{"id":"https://openalex.org/W4413917696","doi":"https://doi.org/10.1109/icra55743.2025.11128411","title":"SAM-Guided Pseudo Label Enhancement for Multi-Modal 3D Semantic Segmentation","display_name":"SAM-Guided Pseudo Label Enhancement for Multi-Modal 3D Semantic Segmentation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917696","doi":"https://doi.org/10.1109/icra55743.2025.11128411"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128411","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/A5060010918","display_name":"Mingyu Yang","orcid":"https://orcid.org/0000-0003-1301-6493"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingyu Yang","raw_affiliation_strings":["University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,USA,48109"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101917470","display_name":"Juan Lu","orcid":"https://orcid.org/0000-0001-5567-8933"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jitong Lu","raw_affiliation_strings":["University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,USA,48109"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014196508","display_name":"Hun-Seok Kim","orcid":"https://orcid.org/0000-0002-6658-5502"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hun-Seok Kim","raw_affiliation_strings":["University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,USA,48109"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060010918"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38258561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11133","last_page":"11140"},"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":0.9902999997138977,"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":0.9902999997138977,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9897000193595886,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.736540675163269},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6619124412536621},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5889121890068054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5491216778755188},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40026575326919556},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.349040687084198},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3398582339286804},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1416548192501068}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736540675163269},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6619124412536621},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5889121890068054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5491216778755188},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40026575326919556},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.349040687084198},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3398582339286804},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1416548192501068},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128411","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":37,"referenced_works":["https://openalex.org/W2117839996","https://openalex.org/W2194775991","https://openalex.org/W2788158258","https://openalex.org/W2798964604","https://openalex.org/W2885553657","https://openalex.org/W2962912109","https://openalex.org/W2963073217","https://openalex.org/W2963107255","https://openalex.org/W2963125977","https://openalex.org/W2963182550","https://openalex.org/W2963576229","https://openalex.org/W2968557240","https://openalex.org/W2972285644","https://openalex.org/W2990613095","https://openalex.org/W2991216808","https://openalex.org/W2999050151","https://openalex.org/W3034562924","https://openalex.org/W3035574168","https://openalex.org/W3035750252","https://openalex.org/W3108566666","https://openalex.org/W3137210930","https://openalex.org/W3177015573","https://openalex.org/W3201726317","https://openalex.org/W4226396592","https://openalex.org/W4312627498","https://openalex.org/W4312707458","https://openalex.org/W4312894203","https://openalex.org/W4313184971","https://openalex.org/W4382240089","https://openalex.org/W4389430914","https://openalex.org/W4390872645","https://openalex.org/W4390872955","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4401416464","https://openalex.org/W4403922060","https://openalex.org/W4408634392"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W4379231730","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W4389858081","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2501551404","https://openalex.org/W2714992399"],"abstract_inverted_index":{"Multi-modal":[0],"3D":[1,57,119,134,197],"semantic":[2,58],"segmentation":[3],"is":[4,25],"vital":[5],"for":[6,52,167],"applications":[7],"such":[8],"as":[9,48],"autonomous":[10],"driving":[11],"and":[12,39,122,173,215,231],"virtual":[13],"reality":[14],"(VR).":[15],"To":[16],"effectively":[17],"deploy":[18],"these":[19],"models":[20],"in":[21,55,70,158],"real-world":[22,40],"scenarios,":[23],"it":[24],"essential":[26],"to":[27,106,144,177,195],"employ":[28,174],"cross-domain":[29,53],"adaptation":[30,54,84,114,217,234],"techniques":[31],"that":[32,93,141,220],"bridge":[33],"the":[34,83,95,101,123,145,152,164,192,200,226,233],"gap":[35],"between":[36],"training":[37],"data":[38],"data.":[41],"Recently,":[42],"self-training":[43],"with":[44],"pseudo-labels":[45,63,72,153,230],"has":[46],"emerged":[47],"a":[49,118],"predominant":[50],"method":[51,150,223],"multi-modal":[56],"segmentation.":[59],"However,":[60],"generating":[61],"reliable":[62,109],"necessitates":[64],"stringent":[65],"constraints,":[66],"which":[67,190],"often":[68],"result":[69],"sparse":[71],"after":[73],"pruning.":[74],"This":[75],"sparsity":[76],"can":[77],"potentially":[78,142],"hinder":[79],"performance":[80,235],"improvement":[81],"during":[82],"process.":[85],"We":[86],"propose":[87],"an":[88],"image-guided":[89],"pseudo-label":[90],"enhancement":[91],"approach":[92],"leverages":[94],"complementary":[96],"2D":[97],"prior":[98],"knowledge":[99],"from":[100,126],"Segment":[102],"Anything":[103],"Model":[104],"(SAM)":[105],"introduce":[107,185],"more":[108],"pseudo-labels,":[110],"thereby":[111],"boosting":[112],"domain":[113,216],"performance.":[115],"Specifically,":[116],"given":[117],"point":[120],"cloud":[121],"SAM":[124,139,156,201],"masks":[125],"its":[127],"paired":[128],"image":[129],"data,":[130],"we":[131,162,184],"collect":[132],"all":[133,196],"points":[135,198],"covered":[136],"by":[137,207],"each":[138,155,168],"mask":[140,157,169,181,193,202],"belong":[143],"same":[146],"object.":[147],"Then":[148],"our":[149,221],"refines":[151],"within":[154,199],"two":[159],"steps.":[160],"First,":[161],"determine":[163],"class":[165],"label":[166,194],"using":[170],"majority":[171],"voting":[172],"various":[175],"constraints":[176],"filter":[178],"out":[179],"unreliable":[180],"labels.":[182],"Next,":[183],"Geometry-Aware":[186],"Progressive":[187],"Propagation":[188],"(GAPP)":[189],"propagates":[191],"while":[203],"avoiding":[204],"outliers":[205],"caused":[206],"2D-3D":[208],"misalignment.":[209],"Experiments":[210],"conducted":[211],"across":[212],"multiple":[213],"datasets":[214],"scenarios":[218],"demonstrate":[219],"proposed":[222],"significantly":[224],"increases":[225],"quantity":[227],"of":[228],"high-quality":[229],"enhances":[232],"over":[236],"baseline":[237],"methods.":[238]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}