/multi-view-stereo","display_name":"multi-view stereo","score":0.7239999771118164},{"id":"https://openalex.org/keywords/panorama-stitching","display_name":"panorama stitching","score":0.9120000004768372},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"affine transformation","score":0.8090000152587891},{"id":"https://openalex.org/keywords/homography","display_name":"homography","score":0.9580000042915344}],"concepts":[{"id":"https://openalex.org/C61265191","wikidata":"https://www.wikidata.org/wiki/Q767770","display_name":"Scale-invariant feature transform","level":3,"score":0.763705849647522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7386902570724487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7154797315597534},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6930426359176636},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.5759457945823669},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.5268009305000305},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5181659460067749},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4993584156036377},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4716602563858032},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40770941972732544},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3770372271537781},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18576881289482117},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2581867180","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1701.06854","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2581867180","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1701.06854","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1677409904","https://openalex.org/W1869500417","https://openalex.org/W1955055330","https://openalex.org/W2001790138","https://openalex.org/W2055685931","https://openalex.org/W2115362620","https://openalex.org/W2126060993","https://openalex.org/W2138621090","https://openalex.org/W2151103935","https://openalex.org/W2156116778","https://openalex.org/W2156598602","https://openalex.org/W2169561155","https://openalex.org/W2177274842","https://openalex.org/W3199643754"],"related_works":["https://openalex.org/W2735029438","https://openalex.org/W7098498071","https://openalex.org/W2348762170","https://openalex.org/W2608188450","https://openalex.org/W3195869412","https://openalex.org/W2340296683","https://openalex.org/W2061193322","https://openalex.org/W3123922547","https://openalex.org/W2944763401","https://openalex.org/W4385804956"],"abstract_inverted_index":{"Recent":[0],"works":[1],"such":[2,31,58,230,239],"as":[3,32,59,231,240],"DEEPDESC,":[4],"DEEPCOMPARE":[5],"have":[6,103],"proposed":[7],"the":[8,40,44,66,88,97,109,121,128,148,156,183,200,212,217,223],"learning":[9,92],"of":[10,25,69,90,114,117,127,130,147,177,214],"robust":[11],"local":[12],"image":[13,61],"descriptors":[14,30,102,229,238],"using":[15],"a":[16,77,91],"Siamese":[17],"convolutional":[18],"neural":[19],"network":[20],"directly":[21],"from":[22,182],"images":[23,169,192,204],"instead":[24],"handcrafting":[26],"them":[27,178],"like":[28],"traditional":[29,101,122],"SIFT":[33],"and":[34,137,152,174],"MROGH.":[35],"Though":[36],"these":[37],"algorithms":[38],"show":[39],"state-of-the-art":[41],"results":[42,219],"on":[43,163,222],"Multi-View":[45],"Stereo":[46],"(MVS)":[47],"dataset,":[48,111],"they":[49],"fail":[50],"to":[51,65,86,104,211,228],"accomplish":[52],"many":[53],"challenging":[54],"real":[55],"world":[56],"tasks":[57],"stitching":[60],"panoramas,":[62],"primarily":[63],"due":[64],"limited":[67],"performance":[68],"finding":[70],"correspondence.":[71,139],"\r\nIn":[72],"this":[73],"paper,":[74],"we":[75,83],"propose":[76,108],"novel":[78],"hybrid":[79],"algorithm":[80],"with":[81,96,112,135,193,205],"which":[82,167],"are":[84],"able":[85],"harness":[87],"power":[89],"based":[93],"approach":[94,162],"along":[95,134],"discriminative":[98],"advantages":[99],"that":[100,120],"offer.":[105],"We":[106,159,209],"also":[107,143],"PhotoSynth":[110,141],"size":[113],"an":[115],"order":[116],"magnitude":[118],"more":[119],"MVS":[123,157],"dataset":[124,142,202],"in":[125],"terms":[126],"number":[129],"scenes,":[131],"images,":[132],"patches":[133],"positive":[136],"negative":[138],"Our":[140],"has":[144],"better":[145],"coverage":[146],"overall":[149],"viewpoint,":[150],"scale,":[151],"lighting":[153],"challenges":[154],"than":[155],"dataset.":[158],"evaluate":[160],"our":[161,215],"two":[164],"data":[165],"sets":[166],"provides":[168],"having":[170],"high":[171],"viewpoints":[172],"difference":[173],"wide-baselines.":[175],"One":[176],"is":[179,199],"Graffiti":[180,225],"scene":[181,226],"Oxford":[184],"Affine":[185],"Covariant":[186],"Regions":[187],"Dataset":[188],"(ACRD)":[189],"for":[190,203],"matching":[191],"2D":[194],"affine":[195],"transformations.":[196,208],"The":[197],"other":[198,236],"Fountain-P11":[201],"3D":[206],"projective":[207],"report,":[210],"best":[213,218],"knowledge,":[216],"till":[220],"date":[221],"ACRD":[224],"compared":[227],"SIFT,":[232],"MROGH":[233],"or":[234],"any":[235],"learnt":[237],"DEEPDESC.":[241]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2017-02-03T00:00:00"}