{"id":"https://openalex.org/W7214933938","doi":"https://doi.org/10.48550/arxiv.2609.36875","title":"S4VY: Segment Anything in Feed-Forward 4D Visual Geometry","display_name":"S4VY: Segment Anything in Feed-Forward 4D Visual Geometry","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214933938","doi":"https://doi.org/10.48550/arxiv.2609.36875"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.36875","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36875","pdf_url":"https://arxiv.org/pdf/2609.36875","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.36875","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153616819","display_name":"Jingdong Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Jingdong","raw_affiliation_strings":["NVIDIA Project Page | Video Demo | Code","Texas A&M University , College Station ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Project Page | Video Demo | Code","institution_ids":[]},{"raw_affiliation_string":"Texas A&M University , College Station ,","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153590878","display_name":"Xin Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Xin","raw_affiliation_strings":["Texas A&M University , College Station ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University , College Station ,","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056503617","display_name":"Jan Kautz","orcid":"https://orcid.org/0000-0002-8830-429X","observed_orcids":["https://orcid.org/0000-0002-8830-429X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kautz, Jan","raw_affiliation_strings":["NVIDIA Project Page | Video Demo | Code"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Project Page | Video Demo | Code","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668416","display_name":"Wenping Wang","orcid":"https://orcid.org/0000-0002-2284-3952","observed_orcids":["https://orcid.org/0000-0002-2284-3952","https://orcid.org/0000-0002-1291-0197","https://orcid.org/0000-0003-2107-3084"]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Wenping","raw_affiliation_strings":["Texas A&M University , College Station ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University , College Station ,","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076611545","display_name":"Christopher Choy","orcid":"https://orcid.org/0009-0000-4023-1311","observed_orcids":["https://orcid.org/0009-0000-4023-1311"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choy, Chris","raw_affiliation_strings":["NVIDIA Project Page | Video Demo | Code"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Project Page | Video Demo | Code","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8647000193595886,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.8647000193595886,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0697999969124794,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.019500000402331352,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/segment-anything-model","display_name":"Segment Anything Model","score":0.7459999918937683},{"id":"https://openalex.org/keywords/dynamic-scenes","display_name":"dynamic scenes","score":0.7039999961853027},{"id":"https://openalex.org/keywords/natural-language-grounding","display_name":"natural language grounding","score":0.6399999856948853},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7210000157356262},{"id":"https://openalex.org/keywords/bounding-box-prediction","display_name":"bounding box prediction","score":0.843999981880188},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.6000000238418579},{"id":"https://openalex.org/keywords/robotics","display_name":"robotics","score":0.6349999904632568}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7552000284194946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7159000039100647},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7106000185012817},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6574000120162964},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5397999882698059},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45320001244544983},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4523000121116638},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.35179999470710754},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.3285999894142151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2583000063896179}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.36875","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36875","pdf_url":"https://arxiv.org/pdf/2609.36875","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,"listed_in":[],"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.2609.36875","doi":"https://doi.org/10.48550/arxiv.2609.36875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.36875","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,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.36875","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36875","pdf_url":"https://arxiv.org/pdf/2609.36875","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214933938.pdf","grobid_xml":"https://content.openalex.org/works/W7214933938.