{"id":"https://openalex.org/W7151300330","doi":"https://doi.org/10.48550/arxiv.2604.03309","title":"TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding","display_name":"TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7151300330","doi":"https://doi.org/10.48550/arxiv.2604.03309"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.03309","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03309","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.03309","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133139109","display_name":"Jingbin You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You, Jingbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133087242","display_name":"Zehao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zehao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133097920","display_name":"Hao Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133107188","display_name":"Xinzhu Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Xinzhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001024587","display_name":"Shuqin Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Shuqin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133132888","display_name":"Honglong Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Honglong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133132826","display_name":"Congcong Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Congcong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001141015","display_name":"Tianlu Mao","orcid":"https://orcid.org/0000-0003-2537-9873"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Tianlu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133082043","display_name":"Feng Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133133716","display_name":"Yucheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133132671","display_name":"Zhaoqi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhaoqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.8586000204086304,"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":0.8586000204086304,"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":0.03480000048875809,"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":0.012900000438094139,"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/segmentation","display_name":"Segmentation","score":0.660099983215332},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5799000263214111},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.48539999127388},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4788999855518341},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44690001010894775},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.44369998574256897},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.4185999929904938},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4043999910354614}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7498999834060669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6826000213623047},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.660099983215332},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5799000263214111},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4788999855518341},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.32109999656677246},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2809000015258789},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.27129998803138733}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.03309","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03309","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.03309","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03309","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6622394919395447,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,23,147,150],"Gaussian":[1,136],"Splatting":[2],"(3DGS)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,58,78,93,120],"real-time,":[8],"differentiable":[9],"representation":[10],"for":[11],"neural":[12],"scene":[13],"understanding.":[14],"However,":[15],"existing":[16],"3DGS-based":[17],"methods":[18],"struggle":[19],"to":[20,106,127],"represent":[21],"hierarchical":[22,39,67],"semantic":[24,68],"structures":[25],"and":[26,37,70,110,119,141,154,160],"capture":[27],"whole-part":[28],"relationships":[29,69],"in":[30,48,73],"complex":[31],"scenes.":[32],"Moreover,":[33],"dense":[34],"pairwise":[35],"comparisons":[36],"inconsistent":[38],"labels":[40],"from":[41,104],"2D":[42],"priors":[43],"hinder":[44],"feature":[45,102],"learning,":[46],"resulting":[47],"suboptimal":[49],"segmentation.":[50],"To":[51],"address":[52],"these":[53],"limitations,":[54],"we":[55,91],"introduce":[56],"TreeGaussian,":[57],"tree-guided":[59],"cascaded":[60,95],"contrastive":[61,74,96],"learning":[62,85,97],"framework":[63],"that":[64,99],"explicitly":[65],"models":[66],"reduces":[71],"redundancy":[72],"supervision.":[75],"By":[76],"constructing":[77],"multi-level":[79],"object":[80,148],"tree,":[81],"TreeGaussian":[82],"enables":[83],"structured":[84],"across":[86,131],"object-part":[87],"hierarchies.":[88],"In":[89],"addition,":[90],"propose":[92],"two-stage":[94],"strategy":[98],"progressively":[100],"refines":[101],"representations":[103],"global":[105],"local,":[107],"mitigating":[108],"saturation":[109],"stabilizing":[111],"training.":[112],"A":[113],"Consistent":[114],"Segmentation":[115],"Detection":[116],"(CSD)":[117],"mechanism":[118],"graph-based":[121],"denoising":[122],"module":[123],"are":[124],"further":[125],"introduced":[126],"align":[128],"segmentation":[129,139],"modes":[130],"views":[132],"while":[133],"suppressing":[134],"unstable":[135],"points,":[137],"enhancing":[138],"consistency":[140],"quality.":[142],"Extensive":[143],"experiments,":[144],"including":[145],"open-vocabulary":[146],"selection,":[149],"point":[151],"cloud":[152],"understanding,":[153],"ablation":[155],"studies,":[156],"demonstrate":[157],"the":[158],"effectiveness":[159],"robustness":[161],"of":[162],"our":[163],"approach.":[164]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-08T00:00:00"}