{"id":"https://openalex.org/W3029631549","doi":"https://doi.org/10.1109/icip40778.2020.9190764","title":"Self-Attention Dense Depth Estimation Network for Unrectified Video Sequences","display_name":"Self-Attention Dense Depth Estimation Network for Unrectified Video Sequences","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3029631549","doi":"https://doi.org/10.1109/icip40778.2020.9190764","mag":"3029631549"},"language":"en","primary_location":{"id":"doi:10.1109/icip40778.2020.9190764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.14313","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alwyn Mathew","orcid":null},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Alwyn Mathew","raw_affiliation_strings":["Indian Institute of Technology Patna, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aditya Prakash Patra","orcid":null},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Prakash Patra","raw_affiliation_strings":["Indian Institute of Technology Patna, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jimson Mathew","orcid":null},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jimson Mathew","raw_affiliation_strings":["Indian Institute of Technology Patna, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, India","institution_ids":["https://openalex.org/I132153292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":null,"apc_paid":null,"fwci":0.3829,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60210095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2810","last_page":"2814"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9998999834060669,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9998999834060669,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9973999857902527,"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/monocular","display_name":"Monocular","score":0.6560999751091003},{"id":"https://openalex.org/keywords/depth-map","display_name":"Depth map","score":0.5778999924659729},{"id":"https://openalex.org/keywords/lidar","display_name":"Lidar","score":0.4706999957561493},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.453000009059906},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.43959999084472656},{"id":"https://openalex.org/keywords/measured-depth","display_name":"Measured depth","score":0.42480000853538513},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3635999858379364},{"id":"https://openalex.org/keywords/radar-imaging","display_name":"Radar imaging","score":0.3634999990463257}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8235999941825867},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7639999985694885},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6560999751091003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6010000109672546},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.5778999924659729},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.453000009059906},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.43959999084472656},{"id":"https://openalex.org/C113346285","wikidata":"https://www.wikidata.org/wiki/Q6804193","display_name":"Measured depth","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C10929652","wikidata":"https://www.wikidata.org/wiki/Q7279985","display_name":"Radar imaging","level":3,"score":0.3634999990463257},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C2987632653","wikidata":"https://www.wikidata.org/wiki/Q7611220","display_name":"Stereo image","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C35861506","wikidata":"https://www.wikidata.org/wiki/Q17141434","display_name":"Stereo cameras","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C84824328","wikidata":"https://www.wikidata.org/wiki/Q4633097","display_name":"2D to 3D conversion","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip40778.2020.9190764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.14313","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.14313","pdf_url":"https://arxiv.org/pdf/2005.14313","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.14313","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.14313","pdf_url":"https://arxiv.org/pdf/2005.14313","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2115579991","https://openalex.org/W2194775991","https://openalex.org/W2520707372","https://openalex.org/W2603777577","https://openalex.org/W2609883120","https://openalex.org/W2963583471","https://openalex.org/W2963906250","https://openalex.org/W2985775862","https://openalex.org/W6685261749","https://openalex.org/W6697658144","https://openalex.org/W6752378368","https://openalex.org/W6755644832","https://openalex.org/W6757193880"],"related_works":[],"abstract_inverted_index":{"The":[0,58],"dense":[1],"depth":[2,26,33,46,63,83,117],"estimation":[3,47,64],"of":[4,56,95],"a":[5,54,80],"3D":[6],"scene":[7],"has":[8,52],"numerous":[9],"applications,":[10],"mainly":[11],"in":[12],"robotics":[13],"and":[14,17,35,70,84],"surveillance.":[15],"LiDAR":[16],"radar":[18],"sensors":[19,30],"are":[20,36],"the":[21,67,96,99],"hardware":[22],"solution":[23],"for":[24,87,116],"real-time":[25],"estimation,":[27],"but":[28],"these":[29],"produce":[31],"sparse":[32],"maps":[34],"sometimes":[37],"unreliable.":[38],"In":[39],"recent":[40],"years":[41],"research":[42],"aimed":[43],"at":[44],"tackling":[45],"using":[48],"single":[49],"2D":[50],"image":[51],"received":[53],"lot":[55],"attention.":[57],"deep":[59],"learning":[60],"based":[61,82],"self-supervised":[62],"methods":[65],"from":[66],"rectified":[68,114],"stereo":[69],"monocular":[71],"video":[72],"frames":[73],"have":[74],"shown":[75],"promising":[76],"results.":[77],"We":[78,90],"propose":[79],"self-attention":[81],"ego-motion":[85],"network":[86],"unrectified":[88],"images.":[89],"also":[91],"introduce":[92],"non-differentiable":[93],"distortion":[94],"camera":[97],"into":[98],"training":[100],"pipeline.":[101],"Our":[102],"approach":[103],"performs":[104],"competitively":[105],"when":[106],"compared":[107],"to":[108],"other":[109],"established":[110],"approaches":[111],"that":[112],"used":[113],"images":[115],"estimation.":[118]},"counts_by_year":[{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2020-06-05T00:00:00"}