{"id":"https://openalex.org/W4416749313","doi":"https://doi.org/10.1109/iros60139.2025.11247354","title":"Monocular One-Shot Metric-Depth Alignment for RGB-Based Robot Grasping","display_name":"Monocular One-Shot Metric-Depth Alignment for RGB-Based Robot Grasping","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749313","doi":"https://doi.org/10.1109/iros60139.2025.11247354"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012909716","display_name":"Teng Guo","orcid":"https://orcid.org/0000-0003-2429-0762"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Teng Guo","raw_affiliation_strings":["Rutgers University,Department of Computer Science,Piscataway,NJ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,Department of Computer Science,Piscataway,NJ,USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031296968","display_name":"Baichuan Huang","orcid":"https://orcid.org/0000-0002-9658-6071"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baichuan Huang","raw_affiliation_strings":["Rutgers University,Department of Computer Science,Piscataway,NJ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,Department of Computer Science,Piscataway,NJ,USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076210154","display_name":"Jingjin Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingjin Yu","raw_affiliation_strings":["Rutgers University,Department of Computer Science,Piscataway,NJ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,Department of Computer Science,Piscataway,NJ,USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102322142"],"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":"642","last_page":"649"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10653","display_name":"Robot Manipulation and Learning","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10812","display_name":"Human Pose and Action Recognition","score":0.005900000222027302,"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":0.005499999970197678,"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":0.6984000205993652},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5889000296592712},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5587000250816345},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.510699987411499},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.49160000681877136},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4586000144481659},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.38769999146461487}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8205000162124634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7906000018119812},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6984000205993652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6575000286102295},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5889000296592712},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5587000250816345},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.38769999146461487},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C136380597","wikidata":"https://www.wikidata.org/wiki/Q10508905","display_name":"Prehensile tail","level":2,"score":0.26460000872612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W575847903","https://openalex.org/W2115579991","https://openalex.org/W2798373498","https://openalex.org/W2955639361","https://openalex.org/W2986303149","https://openalex.org/W3035198432","https://openalex.org/W3035508487","https://openalex.org/W3035563424","https://openalex.org/W3089874271","https://openalex.org/W3171847116","https://openalex.org/W3173727695","https://openalex.org/W3174458495","https://openalex.org/W3202948970","https://openalex.org/W3207187156","https://openalex.org/W4285190019","https://openalex.org/W4312344659","https://openalex.org/W4312904920","https://openalex.org/W4382366145","https://openalex.org/W4383108845","https://openalex.org/W4383109008","https://openalex.org/W4385844595","https://openalex.org/W4390871919","https://openalex.org/W4390874575","https://openalex.org/W4395481595","https://openalex.org/W4396594854","https://openalex.org/W4401414450","https://openalex.org/W4402727359","https://openalex.org/W4415798746"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"6D":[1,19],"object":[2],"pose":[3,20],"estimation":[4,21,63,134],"is":[5],"a":[6,93,106,111],"prerequisite":[7],"for":[8,22],"successfully":[9],"completing":[10],"robotic":[11,23],"prehensile":[12],"and":[13,36,50,75,164],"non-prehensile":[14],"manipulation":[15,24],"tasks.":[16],"At":[17],"present,":[18],"generally":[25],"relies":[26],"on":[27,84,115,142,151,160],"depth":[28,62,104,129,133],"sensors":[29],"based":[30],"on,":[31],"e.g.,":[32],"structured":[33],"light,":[34],"time-of-flight,":[35],"stereo-vision,":[37],"which":[38],"can":[39],"be":[40],"expensive,":[41],"produce":[42],"noisy":[43],"output":[44],"(as":[45],"compared":[46],"with":[47],"RGB":[48,108],"cameras),":[49],"fail":[51,88],"to":[52,71,89,101],"handle":[53],"transparent":[54,152],"objects.":[55],"On":[56],"the":[57,143,149],"other":[58],"hand,":[59],"state-of-the-art":[60],"monocular":[61,96],"models":[64],"(MDEMs)":[65],"provide":[66],"only":[67],"affine-invariant":[68],"depths":[69],"up":[70],"an":[72],"unknown":[73],"scale":[74],"shift.":[76],"Metric":[77],"MDEMs":[78],"achieve":[79],"some":[80],"successful":[81],"zero-shot":[82],"results":[83],"public":[85],"datasets,":[86],"but":[87],"generalize.":[90],"We":[91],"propose":[92],"novel":[94],"framework,":[95],"one-shot":[97,112],"metric-depth":[98],"alignment,":[99],"MOMA,":[100],"recover":[102],"metric":[103],"from":[105],"single":[107],"image,":[109],"through":[110],"adaptation":[113],"building":[114],"MDEM":[116,150],"techniques.":[117],"MOMA":[118,146,169],"performs":[119],"scale-rotation-shift":[120],"alignments":[121],"during":[122],"camera":[123],"calibration,":[124],"guided":[125],"by":[126],"sparse":[127],"ground-truth":[128],"points,":[130],"enabling":[131],"accurate":[132],"without":[135],"additional":[136],"data":[137],"collection":[138],"or":[139],"model":[140],"retraining":[141],"testing":[144],"setup.":[145],"supports":[147],"fine-tuning":[148],"objects,":[153],"demonstrating":[154],"strong":[155],"generalization":[156],"capabilities.":[157],"Real-world":[158],"experiments":[159],"tabletop":[161],"2-finger":[162],"grasping":[163],"suction-based":[165],"bin-picking":[166],"applications":[167],"show":[168],"achieves":[170],"high":[171],"success":[172],"rates":[173],"in":[174],"diverse":[175],"tasks,":[176],"confirming":[177],"its":[178],"effectiveness.":[179]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}