{"id":"https://openalex.org/W4413145934","doi":"https://doi.org/10.1109/cvpr52734.2025.02037","title":"Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks","display_name":"Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145934","doi":"https://doi.org/10.1109/cvpr52734.2025.02037"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.08320","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041291991","display_name":"Marwane Hariat","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Marwane Hariat","raw_affiliation_strings":["Institut Polytechnique de Paris,U2IS, ENSTA,Palaiseau,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,U2IS, ENSTA,Palaiseau,France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083582547","display_name":"Antoine Manzanera","orcid":"https://orcid.org/0000-0001-5718-411X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antoine Manzanera","raw_affiliation_strings":["Institut Polytechnique de Paris,U2IS, ENSTA,Palaiseau,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,U2IS, ENSTA,Palaiseau,France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027931470","display_name":"David Filliat","orcid":"https://orcid.org/0000-0002-5739-1618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Filliat","raw_affiliation_strings":["Institut Polytechnique de Paris,U2IS, ENSTA,Palaiseau,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,U2IS, ENSTA,Palaiseau,France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041291991"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.264954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21868","last_page":"21879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9398000240325928,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9398000240325928,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9168000221252441,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7679217457771301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.739228367805481},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6837674379348755},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.561486005783081},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4836893677711487},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4310721457004547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7679217457771301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.739228367805481},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6837674379348755},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.561486005783081},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4836893677711487},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4310721457004547}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.08320","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.08320","pdf_url":"https://arxiv.org/pdf/2605.08320","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05430193v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05430193","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2025, Nashville, France. pp.21868-21879, ⟨10.1109/CVPR52734.2025.02037⟩","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2605.08320","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08320","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:2605.08320","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.08320","pdf_url":"https://arxiv.org/pdf/2605.08320","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"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":{"Monocular":[0],"depth":[1,19,54,90],"estimation":[2],"(MDE)":[3],"with":[4,67],"self-supervised":[5,125],"training":[6,87],"approaches":[7],"struggles":[8],"in":[9,44,74,80,105,127],"low-texture":[10],"areas,":[11],"where":[12],"photometric":[13],"losses":[14],"may":[15],"lead":[16],"to":[17,62],"ambiguous":[18],"predictions.":[20],"To":[21],"address":[22],"this,":[23],"we":[24],"propose":[25],"a":[26,35],"novel":[27],"technique":[28,104],"that":[29,96],"enhances":[30],"spatial":[31],"information":[32],"by":[33,70],"applying":[34],"distance":[36,72,98],"transform":[37,73,99],"over":[38],"pre-semantic":[39,52,58],"contours,":[40,53],"augmenting":[41],"discriminative":[42],"power":[43],"low":[45],"texture":[46],"regions.":[47],"Our":[48],"approach":[49,78],"jointly":[50],"estimates":[51],"and":[55,91,116],"ego-motion.":[56,92],"The":[57],"contours":[59],"are":[60],"leveraged":[61],"produce":[63],"new":[64],"input":[65],"images,":[66],"variance":[68],"augmented":[69],"the":[71,86,97,101],"uniform":[75],"areas.":[76],"This":[77],"results":[79],"more":[81],"effective":[82],"loss":[83],"functions,":[84],"enhancing":[85],"process":[88],"for":[89],"We":[93],"demonstrate":[94],"theoretically":[95],"is":[100],"optimal":[102],"variance-augmenting":[103],"this":[106],"context.":[107],"Through":[108],"extensive":[109],"experiments":[110],"on":[111],"KITTI,":[112],"Cityscapes,":[113],"Waymo,":[114],"NYUv2":[115],"ScanNet":[117],"our":[118],"model":[119],"demonstrates":[120],"robust":[121],"performance,":[122],"surpassing":[123],"competing":[124],"methods":[126],"MDE.":[128]},"counts_by_year":[],"updated_date":"2026-05-15T08:27:34.491423","created_date":"2025-10-10T00:00:00"}