{"id":"https://openalex.org/W7117967525","doi":"https://doi.org/10.48550/arxiv.2512.24763","title":"UniC-Lift: Unified 3D Instance Segmentation via Contrastive Learning","display_name":"UniC-Lift: Unified 3D Instance Segmentation via Contrastive Learning","publication_year":2025,"publication_date":"2025-12-31","ids":{"openalex":"https://openalex.org/W7117967525","doi":"https://doi.org/10.48550/arxiv.2512.24763"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.24763","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.24763","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2512.24763","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062494269","display_name":"Ankit Dhiman","orcid":"https://orcid.org/0000-0002-9451-2052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhiman, Ankit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121809791","display_name":"Srinath R","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R, Srinath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108779437","display_name":"Jaswanth Reddy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reddy, Jaswanth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003154827","display_name":"Lokesh R Boregowda","orcid":"https://orcid.org/0009-0004-5966-4220"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boregowda, Lokesh R","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062096014","display_name":"Venkatesh Babu Radhakrishnan","orcid":"https://orcid.org/0000-0002-1926-1804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radhakrishnan, Venkatesh Babu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8568000197410583,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8568000197410583,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.02630000002682209,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.01940000057220459,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/segmentation","display_name":"Segmentation","score":0.6829000115394592},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6611999869346619},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6531000137329102},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5870000123977661},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5681999921798706},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4372999966144562},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41350001096725464},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3993000090122223},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.37279999256134033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753999829292297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7250999808311462},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6829000115394592},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6611999869346619},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6531000137329102},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5870000123977661},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5681999921798706},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.37279999256134033},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3693000078201294},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2639000117778778},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2531999945640564},{"id":"https://openalex.org/C23690007","wikidata":"https://www.wikidata.org/wiki/Q1411145","display_name":"Radiance","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.24763","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.24763","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2512.24763","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.24763","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,43],"Gaussian":[1,91],"Splatting":[2],"(3DGS)":[3],"and":[4,79,168,177,183],"Neural":[5],"Radiance":[6],"Fields":[7],"(NeRF)":[8],"have":[9],"advanced":[10],"novel-view":[11],"synthesis.":[12],"Recent":[13],"methods":[14,46],"extend":[15],"multi-view":[16],"2D":[17,35],"segmentation":[18,23,89],"to":[19,41,143,155],"3D,":[20],"enabling":[21],"instance/semantic":[22],"for":[24,65,88],"better":[25],"scene":[26],"understanding.":[27],"A":[28],"key":[29],"challenge":[30],"is":[31,95],"the":[32,109,122,127,144,156,162,180],"inconsistency":[33],"of":[34],"instance":[36,100],"labels":[37,64,101],"across":[38],"views,":[39],"leading":[40],"poor":[42],"predictions.":[44],"Existing":[45],"use":[47],"a":[48,69,84,103,152],"two-stage":[49],"approach":[50],"in":[51,90],"which":[52,165],"some":[53],"rely":[54],"on":[55,179],"contrastive":[56],"learning":[57],"with":[58],"hyperparameter-sensitive":[59],"clustering,":[60],"while":[61],"others":[62],"preprocess":[63],"consistency.":[66],"We":[67],"propose":[68,132],"unified":[70,113],"framework":[71,114],"that":[72],"merges":[73],"these":[74,136],"steps,":[75],"reducing":[76],"training":[77,167],"time":[78],"improving":[80],"performance":[81],"by":[82],"introducing":[83],"learnable":[85],"feature":[86,145,158],"embedding":[87,94],"primitives.":[92],"This":[93],"then":[96],"efficiently":[97],"decoded":[98],"into":[99],"through":[102],"novel":[104],"\"Embedding-to-Label\"":[105],"process,":[106],"effectively":[107],"integrating":[108],"optimization.":[110],"While":[111],"this":[112],"offers":[115],"substantial":[116],"benefits,":[117],"we":[118,131,150],"observed":[119],"artifacts":[120],"at":[121],"object":[123,128],"boundaries.":[124,137],"To":[125],"address":[126],"boundary":[129],"issues,":[130],"hard-mining":[133],"samples":[134],"along":[135],"However,":[138],"directly":[139],"applying":[140],"hard":[141],"mining":[142],"embeddings":[146,159],"proved":[147],"unstable.":[148],"Therefore,":[149],"apply":[151],"linear":[153],"layer":[154],"rasterized":[157],"before":[160],"calculating":[161],"triplet":[163],"loss,":[164],"stabilizes":[166],"significantly":[169],"improves":[170],"performance.":[171],"Our":[172],"method":[173],"outperforms":[174],"baselines":[175],"qualitatively":[176],"quantitatively":[178],"ScanNet,":[181],"Replica3D,":[182],"Messy-Rooms":[184],"datasets.":[185]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-02T00:00:00"}