{"id":"https://openalex.org/W4412536349","doi":"https://doi.org/10.1109/access.2025.3591146","title":"ETIA:Enhancing Text2Image surround view scene generation with semantic annotation via diffusion for autonomous driving","display_name":"ETIA:Enhancing Text2Image surround view scene generation with semantic annotation via diffusion for autonomous driving","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412536349","doi":"https://doi.org/10.1109/access.2025.3591146"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3591146","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591146","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3591146","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029107828","display_name":"Ramyashree Ramyashree","orcid":null},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ramyashree","raw_affiliation_strings":["Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India"],"raw_orcid":"https://orcid.org/0000-0002-0237-2444","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India","institution_ids":["https://openalex.org/I164861460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061441269","display_name":"S Raghavendra","orcid":null},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S Raghavendra","raw_affiliation_strings":["Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India"],"raw_orcid":"https://orcid.org/0000-0003-2733-3916","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India","institution_ids":["https://openalex.org/I164861460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010573887","display_name":"S. K. Abhilash","orcid":"https://orcid.org/0000-0002-1119-4782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S K Abhilash","raw_affiliation_strings":["KPIT Technologies, Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0002-1119-4782","affiliations":[{"raw_affiliation_string":"KPIT Technologies, Bengaluru, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008205311","display_name":"Venu Madhav Nookala","orcid":"https://orcid.org/0000-0002-0078-5050"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Venu Madhav Nookala","raw_affiliation_strings":["KPIT Technologies, Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0002-0078-5050","affiliations":[{"raw_affiliation_string":"KPIT Technologies, Bengaluru, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053942457","display_name":"Arun Kumar","orcid":"https://orcid.org/0000-0002-5493-8059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arun Kumar","raw_affiliation_strings":["KPIT Technologies, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KPIT Technologies, Bengaluru, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093780454","display_name":"P Malashree","orcid":null},"institutions":[{"id":"https://openalex.org/I2802584695","display_name":"Government of Karnataka","ror":"https://ror.org/00maf9573","country_code":"IN","type":"government","lineage":["https://openalex.org/I2802584695"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P Malashree","raw_affiliation_strings":["Government P.U College for Girls, Udupi, Karnataka, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Government P.U College for Girls, Udupi, Karnataka, India","institution_ids":["https://openalex.org/I2802584695"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5029107828"],"corresponding_institution_ids":["https://openalex.org/I164861460"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14418993,"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":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9764000177383423,"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":0.9764000177383423,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9749000072479248,"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":0.9699000120162964,"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/computer-science","display_name":"Computer science","score":0.7762665152549744},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6289759874343872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6167214512825012},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5314186215400696},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4622390568256378},{"id":"https://openalex.org/keywords/semantic-annotation","display_name":"Semantic annotation","score":0.4209679961204529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762665152549744},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6289759874343872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6167214512825012},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5314186215400696},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4622390568256378},{"id":"https://openalex.org/C2985727698","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Semantic annotation","level":3,"score":0.4209679961204529},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3591146","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591146","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0220d04561634b6780c19e032616fee4","is_oa":true,"landing_page_url":"https://doaj.org/article/0220d04561634b6780c19e032616fee4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"IEEE Access, Vol 13, Pp 132209-132222 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3591146","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591146","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"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":{"Generating":[0],"high-fidelity":[1],"surround":[2,42,177,271],"view":[3,43,178,272],"images":[4,273],"from":[5],"text":[6,50,55,81],"prompts":[7,56],"is":[8],"a":[9,24,48,147,210],"complex":[10],"task":[11],"that":[12,27,105,127],"requires":[13],"balancing":[14],"contextual":[15,58],"coherence":[16,116],"with":[17,33,83,117,274],"computational":[18],"efficiency.":[19],"The":[20,45,139,180],"proposed":[21,66,170,181,264],"work":[22,265],"introduces":[23],"novel":[25],"methodology":[26],"combines":[28],"recurrent":[29],"attention-based":[30],"encoder-decoder":[31],"architectures":[32],"text-to-image":[34,281],"diffusion":[35],"models":[36],"to":[37,52,96,110,252,256],"produce":[38],"coherent":[39],"and":[40,135,152,188,199,206,217,225,243,254,283],"continuous":[41],"images.":[44,119,179],"approach":[46,203],"utilizes":[47],"custom":[49],"encoder":[51],"convert":[53],"input":[54],"into":[57],"embeddings,":[59],"which":[60],"are":[61],"then":[62],"processed":[63],"by":[64],"the":[65,71,89,100,161,166,169,231,261,278],"ViewNet":[67],"Unet2d":[68],"architecture":[69,74],"within":[70],"decoder.":[72],"This":[73,102],"employs":[75],"dual":[76],"cross-attention":[77],"mechanisms:":[78],"one":[79],"aligns":[80],"embeddings":[82],"corresponding":[84],"noise":[85],"image":[86,94,108,144],"latents,":[87],"while":[88,114],"other":[90],"integrates":[91],"previously":[92],"generated":[93,107],"latents":[95],"ensure":[97],"continuity":[98],"across":[99],"sequence.":[101],"method":[103],"guarantees":[104],"each":[106,156],"adheres":[109],"its":[111],"specific":[112],"prompt,":[113],"maintaining":[115],"preceding":[118],"In":[120],"addition,":[121],"an":[122,184,189],"annotation":[123,140,157],"decoder":[124,141],"was":[125],"introduced":[126],"generates":[128],"semantic":[129],"segmentation":[130,133,205],"maps,":[131],"instance":[132],"masks,":[134],"object":[136],"detection":[137,207],"annotations.":[138],"processes":[142],"latent":[143],"maps":[145],"using":[146],"shared":[148],"feature":[149],"extraction":[150],"backbone":[151],"dedicated":[153],"heads":[154],"for":[155],"task.Experimental":[158],"results":[159,259],"on":[160],"nuScenes":[162],"validation":[163],"set":[164],"demonstrate":[165,260],"effectiveness":[167,262],"of":[168,186,191,212,215,219,233,263,280],"model":[171,182],"in":[172,236,266],"producing":[173,267],"high-quality":[174],"contextually":[175,269],"aligned":[176,270],"achieves":[183],"FVD":[185,251],"99":[187,253],"FID":[190,255],"12.6,":[192],"outperforming":[193],"existing":[194],"methods":[195,222],"such":[196],"as":[197],"Panacea+":[198],"DriveDreamer-2.":[200],"Furthermore,":[201],"our":[202,237],"improves":[204],"accuracy,":[208],"achieving":[209],"PQ":[211],"67.4,":[213],"mIoU":[214],"80.1,":[216],"mAP":[218],"65.4,":[220],"surpassing":[221],"like":[223],"OpenSeeD":[224],"D2Det.":[226],"An":[227],"ablation":[228],"study":[229],"highlights":[230],"contributions":[232],"key":[234],"components":[235],"architecture.":[238],"Integrating":[239],"positional":[240],"encoding,":[241],"self-attention,":[242],"concurrent":[244],"attention":[245],"significantly":[246],"enhances":[247],"generation":[248],"quality,":[249],"reducing":[250],"12.6.":[257],"Experimental":[258],"high-quality,":[268],"comprehensive":[275],"annotations,":[276],"pushing":[277],"boundaries":[279],"synthesis":[282],"scene":[284],"understanding.":[285]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}