{"id":"https://openalex.org/W4405300890","doi":"https://doi.org/10.1109/iccv51701.2025.00651","title":"3DSRBENCH: A Comprehensive 3D Spatial Reasoning Benchmark","display_name":"3DSRBENCH: A Comprehensive 3D Spatial Reasoning Benchmark","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405300890","doi":"https://doi.org/10.1109/iccv51701.2025.00651"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00651","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.07825","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070188278","display_name":"Wufei Ma","orcid":"https://orcid.org/0000-0002-4696-2833"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wufei Ma","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024460953","display_name":"Haoyu Chen","orcid":"https://orcid.org/0000-0003-4110-4685"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyu Chen","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111345587","display_name":"Guofeng Zhang","orcid":"https://orcid.org/0009-0005-8183-0771"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guofeng Zhang","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu-Cheng Chou","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-Cheng Chou","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083362398","display_name":"Jieneng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jieneng Chen","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066072868","display_name":"Celso M. de Melo","orcid":"https://orcid.org/0000-0003-2680-8334"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Celso De Melo","raw_affiliation_strings":["DEVCOM Army Research Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086706224","display_name":"Alan Yuille","orcid":"https://orcid.org/0000-0001-5207-9249"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Yuille","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5070188278"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00129045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6924","last_page":"6934"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9940000176429749,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9891999959945679,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7656242847442627},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.646868109703064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5210021138191223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35303059220314026},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.32760089635849},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.20290213823318481}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7656242847442627},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.646868109703064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5210021138191223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35303059220314026},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.32760089635849},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.20290213823318481}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00651","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:2412.07825","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.07825","pdf_url":"https://arxiv.org/pdf/2412.07825","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.07825","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.07825","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.07825","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.07825","pdf_url":"https://arxiv.org/pdf/2412.07825","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526"],"abstract_inverted_index":{"3D":[0,20,32,73,91,114,134,139,147,176],"spatial":[1,14,74,92,115,135,148,212],"reasoning":[2,75,93,116,136,149,213],"is":[3,218],"the":[4,10,19,31,88,131],"ability":[5],"to":[6,25,37,71],"analyze":[7],"and":[8,13,48,65,110,122,156,166,183,203],"interpret":[9],"positions,":[11],"orientations,":[12],"relationships":[15],"of":[16,30,41,63,113,133,164,175,208],"objects":[17],"within":[18],"space.":[21],"This":[22],"allows":[23],"models":[24,53],"develop":[26],"a":[27,38,60,124,161],"comprehensive":[28,90],"understanding":[29,67],"scene,":[33],"enabling":[34],"their":[35,69,170,189],"applicability":[36],"broader":[39],"range":[40,62,163],"areas,":[42],"such":[43,178],"as":[44,179,186,188],"autonomous":[45],"navigation,":[46],"robotics,":[47],"AR/VR.":[49],"While":[50],"large":[51],"multi-modal":[52],"(LMMs)":[54],"have":[55],"achieved":[56],"remarkable":[57],"progress":[58],"in":[59,172],"wide":[61,162],"image":[64],"video":[66],"tasks,":[68],"capabilities":[70],"perform":[72],"on":[76,151,192],"diverse":[77],"natural":[78],"images":[79,153,193],"are":[80],"less":[81],"studied.":[82],"In":[83],"this":[84],"work":[85],"we":[86],"present":[87],"first":[89],"benchmark,":[94],"3DSRBench,":[95],"with":[96,146,154,210],"2,772":[97],"manually":[98],"annotated":[99],"visual":[100],"question-answer":[101],"pairs":[102],"across":[103],"12":[104],"question":[105],"types.":[106],"We":[107,159],"conduct":[108],"robust":[109],"thorough":[111],"evaluation":[112],"abilities":[117],"by":[118],"balancing":[119],"data":[120],"distribution":[121],"adopting":[123],"novel":[125],"FlipEval":[126],"strategy.":[127],"To":[128],"further":[129],"study":[130],"robustness":[132],"w.r.t.":[137],"camera":[138],"viewpoints,":[140],"our":[141],"3DSRBench":[142,199],"includes":[143],"two":[144],"subsets":[145],"questions":[150],"paired":[152],"common":[155],"uncommon":[157,195],"viewpoints.":[158,197],"benchmark":[160],"open-sourced":[165],"proprietary":[167],"LMMs,":[168],"uncovering":[169],"limitations":[171],"various":[173],"aspects":[174],"awareness,":[177],"height,":[180],"orientation,":[181],"location,":[182],"multi-object":[184],"reasoning,":[185],"well":[187],"degraded":[190],"performance":[191],"from":[194],"6D":[196],"Our":[198,215],"provide":[200],"valuable":[201],"findings":[202],"insights":[204],"about":[205],"future":[206],"development":[207],"LMMs":[209],"strong":[211],"abilities.":[214],"project":[216],"page":[217],"available":[219],"at":[220],"https://3dsrbench.github.io/.":[221]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}