{"id":"https://openalex.org/W4413145675","doi":"https://doi.org/10.1109/cvpr52734.2025.01314","title":"InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception","display_name":"InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145675","doi":"https://doi.org/10.1109/cvpr52734.2025.01314"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5005801079","display_name":"Haijie Li","orcid":"https://orcid.org/0000-0003-4908-4615"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijie Li","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101688674","display_name":"Yanmin Wu","orcid":"https://orcid.org/0000-0002-3926-4500"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Wu","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100594358","display_name":"Jiarui Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarui Meng","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027281574","display_name":"Qiankun Gao","orcid":"https://orcid.org/0000-0001-7188-1018"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiankun Gao","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104037120","display_name":"Zhiyao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyao Zhang","raw_affiliation_strings":["Northeastern University,College of Information Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,College of Information Science and Engineering,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055296802","display_name":"Ronggang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronggang Wang","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102752768","display_name":"Jian Xin Zhang","orcid":"https://orcid.org/0009-0001-8651-0524"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.1576,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.98676824,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"14078","last_page":"14088"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9962999820709229,"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":0.9962999820709229,"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/T11448","display_name":"Face recognition and analysis","score":0.9954000115394592,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.6991121768951416},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6026970148086548},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.597727358341217},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5907658338546753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.549289345741272},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.45790529251098633},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38458865880966187},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3394855856895447},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32011789083480835},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1113848090171814},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06323906779289246},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05531767010688782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991121768951416},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6026970148086548},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.597727358341217},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5907658338546753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.549289345741272},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.45790529251098633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38458865880966187},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3394855856895447},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32011789083480835},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1113848090171814},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06323906779289246},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05531767010688782},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2628861693","https://openalex.org/W2062195135","https://openalex.org/W2888483922","https://openalex.org/W4396737233","https://openalex.org/W3203087560","https://openalex.org/W2367747139","https://openalex.org/W4391102217","https://openalex.org/W4361279463"],"abstract_inverted_index":{"3D":[0,19,115],"scene":[1,15],"understanding":[2,16],"is":[3],"vital":[4],"for":[5,87,100],"applications":[6],"in":[7,35,112],"autonomous":[8],"driving,":[9],"robotics,":[10],"and":[11,31,38,58,79,90,92],"augmented":[12],"reality.":[13],"However,":[14],"based":[17],"on":[18],"Gaussian":[20],"Splatting":[21],"faces":[22],"three":[23],"key":[24],"challenges:":[25],"(i)":[26,70],"an":[27],"imbalance":[28],"between":[29],"appearance":[30,57],"semantics,":[32],"(ii)":[33,82],"inconsistencies":[34],"object":[36],"boundaries,":[37],"(iii)":[39,93],"difficulties":[40],"with":[41],"top-down":[42],"instance":[43,97],"segmentation.":[44,102],"To":[45],"address":[46],"these":[47],"challenges,":[48],"we":[49],"propose":[50],"InstanceGaussian,":[51],"a":[52,71,83,94],"method":[53],"that":[54,106],"jointly":[55],"learns":[56],"semantic":[59],"features":[60],"while":[61],"adaptively":[62],"aggregating":[63],"instances.":[64],"Our":[65],"contributions":[66],"are":[67],"as":[68],"follows:":[69],"new":[72],"Semantic-Scaffold-GS":[73],"representation":[74,78],"to":[75],"improve":[76],"feature":[77],"boundary":[80],"delineation,":[81],"progressive":[84],"training":[85],"strategy":[86],"enhanced":[88],"stability":[89],"segmentation,":[91,117],"category-agnostic,":[95,113],"bottom-up":[96],"aggregation":[98],"approach":[99,108],"better":[101],"Experimental":[103],"results":[104],"demonstrate":[105],"our":[107,122],"achieves":[109],"state-of-the-art":[110],"performance":[111],"open-vocabulary":[114],"point-level":[116],"validating":[118],"the":[119],"effectiveness":[120],"of":[121],"proposed":[123],"method.":[124],"Project":[125],"page:":[126],"https://lhj-git.github.io/InstanceGaussian/":[127]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}