{"id":"https://openalex.org/W7126203607","doi":"https://doi.org/10.1007/s44443-026-00477-0","title":"R-TAFM: purely convolutional recurrent refinement for deployment-oriented monocular depth estimation","display_name":"R-TAFM: purely convolutional recurrent refinement for deployment-oriented monocular depth estimation","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7126203607","doi":"https://doi.org/10.1007/s44443-026-00477-0"},"language":"en","primary_location":{"id":"doi:10.1007/s44443-026-00477-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00477-0","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s44443-026-00477-0","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004548883","display_name":"Zhongkai Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongkai Zhou","raw_affiliation_strings":["Jiangsu Provincial Key Laboratory of Power Transmission and Distribution Equipment Technology, Hohai University, Changzhou, 213022, China"],"affiliations":[{"raw_affiliation_string":"Jiangsu Provincial Key Laboratory of Power Transmission and Distribution Equipment Technology, Hohai University, Changzhou, 213022, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124412703","display_name":"Xinnan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinnan Fan","raw_affiliation_strings":["College of Information Science and Engineering, Hohai University, Changzhou, 213200, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hohai University, Changzhou, 213200, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124397876","display_name":"Pengfei Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Shi","raw_affiliation_strings":["College of Artificial Intelligence and Automation, Hohai University, Changzhou, 213200, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence and Automation, Hohai University, Changzhou, 213200, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124319869","display_name":"Yuanxue Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanxue Xin","raw_affiliation_strings":["College of Information Science and Engineering, Hohai University, Changzhou, 213200, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hohai University, Changzhou, 213200, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124428025","display_name":"Congxuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I927504317","display_name":"Nanchang Hangkong University","ror":"https://ror.org/0369pvp92","country_code":"CN","type":"education","lineage":["https://openalex.org/I927504317"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congxuan Zhang","raw_affiliation_strings":["the Key Laboratory of Nondestructive Testing, Ministry of Education, Nanchang Hangkong University, Nanchang, 330063, China"],"affiliations":[{"raw_affiliation_string":"the Key Laboratory of Nondestructive Testing, Ministry of Education, Nanchang Hangkong University, Nanchang, 330063, China","institution_ids":["https://openalex.org/I927504317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124438132","display_name":"Yu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["College of Artificial Intelligence and Automation, Hohai University, Changzhou, 213200, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence and Automation, Hohai University, Changzhou, 213200, China","institution_ids":["https://openalex.org/I163340411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5124412703"],"corresponding_institution_ids":["https://openalex.org/I163340411"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22872551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.854200005531311,"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":0.854200005531311,"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":0.08190000057220459,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.010300000198185444,"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":0.5778999924659729},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48899999260902405},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4596000015735626},{"id":"https://openalex.org/keywords/reprojection-error","display_name":"Reprojection error","score":0.42590001225471497},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.4081999957561493},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3970000147819519},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3700999915599823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073999881744385},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5299999713897705},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45019999146461487},{"id":"https://openalex.org/C23903533","wikidata":"https://www.wikidata.org/wiki/Q17122739","display_name":"Reprojection