{"id":"https://openalex.org/W4405271034","doi":"https://doi.org/10.1109/cvmi61877.2024.10782691","title":"TexAVi: Generating Stereoscopic VR Video Clips from Text Descriptions","display_name":"TexAVi: Generating Stereoscopic VR Video Clips from Text Descriptions","publication_year":2024,"publication_date":"2024-10-19","ids":{"openalex":"https://openalex.org/W4405271034","doi":"https://doi.org/10.1109/cvmi61877.2024.10782691"},"language":"en","primary_location":{"id":"doi:10.1109/cvmi61877.2024.10782691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi61877.2024.10782691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.01156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shruti Jayaraman","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shruti Jayaraman","raw_affiliation_strings":["College of Engineering, Guindy,Dept. of Computer Science and Engineering,Chennai,India"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Guindy,Dept. of Computer Science and Engineering,Chennai,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069140102","display_name":"R Bhavya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R Bhavya","raw_affiliation_strings":["College of Engineering, Guindy,Dept. of Computer Science and Engineering,Chennai,India"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Guindy,Dept. of Computer Science and Engineering,Chennai,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vriksha Srihari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vriksha Srihari","raw_affiliation_strings":["College of Engineering, Guindy,Dept. of Computer Science and Engineering,Chennai,India"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Guindy,Dept. of Computer Science and Engineering,Chennai,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089830684","display_name":"V. Mary Anita Rajam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"V Mary Anita Rajam","raw_affiliation_strings":["College of Engineering, Guindy,Dept. of Computer Science and Engineering,Chennai,India"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Guindy,Dept. of Computer Science and Engineering,Chennai,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.22013523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9925000071525574,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9925000071525574,"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/T12290","display_name":"Human Motion and Animation","score":0.9878000020980835,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9721999764442444,"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/clips","display_name":"CLIPS","score":0.8931376934051514},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.818851113319397},{"id":"https://openalex.org/keywords/stereoscopy","display_name":"Stereoscopy","score":0.7036254405975342},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.49764588475227356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4091615676879883},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3807717561721802}],"concepts":[{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.8931376934051514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818851113319397},{"id":"https://openalex.org/C126057942","wikidata":"https://www.wikidata.org/wiki/Q35158","display_name":"Stereoscopy","level":2,"score":0.7036254405975342},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.49764588475227356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4091615676879883},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3807717561721802}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvmi61877.2024.10782691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi61877.2024.10782691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.01156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.01156","pdf_url":"https://arxiv.org/pdf/2501.01156","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.01156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.01156","pdf_url":"https://arxiv.org/pdf/2501.01156","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"While":[0],"generative":[1,49],"models":[2,8],"such":[3],"as":[4],"text-to-image,":[5],"large":[6],"language":[7],"and":[9,29,36,96,110,135,144,156],"text-to-video":[10],"have":[11],"seen":[12],"significant":[13],"progress,":[14],"the":[15,30,86,161,168,174,177,183],"extension":[16],"to":[17,23,46,51,90,107,117,159],"text-to-virtual-reality":[18],"remains":[19],"largely":[20],"unexplored,":[21],"due":[22],"a":[24,53,69],"deficit":[25],"in":[26,38,62,129,191],"training":[27],"data":[28],"complexity":[31],"of":[32,142,164,176,186],"achieving":[33],"realistic":[34],"depth":[35,104],"motion":[37],"virtual":[39,55,130,194],"environments.":[40],"This":[41],"paper":[42],"proposes":[43],"an":[44,77,119],"approach":[45],"coalesce":[47],"existing":[48],"systems":[50,124],"form":[52],"stereoscopic":[54],"reality":[56,131,195],"video":[57],"from":[58,76],"text.":[59,79],"Carried":[60],"out":[61],"three":[63],"main":[64],"stages,":[65],"we":[66],"start":[67],"with":[68,93,103],"base":[70],"text-to-image":[71],"model":[72],"that":[73],"captures":[74],"context":[75],"input":[78],"We":[80,147],"then":[81],"employ":[82],"Stable":[83],"Diffusion":[84],"on":[85],"rudimentary":[87],"image":[88,149],"produced,":[89],"generate":[91],"frames":[92,100,165],"enhanced":[94],"realism":[95],"overall":[97],"quality.":[98],"These":[99,170],"are":[101,114],"processed":[102],"estimation":[105],"algorithms":[106],"create":[108,118],"left-eye":[109],"right-eye":[111],"views,":[112],"which":[113],"stitched":[115],"side-by-side":[116],"immersive":[120],"viewing":[121],"experience.":[122],"Such":[123],"would":[125],"be":[126],"highly":[127],"beneficial":[128],"production,":[132],"since":[133],"filming":[134],"scene":[136],"building":[137],"often":[138],"require":[139],"extensive":[140],"hours":[141],"work":[143,181],"post-production":[145],"effort.":[146],"utilize":[148],"evaluation":[150],"techniques,":[151],"specifically":[152],"Fr\u00e9chet":[153],"Inception":[154],"Distance":[155],"CLIP":[157],"Score,":[158],"assess":[160],"visual":[162],"quality":[163],"produced":[166],"for":[167],"video.":[169],"quantitative":[171],"measures":[172],"establish":[173],"proficiency":[175],"proposed":[178],"method.":[179],"Our":[180],"highlights":[182],"exciting":[184],"possibilities":[185],"using":[187],"natural":[188],"language-driven":[189],"graphics":[190],"fields":[192],"like":[193],"simulations.":[196]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2024-12-12T00:00:00"}