{"id":"https://openalex.org/W4415540607","doi":"https://doi.org/10.1145/3746027.3754772","title":"OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving","display_name":"OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540607","doi":"https://doi.org/10.1145/3746027.3754772"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754772","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5081233515","display_name":"Tao Tang","orcid":"https://orcid.org/0000-0001-8526-220X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Tang","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8526-220X","affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102535824","display_name":"Enhui Ma","orcid":"https://orcid.org/0009-0003-5334-7024"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhui Ma","raw_affiliation_strings":["Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-5334-7024","affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100886272","display_name":"Xia Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia Zhou","raw_affiliation_strings":["Li Auto Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-1892-351X","affiliations":[{"raw_affiliation_string":"Li Auto Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045596261","display_name":"Letian Wang","orcid":"https://orcid.org/0000-0002-0231-6960"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Letian Wang","raw_affiliation_strings":["The University of Toronto, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0231-6960","affiliations":[{"raw_affiliation_string":"The University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025994300","display_name":"Tianyi Yan","orcid":"https://orcid.org/0000-0003-3685-2566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Yan","raw_affiliation_strings":["Li Auto Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3685-2566","affiliations":[{"raw_affiliation_string":"Li Auto Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013396646","display_name":"X K Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueyang Zhang","raw_affiliation_strings":["Li Auto Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-3678-5761","affiliations":[{"raw_affiliation_string":"Li Auto Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Zhan","orcid":"https://orcid.org/0000-0002-4208-5220"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zhan","raw_affiliation_strings":["Li Auto Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4208-5220","affiliations":[{"raw_affiliation_string":"Li Auto Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066851686","display_name":"Peng Jia","orcid":"https://orcid.org/0000-0002-2273-3892"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Jia","raw_affiliation_strings":["Li Auto Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2273-3892","affiliations":[{"raw_affiliation_string":"Li Auto Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065122260","display_name":"Xianpeng Lang","orcid":"https://orcid.org/0000-0002-2620-7128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianpeng Lang","raw_affiliation_strings":["Li Auto Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2620-7128","affiliations":[{"raw_affiliation_string":"Li Auto Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072209031","display_name":"Jia-Wang Bian","orcid":"https://orcid.org/0000-0003-2046-3363"},"institutions":[{"id":"https://openalex.org/I3130757197","display_name":"Distance State University","ror":"https://ror.org/0529rbt18","country_code":"CR","type":"education","lineage":["https://openalex.org/I3130757197"]}],"countries":["CR"],"is_corresponding":false,"raw_author_name":"Jia-Wang Bian","raw_affiliation_strings":["ByteDance Seed, San Jose, USA"],"raw_orcid":"https://orcid.org/0000-0003-2046-3363","affiliations":[{"raw_affiliation_string":"ByteDance Seed, San Jose, USA","institution_ids":["https://openalex.org/I3130757197"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038563167","display_name":"Kaicheng Yu","orcid":"https://orcid.org/0000-0002-0186-3399"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaicheng Yu","raw_affiliation_strings":["Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0186-3399","affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3213-3062","affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":12,"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":0.29183478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9365","last_page":"9374"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9927999973297119,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/focus","display_name":"Focus (optics)","score":0.4196000099182129},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4189999997615814},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3840000033378601},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.34299999475479126},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.328000009059906},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.2849999964237213},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.2831999957561493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056000232696533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5338000059127808},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3163999915122986},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754772","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2236135741","display_name":null,"funder_award_id":"2024YFE0203100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2897529137","https://openalex.org/W2963727135","https://openalex.org/W3003474258","https://openalex.org/W3035574168","https://openalex.org/W3176368002","https://openalex.org/W3204859697","https://openalex.org/W4311033863","https://openalex.org/W4312369535","https://openalex.org/W4312739686","https://openalex.org/W4312894406","https://openalex.org/W4312933868","https://openalex.org/W4383066393","https://openalex.org/W4386076215","https://openalex.org/W4386076299","https://openalex.org/W4386076400","https://openalex.org/W4390872297","https://openalex.org/W4390873054"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"driving":[1],"has":[2],"seen":[3],"remarkable":[4],"advancements,":[5],"largely":[6],"driven":[7],"by":[8,31],"extensive":[9],"real-world":[10],"data":[11,18,65,144],"collection.":[12],"However,":[13,36],"acquiring":[14],"diverse":[15],"and":[16,21,47,84,97,111,149],"corner-case":[17],"remains":[19],"costly":[20],"inefficient.":[22],"Generative":[23],"models":[24],"have":[25],"emerged":[26],"as":[27],"a":[28,67,73,86,117,122],"promising":[29],"solution":[30],"synthesizing":[32],"realistic":[33],"sensor":[34,51,64,104,129,143,151],"data.":[35,52,100],"existing":[37],"approaches":[38],"primarily":[39],"focus":[40],"on":[41],"single-modality":[42],"generation,":[43],"leading":[44],"to":[45,80,93,125],"inefficiencies":[46],"misalignment":[48],"in":[49,66,140],"multimodal":[50,63,82,89,103,128,142,147],"To":[53],"address":[54],"these":[55],"challenges,":[56],"we":[57,115],"propose":[58],"OminiGen,":[59],"which":[60],"generates":[61],"aligned":[62],"unified":[68,141],"framework.":[69],"Our":[70,131],"approach":[71],"leverages":[72],"shared":[74],"Bird's":[75],"Eye":[76],"View":[77],"(BEV)":[78],"space":[79],"unify":[81],"features":[83],"designs":[85],"novel":[87],"generalizable":[88],"reconstruction":[90],"method,":[91],"UAE,":[92],"jointly":[94],"decode":[95],"LiDAR":[96],"multi-view":[98],"camera":[99],"UAE":[101],"achieves":[102,137],"decoding":[105],"through":[106],"volume":[107],"rendering,":[108],"enabling":[109],"accurate":[110],"flexible":[112,150],"reconstruction.":[113],"Furthermore,":[114],"incorporate":[116],"Diffusion":[118],"Transformer":[119],"(DiT)":[120],"with":[121,146],"ControlNet":[123],"branch":[124],"enable":[126],"controllable":[127],"generation.":[130],"comprehensive":[132],"experiments":[133],"demonstrate":[134],"that":[135],"OminiGen":[136],"desired":[138],"performances":[139],"generation":[145],"consistency":[148],"adjustments.":[152]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}