error","level":3,"score":0.42590001225471497},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41999998688697815},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.40790000557899475},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.36890000104904175},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s44443-026-00477-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00477-0","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s44443-026-00477-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00477-0","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1901129140","https://openalex.org/W1905829557","https://openalex.org/W2115579991","https://openalex.org/W2117248802","https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W2300779272","https://openalex.org/W2340897893","https://openalex.org/W2520707372","https://openalex.org/W2531409750","https://openalex.org/W2609883120","https://openalex.org/W2752782242","https://openalex.org/W2883780447","https://openalex.org/W2884585870","https://openalex.org/W2890949887","https://openalex.org/W2963265330","https://openalex.org/W2963316641","https://openalex.org/W2963587345","https://openalex.org/W2963652981","https://openalex.org/W2963654727","https://openalex.org/W2964156315","https://openalex.org/W2964199361","https://openalex.org/W2982083293","https://openalex.org/W2985775862","https://openalex.org/W3003669105","https://openalex.org/W3007774126","https://openalex.org/W3034428934","https://openalex.org/W3034604951","https://openalex.org/W3034879369","https://openalex.org/W3082841037","https://openalex.org/W3107156787","https://openalex.org/W3119205652","https://openalex.org/W3152863269","https://openalex.org/W3157340408","https://openalex.org/W3167976421","https://openalex.org/W3173274332","https://openalex.org/W3173727695","https://openalex.org/W3174211490","https://openalex.org/W3175682855","https://openalex.org/W3198777869","https://openalex.org/W3204559841","https://openalex.org/W3206647015","https://openalex.org/W4224288444","https://openalex.org/W4225692545","https://openalex.org/W4285061034","https://openalex.org/W4293428446","https://openalex.org/W4297845938","https://openalex.org/W4297878068","https://openalex.org/W4312460030","https://openalex.org/W4312740558","https://openalex.org/W4312819733","https://openalex.org/W4386076206","https://openalex.org/W4386083069","https://openalex.org/W4390872248","https://openalex.org/W4391002602","https://openalex.org/W4399167840","https://openalex.org/W4402899901","https://openalex.org/W4404032514","https://openalex.org/W4405768708","https://openalex.org/W4409186742","https://openalex.org/W4413402787","https://openalex.org/W4417046463"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Monocular":[1],"depth":[2,76],"estimation":[3],"is":[4,95],"widely":[5],"used":[6],"for":[7],"navigation":[8],"and":[9,20,45,67,113,132,139,157],"scene":[10],"understanding,":[11],"yet":[12,100],"deployment":[13,54],"requires":[14],"balancing":[15],"accuracy":[16,173],"with":[17,31,83,97,162],"predictable":[18],"runtime":[19],"compact":[21],"models.":[22],"Many":[23],"recent":[24,178],"lightweight":[25,179],"designs":[26],"pair":[27],"depthwise":[28],"separable":[29],"convolutions":[30],"transformer":[32],"components":[33],"to":[34,103,147,175],"boost":[35],"accuracy,":[36],"which":[37,94],"typically":[38],"introduces":[39],"a":[40,64,79,84,90,104,115,140],"more":[41,50],"diverse":[42],"operator":[43],"set":[44],"can":[46],"make":[47],"realized":[48],"throughput":[49],"dependent":[51],"on":[52,110,114],"the":[53],"backend":[55],"in":[56,151],"practice.":[57],"Instead,":[58],"we":[59,122],"revisit":[60],"recurrent":[61,98],"refinement":[62,77],"from":[63],"deployment-oriented":[65],"perspective":[66],"introduce":[68,123],"R-TAFM,":[69],"purely":[70],"convolutional":[71],"framework":[72],"that":[73,128],"performs":[74],"iterative":[75],"at":[78],"fixed":[80],"working":[81],"resolution":[82],"parameter-shared":[85],"decoder.":[86],"We":[87],"further":[88],"derive":[89],"deployment-mode":[91],"variant,":[92],"R-TAFM-Fast,":[93],"trained":[96],"supervision":[99,149],"reduces":[101],"inference":[102],"single":[105],"decoder":[106],"pass,":[107],"lowering":[108],"latency":[109],"commodity":[111],"GPU":[112],"Jetson-class":[116],"embedded":[117],"GPU.":[118],"For":[119],"self-supervised":[120],"learning,":[121],"an":[124],"adaptive":[125],"reprojection":[126],"objective":[127],"jointly":[129],"handles":[130],"occlusions":[131],"independently":[133],"moving":[134],"objects":[135],"without":[136],"auxiliary":[137],"tasks,":[138],"neighborhood-consistent":[141],"correction":[142],"of":[143],"auto-masked":[144],"stationary":[145],"pixels":[146],"prevent":[148],"collapse":[150],"homogeneous":[152],"regions.":[153],"Both":[154],"quantitative":[155],"benchmarks":[156],"qualitative":[158],"assessments":[159],"demonstrate":[160],"that,":[161],"$$\\approx":[163],"$$":[164],"<mml:math":[165],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[166],"<mml:mo>\u2248</mml:mo>":[167],"</mml:math>":[168],"3.2M":[169],"parameters,":[170],"R-TAFM":[171],"achieves":[172],"comparable":[174],"or":[176],"exceeding":[177],"state-of-the-art":[180],"methods,":[181],"using":[182],"only":[183],"standard":[184],"convolutions.":[185]},"counts_by_year":[],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2026-02-01T00:00:00"}