{"id":"https://openalex.org/W7131070915","doi":"https://doi.org/10.1109/iccvw69036.2025.00046","title":"Controllable Generation with Disentangled Representative Learning of Multiple Perspectives in Autonomous Driving","display_name":"Controllable Generation with Disentangled Representative Learning of Multiple Perspectives in Autonomous Driving","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131070915","doi":"https://doi.org/10.1109/iccvw69036.2025.00046"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00046","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 Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060107167","display_name":"Haoran Jin","orcid":"https://orcid.org/0000-0001-7555-6685"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Haoran Jin","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060107167"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"388","last_page":"395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10869999974966049,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10869999974966049,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09560000151395798,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.08380000293254852,"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/modular-design","display_name":"Modular design","score":0.6759999990463257},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6406000256538391},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6323000192642212},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.534600019454956},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4814999997615814},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4779999852180481},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43470001220703125},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41339999437332153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390000224113464},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6759999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6482999920845032},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6406000256538391},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4779999852180481},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36880001425743103},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36160001158714294},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00046","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 Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7244726419448853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2071524685","https://openalex.org/W2519536754","https://openalex.org/W2601686579","https://openalex.org/W2748021867","https://openalex.org/W2933283236","https://openalex.org/W2962770929","https://openalex.org/W2962793285","https://openalex.org/W2962912205","https://openalex.org/W3035574168","https://openalex.org/W3173531806","https://openalex.org/W3175645231","https://openalex.org/W3176179930","https://openalex.org/W3176368002","https://openalex.org/W3176726917","https://openalex.org/W3180355996","https://openalex.org/W3195511699","https://openalex.org/W3201594678","https://openalex.org/W3203597819","https://openalex.org/W3204859697","https://openalex.org/W3207845222","https://openalex.org/W4200150166","https://openalex.org/W4285411754","https://openalex.org/W4312453532","https://openalex.org/W4386352865","https://openalex.org/W4390872379","https://openalex.org/W4400188660","https://openalex.org/W4403878008","https://openalex.org/W4404654662","https://openalex.org/W4413947039","https://openalex.org/W4415795895","https://openalex.org/W4415796825"],"related_works":[],"abstract_inverted_index":{"We":[0,64],"present":[1],"a":[2,18,38,69],"novel":[3],"framework":[4],"for":[5],"controllable":[6,82],"multi-view":[7,71],"image":[8],"generation":[9],"in":[10,87],"autonomous":[11],"driving":[12,30,72],"scenarios.":[13],"Our":[14],"method":[15],"builds":[16],"upon":[17],"modular":[19],"generative":[20],"architecture":[21],"that":[22],"disentangles":[23],"key":[24],"semantic":[25,62],"factors-specifically,":[26],"weather":[27],"conditions":[28],"and":[29,42,74,91],"speed-from":[31],"the":[32,48],"underlying":[33],"scene":[34],"representation.":[35],"By":[36],"leveraging":[37],"structured":[39],"latent":[40],"encoder":[41],"volumetric":[43],"rendering,":[44],"our":[45,66],"model":[46],"enables":[47],"synthesis":[49],"of":[50],"realistic":[51],"images":[52],"under":[53],"arbitrary":[54],"camera":[55],"viewpoints,":[56],"including":[57],"missing":[58],"views,":[59,83],"while":[60],"preserving":[61],"consistency.":[63],"validate":[65],"approach":[67],"on":[68],"custom":[70],"dataset":[73],"demonstrate":[75],"its":[76],"ability":[77],"to":[78],"generate":[79],"high-fidelity,":[80],"semantically":[81],"showcasing":[84],"improved":[85],"performance":[86],"disentangled":[88],"representation":[89],"learning":[90],"view":[92],"completion.":[93]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-24T00:00:00"}