{"id":"https://openalex.org/W4404370903","doi":"https://doi.org/10.1109/tcsvt.2024.3498041","title":"SGIFormer: Semantic-Guided and Geometric-Enhanced Interleaving Transformer for 3D Instance Segmentation","display_name":"SGIFormer: Semantic-Guided and Geometric-Enhanced Interleaving Transformer for 3D Instance Segmentation","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404370903","doi":"https://doi.org/10.1109/tcsvt.2024.3498041"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3498041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3498041","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/116366/1/Yao_Sgiformer_Semantic-guided_Geometric-enhanced.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101659036","display_name":"Lei Yao","orcid":"https://orcid.org/0009-0007-0304-3056"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Lei Yao","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, SAR, Hong Kong","Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0007-0304-3056","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, SAR, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100784213","display_name":"Yi Wang","orcid":"https://orcid.org/0000-0001-8659-4724"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, SAR, Hong Kong","Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-8659-4724","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, SAR, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016553220","display_name":"Moyun Liu","orcid":"https://orcid.org/0000-0002-4530-2606"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Moyun Liu","raw_affiliation_strings":["School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4530-2606","affiliations":[{"raw_affiliation_string":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044722301","display_name":"Lap\u2010Pui Chau","orcid":"https://orcid.org/0000-0003-4932-0593"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lap-Pui Chau","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, SAR, Hong Kong","Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-4932-0593","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, SAR, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101659036"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":2.1121,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8662653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"35","issue":"3","first_page":"2276","last_page":"2288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9957000017166138,"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":0.9957000017166138,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9908000230789185,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9776999950408936,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.7152494192123413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6737658381462097},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.646573543548584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5805155634880066},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5635698437690735},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5452181100845337},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5172491669654846},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4028724431991577},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38893893361091614},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10497391223907471},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09036532044410706}],"concepts":[{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.7152494192123413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6737658381462097},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.646573543548584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5805155634880066},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5635698437690735},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5452181100845337},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5172491669654846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4028724431991577},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38893893361091614},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10497391223907471},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09036532044410706},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2024.3498041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3498041","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/116366","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/116366","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/116366/1/Yao_Sgiformer_Semantic-guided_Geometric-enhanced.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"}],"best_oa_location":{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/116366","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/116366","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/116366/1/Yao_Sgiformer_Semantic-guided_Geometric-enhanced.