{"id":"https://openalex.org/W4416799982","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249014","title":"Semantic Scene Completion from a Single Depth Image with Coarse-Grained Segmentation","display_name":"Semantic Scene Completion from a Single Depth Image with Coarse-Grained Segmentation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799982","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249014"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"Jiun Yen Ching","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Jiun Yen Ching","raw_affiliation_strings":["Center for Image and Visual Computing, Multimedia University,Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Image and Visual Computing, Multimedia University,Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046326626","display_name":"Lai-Kuan Wong","orcid":"https://orcid.org/0000-0002-4517-0391"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Lai-Kuan Wong","raw_affiliation_strings":["Center for Image and Visual Computing, Multimedia University,Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Image and Visual Computing, Multimedia University,Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015084583","display_name":"Fabian Wai-Lee Kung","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Fabian Wai-Lee Kung","raw_affiliation_strings":["Center for Image and Visual Computing, Multimedia University,Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Image and Visual Computing, Multimedia University,Malaysia","institution_ids":["https://openalex.org/I173029219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I173029219"],"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":"2311","last_page":"2316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.28999999165534973,"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"}},"topics":[{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.28999999165534973,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.2084999978542328,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.15389999747276306,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7009999752044678},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5735999941825867},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5511000156402588},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4235000014305115},{"id":"https://openalex.org/keywords/frustum","display_name":"Frustum","score":0.42100000381469727},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.40549999475479126},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.39469999074935913},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.38269999623298645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421000003814697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7376000285148621},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7009999752044678},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6733999848365784},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5735999941825867},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4235000014305115},{"id":"https://openalex.org/C97402662","wikidata":"https://www.wikidata.org/wiki/Q846235","display_name":"Frustum","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C2781289151","wikidata":"https://www.wikidata.org/wiki/Q2903989","display_name":"Class hierarchy","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2718000113964081},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:shdl.mmu.edu.my:15497","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196753","display_name":"Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173029219","host_organization_name":"Multimedia University","host_organization_lineage":["https://openalex.org/I173029219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W2444097022","https://openalex.org/W2557465155","https://openalex.org/W2963307292","https://openalex.org/W2963766190","https://openalex.org/W2963787264","https://openalex.org/W2964160369","https://openalex.org/W2981604966","https://openalex.org/W3002961783","https://openalex.org/W3009205130","https://openalex.org/W3089939852","https://openalex.org/W3160834782","https://openalex.org/W4312689172","https://openalex.org/W4313534977","https://openalex.org/W4403098246"],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"Scene":[1],"Completion":[2],"(SSC)":[3],"plays":[4],"an":[5,27,110],"important":[6],"role":[7],"in":[8,31,43,54,60,90],"computer":[9],"vision":[10],"applications":[11],"such":[12],"as":[13],"mobile":[14],"robots":[15],"navigation.":[16],"SSC":[17,137,163],"aims":[18],"to":[19,113],"reconstruct":[20],"a":[21,35,47,61,74,104],"complete":[22],"3D":[23,29],"volumetric":[24],"scene":[25,30,80],"from":[26],"incomplete":[28],"the":[32,44,57,88,91,94,115,122,131,148,151,155,171],"form":[33],"of":[34,150,157,161,173],"single":[36],"depth":[37],"image,":[38],"by":[39],"assigning":[40],"each":[41],"voxel":[42],"camera":[45],"frustum":[46],"class":[48,76,117],"label.":[49],"The":[50],"main":[51],"challenge":[52],"lies":[53],"directly":[55],"predicting":[56],"fine-grained":[58,99,158],"classes":[59],"complex":[62],"and":[63,98,119,124,129,142,167],"class-diverse":[64],"indoor":[65],"environment.":[66],"To":[67],"resolve":[68],"this":[69],"challenge,":[70],"we":[71],"first":[72],"introduce":[73],"novel":[75],"taxonomy":[77,92],"for":[78],"SUNCG":[79],"labels":[81],"based":[82],"on":[83,165],"common":[84],"shared":[85],"characteristics,":[86],"whereby":[87],"hierarchy":[89],"describes":[93],"relationship":[95],"between":[96],"coarse-grained":[97],"classes.":[100],"We":[101,127],"then":[102],"designed":[103],"lightweight":[105],"Coarse-Grained":[106],"Segmentation":[107],"(CGS)":[108],"module,":[109],"adaptable":[111],"decoder,":[112],"exploit":[114],"structured":[116],"relations":[118],"explicitly":[120],"model":[121],"high-":[123],"mid-level":[125],"features.":[126],"implemented":[128],"validated":[130],"CGS":[132,152],"module":[133,153],"with":[134],"three":[135],"existing":[136,162],"models,":[138],"i.e.,":[139],"SSCNet,":[140],"EdgeNet-D":[141],"Real-Time.":[143],"Experimental":[144],"results":[145],"demonstrate":[146],"that":[147],"incorporation":[149],"improved":[154],"performance":[156],"semantic":[159],"segmentation":[160],"models":[164],"NYUv2":[166],"NYUCAD":[168],"datasets,":[169],"demonstrating":[170],"effectiveness":[172],"our":[174],"approach.":[175]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}