{"id":"https://openalex.org/W7160313415","doi":"https://doi.org/10.1109/wacv61042.2026.00828","title":"VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning","display_name":"VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160313415","doi":"https://doi.org/10.1109/wacv61042.2026.00828"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5115539636","display_name":"Vivek Madhavaram","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161644","display_name":"Indian Institute of Information Technology Senapati, Manipur","ror":"https://ror.org/052ndvg69","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210161644"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vivek Madhavaram","raw_affiliation_strings":["IIIT,Machine Learning Lab,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT,Machine Learning Lab,Hyderabad,India","institution_ids":["https://openalex.org/I65181880","https://openalex.org/I4210161644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071891538","display_name":"Vartika Sengar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vartika Sengar","raw_affiliation_strings":["Fujitsu Research India,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research India,Bangalore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043602469","display_name":"Arkadipta De","orcid":"https://orcid.org/0000-0002-0460-1458"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arkadipta De","raw_affiliation_strings":["Fujitsu Research India,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research India,Bangalore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101841889","display_name":"Charu Sharma","orcid":"https://orcid.org/0000-0003-2518-5008"},"institutions":[{"id":"https://openalex.org/I4210161644","display_name":"Indian Institute of Information Technology Senapati, Manipur","ror":"https://ror.org/052ndvg69","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210161644"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Charu Sharma","raw_affiliation_strings":["IIIT,Machine Learning Lab,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT,Machine Learning Lab,Hyderabad,India","institution_ids":["https://openalex.org/I65181880","https://openalex.org/I4210161644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.54084745,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8584","last_page":"8595"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8515999913215637,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8515999913215637,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.044599998742341995,"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":0.03700000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.460999995470047},{"id":"https://openalex.org/keywords/scene-statistics","display_name":"Scene statistics","score":0.3939000070095062},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.3440999984741211},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.33719998598098755},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.33219999074935913},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.2867000102996826}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6319000124931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6000999808311462},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5999000072479248},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.3939000070095062},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.3440999984741211},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C5134670","wikidata":"https://www.wikidata.org/wiki/Q1626444","display_name":"Cut","level":4,"score":0.271699994802475},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2006698373","https://openalex.org/W2489434015","https://openalex.org/W2594519801","https://openalex.org/W2913618459","https://openalex.org/W2963101956","https://openalex.org/W2964345792","https://openalex.org/W2979750740","https://openalex.org/W2990129662","https://openalex.org/W2992478697","https://openalex.org/W3010715592","https://openalex.org/W3016121695","https://openalex.org/W3035154952","https://openalex.org/W3039925688","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3107848485","https://openalex.org/W3119206490","https://openalex.org/W3133833192","https://openalex.org/W3159619744","https://openalex.org/W3173271937","https://openalex.org/W3175234951","https://openalex.org/W3195129957","https://openalex.org/W3198299822","https://openalex.org/W3203949114","https://openalex.org/W3204757729","https://openalex.org/W3205398323","https://openalex.org/W3206171352","https://openalex.org/W4214684415","https://openalex.org/W4226094317","https://openalex.org/W4226236972","https://openalex.org/W4231449374","https://openalex.org/W4285058186","https://openalex.org/W4308769670","https://openalex.org/W4312732547","https://openalex.org/W4312749817","https://openalex.org/W4312852845","https://openalex.org/W4322704448","https://openalex.org/W4383108719","https://openalex.org/W4383109105","https://openalex.org/W4388622909","https://openalex.org/W4393149385","https://openalex.org/W4399563600","https://openalex.org/W4401414715","https://openalex.org/W4402354022","https://openalex.org/W4402726938","https://openalex.org/W4402754162","https://openalex.org/W4402754253","https://openalex.org/W4402917081","https://openalex.org/W4404612908","https://openalex.org/W4405787186","https://openalex.org/W4413144643","https://openalex.org/W4413917118","https://openalex.org/W7133190492","https://openalex.org/W7133193597","https://openalex.org/W7133211520","https://openalex.org/W7133250029"],"related_works":[],"abstract_inverted_index":{"Scene":[0],"understanding":[1],"and":[2,20,47,61,141,156,169,188,191,201],"reasoning":[3],"has":[4],"been":[5],"a":[6,92],"fundamental":[7],"problem":[8],"in":[9,165,184,194],"3D":[10,86,100,106],"computer":[11],"vision,":[12],"requiring":[13,148],"models":[14],"to":[15,120,159],"identify":[16],"objects,":[17],"their":[18],"properties,":[19],"spatial":[21,64,115,140],"or":[22],"comparative":[23],"relationships":[24,49,65,116,137,143],"among":[25,144],"the":[26,130,161,199],"objects.":[27],"Existing":[28],"approaches":[29],"enable":[30],"this":[31],"by":[32],"creating":[33],"scene":[34,82,87,101,110,145,166,185],"graphs":[35,102],"using":[36],"multiple":[37],"inputs":[38],"such":[39,172],"as":[40,114,173],"2D":[41],"images,":[42],"depth":[43],"maps,":[44],"object":[45,175],"labels,":[46],"annotated":[48,149],"from":[50,104],"specific":[51],"reference":[52,131],"view.":[53,132],"However,":[54],"these":[55,76],"methods":[56],"often":[57],"struggle":[58],"with":[59],"generalization":[60],"produce":[62],"inaccurate":[63],"like":[66],"\"left/right\",":[67],"which":[68],"become":[69],"inconsistent":[70],"across":[71],"different":[72],"viewpoints.":[73],"To":[74],"address":[75],"limitations,":[77],"we":[78],"propose":[79],"Viewpoint-Invariant":[80],"ZerO-shot":[81],"graph":[83,111,167,186],"generation":[84,168,187],"for":[85],"Reasoning":[88],"(VIZOR).":[89],"VIZOR":[90,164,177],"is":[91,112],"training-free,":[93],"end-to-end":[94],"framework":[95],"that":[96,138],"constructs":[97],"dense,":[98],"viewpoint-invariant":[99],"directly":[103],"raw":[105],"scenes.":[107],"The":[108],"generated":[109],"unambiguous,":[113],"are":[117],"defined":[118],"relative":[119],"each":[121],"object\u2019s":[122],"front-facing":[123],"direction,":[124],"making":[125],"them":[126],"consistent":[127],"regardless":[128],"of":[129,163],"Furthermore,":[133],"it":[134],"infers":[135],"open-vocabulary":[136],"describe":[139],"proximity":[142],"objects":[146],"without":[147],"training":[150],"data.":[151],"We":[152],"conduct":[153],"extensive":[154],"quantitative":[155],"qualitative":[157],"evaluations":[158],"assess":[160],"effectiveness":[162],"downstream":[170],"tasks,":[171],"query-based":[174],"grounding.":[176],"outperforms":[178],"state-of-the-art":[179],"methods,":[180],"showing":[181],"clear":[182],"improvements":[183],"achieving":[189],"22%":[190],"4.81%":[192],"gains":[193],"zero-shot":[195],"grounding":[196],"accuracy":[197],"on":[198],"Replica":[200],"Nr3D":[202],"datasets,":[203],"respectively.":[204],"Project":[205],"page:":[206],"https://vivekmadhavaram.github.io/vizor/":[207]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-05-06T00:00:00"}