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404370903.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1999478155","https://openalex.org/W2162656786","https://openalex.org/W2222512263","https://openalex.org/W2460657278","https://openalex.org/W2594519801","https://openalex.org/W2904332125","https://openalex.org/W2962759414","https://openalex.org/W2963125977","https://openalex.org/W2963281829","https://openalex.org/W2971142047","https://openalex.org/W3034550906","https://openalex.org/W3034949383","https://openalex.org/W3035748168","https://openalex.org/W3096609285","https://openalex.org/W3204034406","https://openalex.org/W4214526701","https://openalex.org/W4214624153","https://openalex.org/W4214773923","https://openalex.org/W4312274934","https://openalex.org/W4312649925","https://openalex.org/W4312815172","https://openalex.org/W4312890284","https://openalex.org/W4317987768","https://openalex.org/W4321482463","https://openalex.org/W4376607688","https://openalex.org/W4382203425","https://openalex.org/W4382457953","https://openalex.org/W4383109105","https://openalex.org/W4385245566","https://openalex.org/W4386071839","https://openalex.org/W4386076523","https://openalex.org/W4388505032","https://openalex.org/W4390872957","https://openalex.org/W4390873101","https://openalex.org/W4390873207","https://openalex.org/W4390873582","https://openalex.org/W4390873929","https://openalex.org/W4394593003","https://openalex.org/W4396238916","https://openalex.org/W4402716329","https://openalex.org/W4402727277","https://openalex.org/W4402727743","https://openalex.org/W4402753560","https://openalex.org/W6739663239","https://openalex.org/W6739778489","https://openalex.org/W6763229141","https://openalex.org/W6780179280","https://openalex.org/W6798837711","https://openalex.org/W6846095257","https://openalex.org/W6857584973","https://openalex.org/W6859500479","https://openalex.org/W6877002387"],"related_works":["https://openalex.org/W1655266410","https://openalex.org/W2389051085","https://openalex.org/W2330343234","https://openalex.org/W1901012776","https://openalex.org/W2463883322","https://openalex.org/W2229382548","https://openalex.org/W2391789612","https://openalex.org/W2389236462","https://openalex.org/W2814468324","https://openalex.org/W1522196789"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"transformer-based":[3],"models":[4],"have":[5],"exhibited":[6],"considerable":[7],"potential":[8],"in":[9],"point":[10,153],"cloud":[11],"instance":[12,27,54,120,158],"segmentation.":[13],"Despite":[14],"the":[15,60,67,74,84,92,102,109,171],"promising":[16],"performance":[17,163],"achieved":[18],"by":[19],"existing":[20],"methods,":[21],"they":[22],"encounter":[23],"challenges":[24],"such":[25],"as":[26,145],"query":[28,104,112,121],"initialization":[29,65,79],"problems":[30],"and":[31,66,99,122,131,149,170,182,187],"excessive":[32],"reliance":[33],"on":[34,164],"stacked":[35],"layers,":[36],"rendering":[37],"them":[38],"incompatible":[39],"with":[40],"large-scale":[41],"3D":[42,53],"scenes.":[43],"This":[44],"paper":[45],"introduces":[46],"a":[47,178],"novel":[48],"method,":[49],"named":[50],"SGIFormer,":[51],"for":[52,101,126],"segmentation,":[55],"which":[56],"is":[57,81],"composed":[58],"of":[59,76],"Semantic-guided":[61],"Mix":[62],"Query":[63],"(SMQ)":[64],"Geometric-enhanced":[68],"Interleaving":[69],"Transformer":[70],"(GIT)":[71],"decoder.":[72],"Specifically,":[73],"principle":[75],"our":[77,114],"SMQ":[78],"scheme":[80],"to":[82,89,117,156],"leverage":[83],"predicted":[85],"voxel-wise":[86],"semantic":[87],"information":[88,130],"implicitly":[90],"generate":[91],"scene-aware":[93],"query,":[94],"yielding":[95],"adequate":[96],"scene":[97,124],"prior":[98],"compensating":[100],"learnable":[103],"set.":[105],"Subsequently,":[106],"we":[107,141],"feed":[108],"formed":[110],"overall":[111],"into":[113],"GIT":[115],"decoder":[116],"alternately":[118],"refine":[119],"global":[123],"features":[125],"further":[127],"capturing":[128],"fine-grained":[129],"reducing":[132],"complex":[133],"design":[134],"intricacies":[135],"simultaneously.":[136],"To":[137],"emphasize":[138],"geometric":[139],"property,":[140],"consider":[142],"bias":[143],"estimation":[144],"an":[146],"auxiliary":[147],"task":[148],"progressively":[150],"integrate":[151],"shifted":[152],"coordinates":[154],"embedding":[155],"reinforce":[157],"localization.":[159],"SGIFormer":[160],"attains":[161],"state-of-the-art":[162],"ScanNet":[165,174],"V2,":[166],"ScanNet200,":[167],"S3DIS":[168],"datasets,":[169],"challenging":[172],"high-fidelity":[173],"++":[175],"benchmark,":[176],"striking":[177],"balance":[179],"between":[180],"accuracy":[181],"efficiency.":[183],"The":[184],"code,":[185],"weights,":[186],"demo":[188],"videos":[189],"are":[190],"publicly":[191],"available":[192],"at":[193],"<uri":[194],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[195],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://rayyoh.github.io/SGIFormer/</uri>.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}