{"id":"https://openalex.org/W4413918342","doi":"https://doi.org/10.1109/icra55743.2025.11128401","title":"Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion","display_name":"Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413918342","doi":"https://doi.org/10.1109/icra55743.2025.11128401"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102766810","display_name":"Jiangyuan Liu","orcid":"https://orcid.org/0000-0001-8467-857X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiangyuan Liu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022867743","display_name":"Hongxuan Ma","orcid":"https://orcid.org/0000-0001-6422-1441"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxuan Ma","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112724309","display_name":"Yuxin Guo","orcid":"https://orcid.org/0009-0008-5036-2575"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Guo","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111066159","display_name":"Yuhao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Zhao","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100610536","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0001-6344-2824"},"institutions":[{"id":"https://openalex.org/I90090648","display_name":"Shijiazhuang Tiedao University","ror":"https://ror.org/022e9e065","country_code":"CN","type":"education","lineage":["https://openalex.org/I90090648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["School of Information Science and Technology, Shijiazhuang Tiedao University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Shijiazhuang Tiedao University","institution_ids":["https://openalex.org/I90090648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407147","display_name":"Sui Wei","orcid":"https://orcid.org/0009-0004-4507-7754"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Sui","raw_affiliation_strings":["D-Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D-Robotics","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108286207","display_name":"Wei Zou","orcid":"https://orcid.org/0000-0003-4215-5361"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zou","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102766810"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":7.9521,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.97405078,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11162","last_page":"11168"},"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":0.9979000091552734,"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":0.9979000091552734,"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":0.986299991607666,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9853000044822693,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7706760168075562},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7566119432449341},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6865880489349365},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6733347177505493},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6557961702346802},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.575644850730896},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.569756805896759},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5341092348098755},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3459670841693878}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7706760168075562},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7566119432449341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6865880489349365},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6733347177505493},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6557961702346802},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.575644850730896},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.569756805896759},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5341092348098755},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3459670841693878},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2889002172","https://openalex.org/W2895401575","https://openalex.org/W2963896186","https://openalex.org/W3035618398","https://openalex.org/W3089874271","https://openalex.org/W3109733326","https://openalex.org/W3138516171","https://openalex.org/W3153051248","https://openalex.org/W3171847116","https://openalex.org/W4200150166","https://openalex.org/W4214520160","https://openalex.org/W4221152259","https://openalex.org/W4285190019","https://openalex.org/W4285505783","https://openalex.org/W4289752563","https://openalex.org/W4312344659","https://openalex.org/W4312601209","https://openalex.org/W4312866343","https://openalex.org/W4327807853","https://openalex.org/W4383108397","https://openalex.org/W4383109008","https://openalex.org/W4383109367","https://openalex.org/W4383988917","https://openalex.org/W4385767327","https://openalex.org/W4387790087","https://openalex.org/W4401414619"],"related_works":["https://openalex.org/W200819717","https://openalex.org/W2032269556","https://openalex.org/W1991834176","https://openalex.org/W2944448661","https://openalex.org/W2064421702","https://openalex.org/W4253756925","https://openalex.org/W2805523177","https://openalex.org/W2131956013","https://openalex.org/W2036566443","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Transparent":[0],"object":[1],"perception":[2,109],"is":[3,67],"indispensable":[4],"for":[5,123],"numerous":[6],"robotic":[7],"tasks.":[8,102],"However,":[9],"accurately":[10],"segmenting":[11],"and":[12,46,54,75,92,131,142,159],"estimating":[13],"the":[14,41,47,68,98],"depth":[15,76],"of":[16,78,110,149],"transparent":[17,79],"objects":[18],"remain":[19],"challenging":[20,129],"due":[21],"to":[22,52,70],"complex":[23],"optical":[24],"properties.":[25],"Existing":[26],"methods":[27,144],"primarily":[28],"delve":[29],"into":[30],"only":[31,82,153],"one":[32],"task":[33],"using":[34],"extra":[35],"inputs":[36],"or":[37],"specialized":[38],"sensors,":[39],"neglecting":[40],"valuable":[42],"interactions":[43],"among":[44],"tasks":[45],"subsequent":[48],"refinement":[49],"process,":[50],"leading":[51],"suboptimal":[53],"blurry":[55],"predictions.":[56],"To":[57],"address":[58],"these":[59],"issues,":[60],"we":[61,87,112],"propose":[62],"a":[63,83,89,146,154],"monocular":[64],"framework,":[65],"which":[66,118],"first":[69],"excel":[71],"in":[72],"both":[73],"segmentation":[74],"estimation":[77],"objects,":[80,111],"with":[81,152],"single-image":[84],"input.":[85,157],"Specifically,":[86],"devise":[88],"novel":[90],"semantic":[91],"geometric":[93],"fusion":[94],"module,":[95],"effectively":[96],"integrating":[97],"multi-scale":[99],"information":[100],"between":[101],"In":[103],"addition,":[104],"drawing":[105],"inspiration":[106],"from":[107],"human":[108],"further":[113],"incorporate":[114],"an":[115],"iterative":[116],"strategy,":[117],"progressively":[119],"refines":[120],"initial":[121],"features":[122],"clearer":[124],"results.":[125],"Experiments":[126],"on":[127],"two":[128],"synthetic":[130],"real-world":[132],"datasets":[133],"demonstrate":[134],"that":[135],"our":[136],"model":[137],"surpasses":[138],"state-of-the-art":[139],"monocular,":[140],"stereo,":[141],"multi-view":[143],"by":[145],"large":[147],"margin":[148],"about":[150],"38.8%-46.2%":[151],"single":[155],"RGB":[156],"Codes":[158],"models":[160],"are":[161],"publicly":[162],"available":[163],"at":[164],"https://github.com/L-J-Yuan/MODEST.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}