{"id":"https://openalex.org/W4417275946","doi":"https://doi.org/10.1109/iccv51701.2025.00729","title":"InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction From Cluttered Scenes","display_name":"InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction From Cluttered Scenes","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417275946","doi":"https://doi.org/10.1109/iccv51701.2025.00729"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.08416","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100517122","display_name":"Zesong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zesong Yang","raw_affiliation_strings":["Zhejiang University,State Key Lab of CAD & CG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,State Key Lab of CAD & CG","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018138574","display_name":"Bangbang Yang","orcid":"https://orcid.org/0000-0001-7604-5553"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bangbang Yang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103268346","display_name":"Liyuan Cui","orcid":"https://orcid.org/0009-0000-9973-313X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyuan Cui","raw_affiliation_strings":["Zhejiang University,State Key Lab of CAD & CG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,State Key Lab of CAD & CG","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuewen Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuewen Ma","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391482","display_name":"Wenqi Dong","orcid":"https://orcid.org/0000-0002-5107-6166"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqi Dong","raw_affiliation_strings":["Zhejiang University,State Key Lab of CAD & CG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,State Key Lab of CAD & CG","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhaopeng Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaopeng Cui","raw_affiliation_strings":["Zhejiang University,State Key Lab of CAD & CG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,State Key Lab of CAD & CG","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenxuan Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxuan Cao","raw_affiliation_strings":["Zhejiang University,State Key Lab of CAD & CG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,State Key Lab of CAD & CG","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059021869","display_name":"Hujun Bao","orcid":"https://orcid.org/0000-0002-2662-0334"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hujun Bao","raw_affiliation_strings":["Zhejiang University,State Key Lab of CAD & CG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,State Key Lab of CAD & CG","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45612731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7771","last_page":"7781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.38929998874664307,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.38929998874664307,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.3646000027656555,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.04500000178813934,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/object","display_name":"Object (grammar)","score":0.6276999711990356},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5504999756813049},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5117999911308289},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.46869999170303345},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.42890000343322754},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.4043000042438507},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.38499999046325684},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3815000057220459},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3596000075340271},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.358599990606308}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.824400007724762},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7135999798774719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6852999925613403},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6276999711990356},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5504999756813049},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5117999911308289},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.46869999170303345},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3815000057220459},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.349700003862381},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2776863239","wikidata":"https://www.wikidata.org/wiki/Q7936601","display_name":"Visual hull","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.08416","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.08416","pdf_url":"https://arxiv.org/pdf/2507.08416","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.08416","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.08416","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"pmh:oai:arXiv.org:2507.08416","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.08416","pdf_url":"https://arxiv.org/pdf/2507.08416","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G957166398","display_name":null,"funder_award_id":"62441222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322927","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884"},{"id":"https://openalex.org/F4320327047","display_name":"State Key Laboratory of Computer Aided Design and Computer Graphics","ror":null},{"id":"https://openalex.org/F4320337013","display_name":"Information Technology Center, Nagoya University","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Humans":[0],"can":[1],"naturally":[2],"identify":[3],"and":[4,32,108,131,137,152],"mentally":[5],"complete":[6,36,66,118],"occluded":[7],"objects":[8],"in":[9,91],"cluttered":[10,92],"environments.":[11],"However,":[12],"imparting":[13],"similar":[14],"cognitive":[15],"ability":[16],"to":[17,34,116],"robotics":[18],"remains":[19],"challenging":[20],"even":[21],"with":[22,57,123],"advanced":[23],"reconstruction":[24],"techniques,":[25],"which":[26],"models":[27,115],"scenes":[28,56,139],"as":[29],"undifferentiated":[30],"wholes":[31],"fails":[33],"recognize":[35],"object":[37,132],"from":[38,97],"partial":[39],"observations.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,72,100],"propose":[45],"InstaScene,":[46],"a":[47,58,74],"new":[48],"paradigm":[49],"towards":[50],"holistic":[51],"3D":[52,113],"perception":[53],"of":[54,82],"complex":[55,135],"primary":[59],"goal:":[60],"decomposing":[61],"arbitrary":[62],"instances":[63,119],"while":[64,148],"ensuring":[65],"reconstruction.":[67],"To":[68,94],"achieve":[69],"precise":[70],"decomposition,":[71],"develop":[73],"novel":[75],"spatial":[76],"contrastive":[77],"learning":[78],"by":[79],"tracing":[80],"rasterization":[81],"each":[83],"instance":[84],"across":[85,134],"views,":[86],"significantly":[87],"enhancing":[88],"semantic":[89],"supervision":[90],"scenes.":[93],"overcome":[95],"incompleteness":[96],"limited":[98],"observations,":[99],"introduce":[101],"in-situ":[102],"generation":[103],"that":[104,120,141],"harnesses":[105],"valuable":[106],"observations":[107],"geometric":[109],"cues,":[110],"effectively":[111],"guiding":[112],"generative":[114],"reconstruct":[117],"seamlessly":[121],"align":[122],"the":[124],"real":[125],"world.":[126],"Experiments":[127],"on":[128],"scene":[129],"decomposition":[130,146],"completion":[133],"real-world":[136],"synthetic":[138],"demonstrate":[140],"our":[142],"method":[143],"achieves":[144],"superior":[145],"accuracy":[147],"producing":[149],"geometrically":[150],"faithful":[151],"visually":[153],"intact":[154],"objects.":[155]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}