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2125188192","https://openalex.org/W2963557767","https://openalex.org/W2964339842","https://openalex.org/W3130522999","https://openalex.org/W3168867926","https://openalex.org/W3203821123","https://openalex.org/W4225544038","https://openalex.org/W4367000115","https://openalex.org/W4379961490","https://openalex.org/W4382173244","https://openalex.org/W4398156429","https://openalex.org/W4400065265","https://openalex.org/W4400434865","https://openalex.org/W4403580243","https://openalex.org/W4409502577","https://openalex.org/W4416780398","https://openalex.org/W4417087265","https://openalex.org/W6891822422","https://openalex.org/W6910441595","https://openalex.org/W6979267127","https://openalex.org/W7101583646","https://openalex.org/W7123922901","https://openalex.org/W7124710716","https://openalex.org/W7133191568","https://openalex.org/W7133212131","https://openalex.org/W7133224126","https://openalex.org/W7140075682","https://openalex.org/W7140472030","https://openalex.org/W7143345120","https://openalex.org/W7152029636","https://openalex.org/W7155391267","https://openalex.org/W7161247360","https://openalex.org/W7162465297","https://openalex.org/W7165657641","https://openalex.org/W7166849315","https://openalex.org/W7170032222","https://openalex.org/W7214037957","https://openalex.org/W7214246148"],"related_works":["https://openalex.org/W7170032222","https://openalex.org/W4417087265","https://openalex.org/W7106850701","https://openalex.org/W7211965385","https://openalex.org/W7106708003","https://openalex.org/W7148988521","https://openalex.org/W7203908631","https://openalex.org/W7215831544","https://openalex.org/W2964104806","https://openalex.org/W4387228701"],"abstract_inverted_index":{"Accurate":[0],"instance":[1,38,78,156,173,183],"segmentation":[2,39,100,184],"in":[3,126],"dynamic":[4,197],"scenes":[5],"is":[6],"important":[7],"for":[8,123],"downstream":[9],"applications":[10],"such":[11],"as":[12,101,103],"robotics":[13],"and":[14,29,105,162,165,185,196],"autonomous":[15],"driving.":[16],"Existing":[17],"Segment":[18,51],"Anything":[19,52],"models":[20],"operate":[21],"primarily":[22],"on":[23,55],"2D":[24],"image":[25],"or":[26,114],"video":[27],"masks":[28,79],"preserve":[30],"identity":[31],"through":[32,80,158],"sequential":[33],"memory,":[34],"while":[35],"promptable":[36],"4D":[37,57,77,133,172,182],"built":[40,54],"upon":[41],"feed-forward":[42,56],"visual":[43,58,152],"geometry":[44],"remains":[45],"underexplored.":[46],"We":[47,117],"introduce":[48],"S4VY,":[49],"a":[50,61,81,111,132,146,191],"model":[53],"geometry.":[59],"From":[60],"set":[62,74],"of":[63,75,131],"RGB":[64],"observations,":[65],"S4VY":[66],"transforms":[67],"shared":[68],"visual-geometric":[69],"features":[70,157],"into":[71],"an":[72,120,166],"exhaustive":[73],"class-agnostic":[76],"space-time":[82],"query":[83,89],"decoder,":[84],"with":[85,154],"each":[86],"persistent":[87],"object":[88],"binding":[90],"one":[91],"entity":[92],"across":[93],"all":[94],"observations.":[95],"This":[96],"representation":[97],"supports":[98],"prompt-independent":[99],"well":[102],"point-":[104],"box-":[106],"conditioned":[107],"selection,":[108],"without":[109,141],"requiring":[110],"seed":[112],"mask":[113,174],"temporal":[115],"ordering.":[116],"further":[118],"develop":[119],"agentic":[121],"harness":[122],"natural-language":[124],"grounding":[125,188],"the":[127,170],"large":[128],"observation":[129],"space":[130],"scene.":[134],"Active":[135],"tree":[136],"search":[137],"identifies":[138],"relevant":[139],"frames":[140],"scanning":[142],"every":[143],"fixed":[144],"window;":[145],"dual-stream":[147],"grounder":[148],"combines":[149],"fine-grained":[150],"VLM":[151],"priors":[153],"geometry-consistent":[155],"complementary":[159],"bounding-box":[160],"prediction":[161],"object-query":[163],"matching;":[164],"independent":[167],"critic":[168],"selects":[169],"final":[171],"from":[175],"their":[176],"predictions.":[177],"Extensive":[178],"experiments":[179],"demonstrate":[180],"state-of-the-art":[181],"strong":[186],"language-guided":[187],"performance":[189],"under":[190],"unified":[192],"evaluation":[193],"spanning":[194],"static":[195],"scenes.":[198]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}