{"id":"https://openalex.org/W4403369827","doi":"https://doi.org/10.48550/arxiv.2408.02231","title":"REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models","display_name":"REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models","publication_year":2024,"publication_date":"2024-08-05","ids":{"openalex":"https://openalex.org/W4403369827","doi":"https://doi.org/10.48550/arxiv.2408.02231"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.02231","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.02231","pdf_url":"https://arxiv.org/pdf/2408.02231","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.02231","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033803475","display_name":"Agneet Chatterjee","orcid":"https://orcid.org/0000-0002-0961-9569"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chatterjee, Agneet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372691","display_name":"Yiran Luo","orcid":"https://orcid.org/0000-0002-8112-4376"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035343276","display_name":"Tejas Gokhale","orcid":"https://orcid.org/0000-0002-5593-2804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gokhale, Tejas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002278578","display_name":"Yezhou Yang","orcid":"https://orcid.org/0000-0003-0126-8976"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yezhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083735830","display_name":"Chitta Baral","orcid":"https://orcid.org/0000-0002-7549-723X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baral, Chitta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.8364999890327454,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.8364999890327454,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10757","display_name":"Geographic Information Systems Studies","score":0.8007000088691711,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.7978000044822693,"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/rendering","display_name":"Rendering (computer graphics)","score":0.8180186748504639},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6979236602783203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6767561435699463},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4334205090999603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4279947876930237},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3844200670719147},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3598218560218811}],"concepts":[{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.8180186748504639},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6979236602783203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6767561435699463},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4334205090999603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4279947876930237},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3844200670719147},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3598218560218811},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.02231","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.02231","pdf_url":"https://arxiv.org/pdf/2408.02231","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2408.02231","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.02231","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:2408.02231","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.02231","pdf_url":"https://arxiv.org/pdf/2408.02231","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5868586035","display_name":"CAREER: Visual Recognition with Knowledge","funder_award_id":"1750082","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8856878232","display_name":"RI: Small: SM-An Active Approach for Data Engineering to Improve Vision-Language Tasks","funder_award_id":"2132724","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309204","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78"},{"id":"https://openalex.org/F4320309835","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403369827.pdf","grobid_xml":"https://content.openalex.org/works/W4403369827.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W291250033","https://openalex.org/W2035757446","https://openalex.org/W3137044537","https://openalex.org/W2008385118","https://openalex.org/W880955280","https://openalex.org/W2106647072","https://openalex.org/W2172753644","https://openalex.org/W2170209930","https://openalex.org/W4246858109","https://openalex.org/W54172855"],"abstract_inverted_index":{"Text-to-Image":[0],"(T2I)":[1],"and":[2,17,91,122,140,157],"multimodal":[3,18],"large":[4],"language":[5],"models":[6,29,111,144],"(MLLMs)":[7],"have":[8],"been":[9,24],"adopted":[10],"in":[11,52,100],"solutions":[12],"for":[13,168],"several":[14],"computer":[15],"vision":[16],"learning":[19],"tasks.":[20],"However,":[21],"it":[22],"has":[23],"found":[25],"that":[26,62,142,160],"such":[27],"vision-language":[28,53],"lack":[30],"the":[31,45,106,120,134],"ability":[32],"to":[33,132,148],"correctly":[34],"reason":[35],"over":[36],"spatial":[37,50,84,107,114,135,150],"relationships.":[38],"To":[39],"tackle":[40],"this":[41],"shortcoming,":[42],"we":[43],"develop":[44],"REVISION":[46,55,72,96],"framework":[47],"which":[48,77],"improves":[49,105],"fidelity":[51],"models.":[54,172],"is":[56,73,164],"a":[57,69,101,129],"3D":[58,81],"rendering":[59],"based":[60],"pipeline":[61],"generates":[63],"spatially":[64],"accurate":[65],"synthetic":[66],"images,":[67],"given":[68],"textual":[70],"prompt.":[71],"an":[74,165],"extendable":[75],"framework,":[76],"currently":[78],"supports":[79],"100+":[80],"assets,":[82],"11":[83],"relationships,":[85,115],"all":[86,113],"with":[87],"diverse":[88],"camera":[89],"perspectives":[90],"backgrounds.":[92],"Leveraging":[93],"images":[94],"from":[95],"as":[97],"additional":[98],"guidance":[99],"training-free":[102],"manner":[103],"consistently":[104],"consistency":[108],"of":[109,138],"T2I":[110],"across":[112],"achieving":[116],"competitive":[117],"performance":[118],"on":[119],"VISOR":[121],"T2I-CompBench":[123],"benchmarks.":[124],"We":[125],"also":[126],"design":[127],"RevQA,":[128],"question-answering":[130],"benchmark":[131],"evaluate":[133],"reasoning":[136,151],"abilities":[137],"MLLMs,":[139],"find":[141],"state-of-the-art":[143],"are":[145],"not":[146],"robust":[147],"complex":[149],"under":[152],"adversarial":[153],"settings.":[154],"Our":[155],"results":[156],"findings":[158],"indicate":[159],"utilizing":[161],"rendering-based":[162],"frameworks":[163],"effective":[166],"approach":[167],"developing":[169],"spatially-aware":[170],"generative":[171]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2024-10-14T00:00:00"}