{"id":"https://openalex.org/W4415541319","doi":"https://doi.org/10.1145/3746027.3754882","title":"SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion","display_name":"SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415541319","doi":"https://doi.org/10.1145/3746027.3754882"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754882","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5101936895","display_name":"Zhiwen Yang","orcid":"https://orcid.org/0000-0002-0416-0576"},"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":"Zhiwen Yang","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0416-0576","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047811387","display_name":"Yuxin Peng","orcid":"https://orcid.org/0000-0001-7658-3845"},"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":"Yuxin Peng","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7658-3845","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27406997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7681","last_page":"7690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9980999827384949,"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/initialization","display_name":"Initialization","score":0.6887000203132629},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5899999737739563},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.5889000296592712},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5647000074386597},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.46209999918937683},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.44609999656677246},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4034999907016754},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.38449999690055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742900013923645},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6887000203132629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126999855041504},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.5889000296592712},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5647000074386597},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46720001101493835},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C3768446","wikidata":"https://www.wikidata.org/wiki/Q877100","display_name":"Spherical harmonics","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.2597000002861023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754882","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W3109395584","https://openalex.org/W3138270694","https://openalex.org/W3138516171","https://openalex.org/W3174692508","https://openalex.org/W3179909833","https://openalex.org/W4200150166","https://openalex.org/W4312894406","https://openalex.org/W4323897324","https://openalex.org/W4382450829","https://openalex.org/W4382464460","https://openalex.org/W4384024451","https://openalex.org/W4385318467","https://openalex.org/W4386066358","https://openalex.org/W4386075718","https://openalex.org/W4390492478","https://openalex.org/W4400876846","https://openalex.org/W4402727915"],"related_works":[],"abstract_inverted_index":{"Camera-based":[0],"3D":[1,117],"Semantic":[2],"Scene":[3],"Completion":[4],"(SSC)":[5],"is":[6,179],"a":[7],"critical":[8],"task":[9],"in":[10],"autonomous":[11,72],"driving":[12,73],"systems,":[13],"assessing":[14],"voxel-level":[15],"geometry":[16],"and":[17,26,53,65,97,105,147,163,169],"semantics":[18],"for":[19,40,91,100],"holistic":[20],"scene":[21,118],"perception.":[22],"While":[23],"existing":[24],"voxel-based":[25],"plane-based":[27],"SSC":[28,156],"methods":[29,50],"have":[30],"achieved":[31],"considerable":[32],"progress,":[33],"they":[34],"struggle":[35],"to":[36,76,120,126,142],"capture":[37],"physical":[38,57,106],"regularities":[39],"realistic":[41,159],"geometric":[42],"details.":[43,160],"On":[44],"the":[45,86,109,132,166,173],"other":[46],"hand,":[47],"neural":[48],"reconstruction":[49],"like":[51],"NeRF":[52],"3DGS":[54],"demonstrate":[55],"superior":[56],"awareness,":[58],"but":[59],"suffer":[60],"from":[61],"high":[62],"computational":[63],"cost":[64],"slow":[66],"convergence":[67],"when":[68],"handling":[69],"large-scale,":[70],"complex":[71],"scenes,":[74],"leading":[75],"inferior":[77],"semantic":[78,104,139],"accuracy.":[79],"To":[80],"address":[81],"these":[82],"issues,":[83],"we":[84],"propose":[85],"Semantic-PHysical":[87],"Engaged":[88],"REpresentation":[89],"(SPHERE)":[90],"camera-based":[92],"SSC,":[93],"which":[94],"integrates":[95],"voxel":[96],"Gaussian":[98,111,129],"representations":[99,119],"joint":[101],"exploitation":[102],"of":[103,175],"information.":[107],"First,":[108],"Semantic-guided":[110],"Initialization":[112],"(SGI)":[113],"module":[114,137],"leverages":[115],"dual-branch":[116],"locate":[121],"focal":[122,152],"voxels":[123],"as":[124],"anchors":[125],"guide":[127],"efficient":[128],"initialization.":[130],"Then,":[131],"Physical-aware":[133],"Harmonics":[134],"Enhancement":[135],"(PHE)":[136],"incorporates":[138],"spherical":[140],"harmonics":[141],"model":[143],"physical-aware":[144],"contextual":[145],"details":[146],"promote":[148],"semantic-geometry":[149],"consistency":[150],"through":[151],"distribution":[153],"alignment,":[154],"generating":[155],"results":[157],"with":[158],"Extensive":[161],"experiments":[162],"analyses":[164],"on":[165],"popular":[167],"SemanticKITTI":[168],"SSCBench-KITTI-360":[170],"benchmarks":[171],"validate":[172],"effectiveness":[174],"SPHERE.":[176],"The":[177],"code":[178],"available":[180],"at":[181],"https://github.com/PKU-ICST-MIPL/SPHERE_ACMMM2025.":[182]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-25T00:00:00"}