{"id":"https://openalex.org/W4416747939","doi":"https://doi.org/10.1109/iros60139.2025.11247636","title":"CDIS : Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging","display_name":"CDIS : Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416747939","doi":"https://doi.org/10.1109/iros60139.2025.11247636"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247636","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":"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/A5024866431","display_name":"Juno Kim","orcid":"https://orcid.org/0000-0003-1300-9875"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juno Kim","raw_affiliation_strings":["Seoul National University,Interdisciplinary Program in AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Interdisciplinary Program in AI","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009471318","display_name":"Hye\u2010Jung Yoon","orcid":"https://orcid.org/0000-0002-3534-3295"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hye-Jung Yoon","raw_affiliation_strings":["Seoul National University,Interdisciplinary Program in AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Interdisciplinary Program in AI","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yesol Park","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yesol Park","raw_affiliation_strings":["Seoul National University,Interdisciplinary Program in AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Interdisciplinary Program in AI","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110585967","display_name":"Byoung Tak Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoung-Tak Zhang","raw_affiliation_strings":["Seoul National University,Interdisciplinary Program in AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Interdisciplinary Program in AI","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42402003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4269","last_page":"4274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.30730000138282776,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.30730000138282776,"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":0.19040000438690186,"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":0.09529999643564224,"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/segmentation","display_name":"Segmentation","score":0.7182999849319458},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5889000296592712},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4546999931335449},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4447999894618988},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4187000095844269},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38530001044273376},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3684000074863434},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3628999888896942}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7228000164031982},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7182999849319458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695900022983551},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6521999835968018},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5889000296592712},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3628999888896942},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3407999873161316},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29750001430511475},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247636","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":23,"referenced_works":["https://openalex.org/W1987648924","https://openalex.org/W1999478155","https://openalex.org/W2898231767","https://openalex.org/W2904332125","https://openalex.org/W2964339842","https://openalex.org/W4312649925","https://openalex.org/W4312815172","https://openalex.org/W4383109105","https://openalex.org/W4386076523","https://openalex.org/W4390873101","https://openalex.org/W4390873847","https://openalex.org/W4390874575","https://openalex.org/W4402667898","https://openalex.org/W4402704512","https://openalex.org/W4402727277","https://openalex.org/W4402733570","https://openalex.org/W4402733574","https://openalex.org/W4403889366","https://openalex.org/W4403906550","https://openalex.org/W4404722414","https://openalex.org/W4405785238","https://openalex.org/W4413513992","https://openalex.org/W4413918264"],"related_works":[],"abstract_inverted_index":{"Class-agnostic":[0],"3D":[1,33,47,53,72,93,98],"instance":[2,30,64,99],"segmentation":[3],"is":[4],"critical":[5],"for":[6,19],"robotic":[7],"systems":[8],"operating":[9],"in":[10],"unknown":[11],"environments,":[12],"enabling":[13],"perception":[14],"of":[15],"previously":[16],"unseen":[17],"objects":[18],"reliable":[20],"manipulation":[21],"and":[22,34,44,68,80,115,124],"navigation.":[23],"Existing":[24],"approaches":[25],"typically":[26],"project":[27],"per-frame":[28],"2D":[29,63,79,88],"masks":[31,65],"into":[32],"merge":[35],"them,":[36],"which":[37],"often":[38],"breaks":[39],"object":[40],"identities":[41],"across":[42,66],"time":[43],"yields":[45],"fragmented":[46],"instances.":[48],"We":[49],"introduce":[50],"Cross-Dimensional":[51],"Class-Agnostic":[52],"Instance":[54],"Segmentation":[55],"(CDIS),":[56],"a":[57,75],"zero-shot":[58,119],"framework":[59],"that":[60,110],"explicitly":[61],"tracks":[62,89],"frames":[67],"associates":[69],"them":[70],"with":[71,90],"superpoints,":[73],"creating":[74],"feedback":[76],"loop":[77],"between":[78],"3D.":[81],"This":[82],"cross-dimensional":[83],"reasoning":[84],"links":[85],"temporally":[86],"stable":[87],"spatially":[91],"coherent":[92],"regions,":[94],"producing":[95],"globally":[96],"consistent":[97],"labels":[100],"without":[101],"any":[102],"3D-specific":[103],"training.":[104],"Experiments":[105],"on":[106],"benchmark":[107],"datasets":[108],"demonstrate":[109],"CDIS":[111],"achieves":[112],"higher":[113],"accuracy":[114],"consistency":[116],"than":[117],"state-of-the-art":[118],"methods,":[120],"while":[121],"remaining":[122],"efficient":[123],"scalable":[125],"to":[126],"diverse":[127],"real-world":[128],"environments.":[129]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}