{"id":"https://openalex.org/W4415183998","doi":"https://doi.org/10.1109/iccv51701.2025.02650","title":"SAM4D: Segment Anything in Camera and LiDAR Streams","display_name":"SAM4D: Segment Anything in Camera and LiDAR Streams","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415183998","doi":"https://doi.org/10.1109/iccv51701.2025.02650"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02650","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/2506.21547","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042055991","display_name":"Jia Xu","orcid":"https://orcid.org/0000-0003-4061-8262"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianyun Xu","raw_affiliation_strings":["CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040116594","display_name":"Song Wang","orcid":"https://orcid.org/0000-0001-7321-1691"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song Wang","raw_affiliation_strings":["CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006427956","display_name":"Zhenyu Ni","orcid":"https://orcid.org/0000-0002-5362-3936"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziqian Ni","raw_affiliation_strings":["CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066424893","display_name":"Chia-Ling Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunyong Hu","raw_affiliation_strings":["CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034205662","display_name":"S. Yang","orcid":"https://orcid.org/0000-0002-2898-6532"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Yang","raw_affiliation_strings":["CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062252650","display_name":"Jianke Zhu","orcid":"https://orcid.org/0000-0003-1831-0106"},"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":"Jianke Zhu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100429873","display_name":"Qiang Li","orcid":"https://orcid.org/0000-0001-5333-2939"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Li","raw_affiliation_strings":["CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CaiNiao Inc.,Alibaba Group,Unmanned Vehicle Dept","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"28535","last_page":"28545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.965499997138977,"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":0.9567999839782715,"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/point-cloud","display_name":"Point cloud","score":0.7337999939918518},{"id":"https://openalex.org/keywords/lidar","display_name":"Lidar","score":0.6829000115394592},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.664900004863739},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5795000195503235},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5268999934196472},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5162000060081482},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.44620001316070557},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4453999996185303},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.412200003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876999974250793},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.7337999939918518},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.6829000115394592},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.664900004863739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6330000162124634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6032999753952026},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5795000195503235},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5268999934196472},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3540000021457672},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3402999937534332},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.26249998807907104}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02650","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:2506.21547","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21547","pdf_url":"https://arxiv.org/pdf/2506.21547","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2506.21547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.21547","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2506.21547","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21547","pdf_url":"https://arxiv.org/pdf/2506.21547","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,119],"present":[1],"SAM4D,":[2],"a":[3,32,77,101],"multi-modal":[4,78],"and":[5,15,28,40,58,90,134],"temporal":[6,56],"foundation":[7],"model":[8],"designed":[9],"for":[10],"promptable":[11],"segmentation":[12,64,132],"across":[13,65],"camera":[14,27],"LiDAR":[16,29],"streams.":[17],"Unified":[18],"Multi-modal":[19],"Positional":[20],"Encoding":[21],"(UMPE)":[22],"is":[23],"introduced":[24],"to":[25,54],"align":[26],"features":[30],"in":[31,115,137],"shared":[33],"3D":[34],"space,":[35],"enabling":[36],"seamless":[37],"cross-modal":[38,91,131],"prompting":[39],"interaction.":[41],"Additionally,":[42],"we":[43,75],"propose":[44],"Motion-aware":[45],"Cross-modal":[46],"Memory":[47],"Attention":[48],"(MCMA),":[49],"which":[50,127],"leverages":[51],"ego-motion":[52],"compensation":[53],"enhance":[55],"consistency":[57],"long-horizon":[59],"feature":[60],"retrieval,":[61],"ensuring":[62],"robust":[63],"dynamically":[66],"changing":[67],"autonomous":[68],"driving":[69],"scenes.":[70],"To":[71],"avoid":[72],"annotation":[73,109,139],"bottlenecks,":[74],"develop":[76],"automated":[79],"data":[80,138],"engine":[81],"that":[82],"synergizes":[83],"VFM-driven":[84],"video":[85],"masklets,":[86],"spatiotemporal":[87],"4D":[88],"reconstruction,":[89],"masklet":[92],"fusion.":[93],"This":[94],"framework":[95],"generates":[96],"camera-LiDAR":[97],"aligned":[98],"pseudo-labels":[99],"at":[100],"speed":[102],"orders":[103],"of":[104,140],"magnitude":[105],"faster":[106],"than":[107],"human":[108],"while":[110],"preserving":[111],"VFM-derived":[112],"semantic":[113],"fidelity":[114],"point":[116],"cloud":[117],"representations.":[118],"conduct":[120],"extensive":[121],"experiments":[122],"on":[123],"the":[124,129],"constructed":[125],"Waymo-4DSeg,":[126],"demonstrate":[128],"powerful":[130],"ability":[133],"great":[135],"potential":[136],"proposed":[141],"SAM4D.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-15T00:00:00"}