{"id":"https://openalex.org/W4413945146","doi":"https://doi.org/10.1109/icra55743.2025.11128068","title":"Dualdiff: Dual-Branch Diffusion Model for Autonomous Driving with Semantic Fusion","display_name":"Dualdiff: Dual-Branch Diffusion Model for Autonomous Driving with Semantic Fusion","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945146","doi":"https://doi.org/10.1109/icra55743.2025.11128068"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5040809961","display_name":"Haoteng Li","orcid":"https://orcid.org/0000-0003-2135-3422"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoteng Li","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100546340","display_name":"Yang Zhao","orcid":"https://orcid.org/0009-0000-5169-3669"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zezhong Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zezhong Qian","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079646718","display_name":"Gongpeng Zhao","orcid":"https://orcid.org/0009-0004-1019-1477"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongpeng Zhao","raw_affiliation_strings":["University of Science and Technology of China,Hefei,Anhui,China,230026"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,Anhui,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002182146","display_name":"Yuqi Huang","orcid":"https://orcid.org/0009-0003-1021-2103"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Huang","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,Anhui,China,230026"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,Anhui,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020775850","display_name":"Huazheng Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huazheng Zhou","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080046377","display_name":"Longjun Liu","orcid":"https://orcid.org/0000-0002-7467-4994"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longjun Liu","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,Shaanxi,China,710049","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"13312","last_page":"13319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.6700999736785889,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.6700999736785889,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T11195","display_name":"Simulation Techniques and Applications","score":0.6603999733924866,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6594376564025879},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6218486428260803},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.585999608039856},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4929184913635254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3623237907886505},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09192594885826111}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6594376564025879},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6218486428260803},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.585999608039856},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4929184913635254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3623237907886505},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09192594885826111},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7988909197","display_name":null,"funder_award_id":"NSFC 62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2756327937","https://openalex.org/W2899072036","https://openalex.org/W3035172746","https://openalex.org/W3035574168","https://openalex.org/W4200150166","https://openalex.org/W4312641958","https://openalex.org/W4312894406","https://openalex.org/W4312933868","https://openalex.org/W4383066393","https://openalex.org/W4390873054","https://openalex.org/W4390874598","https://openalex.org/W4391807781","https://openalex.org/W4392016505","https://openalex.org/W4393148069","https://openalex.org/W4394862623","https://openalex.org/W4401109681","https://openalex.org/W4401414033","https://openalex.org/W4402727021","https://openalex.org/W4402727035","https://openalex.org/W4402727180","https://openalex.org/W4402778069","https://openalex.org/W4403759442","https://openalex.org/W4404722496","https://openalex.org/W4409366191"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Accurate":[0],"and":[1,23,28,40,80,98,135],"high-fidelity":[2],"driving":[3,59,74],"scene":[4,10,39,60,75],"reconstruction":[5],"relies":[6],"on":[7],"fully":[8],"leveraging":[9],"information":[11,86],"as":[12,125,127],"conditioning.":[13],"However,":[14],"existing":[15],"approaches,":[16],"which":[17],"primarily":[18],"use":[19],"3D":[20,70,136],"bounding":[21],"boxes":[22],"binary":[24],"maps":[25],"for":[26,77],"foreground":[27,79],"background":[29,81],"control,":[30],"fall":[31],"short":[32],"in":[33,122,131],"capturing":[34],"the":[35,38,113],"complexity":[36],"of":[37,115],"integrating":[41],"multi-modal":[42],"information.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,88,104],"propose":[48,89],"DualDiff,":[49],"a":[50,68,90,106],"dual-branch":[51],"conditional":[52],"diffusion":[53],"model":[54],"designed":[55],"to":[56,111],"enhance":[57,112],"multi-view":[58],"generation.":[61],"We":[62],"introduce":[63],"Occupancy":[64],"Ray":[65],"Sampling":[66],"(ORS),":[67],"semantic-rich":[69],"representation,":[71,76],"alongside":[72],"numerical":[73],"comprehensive":[78],"control.":[82],"To":[83],"improve":[84],"cross-modal":[85],"integration,":[87],"Semantic":[91],"Fusion":[92],"Attention":[93],"(SFA)":[94],"mechanism":[95],"that":[96],"aligns":[97],"fuses":[99],"features":[100],"across":[101],"modalities.":[102],"Furthermore,":[103],"design":[105],"foreground-aware":[107],"masked":[108],"(FGM)":[109],"loss":[110],"generation":[114],"tiny":[116],"objects.":[117],"DualDiff":[118],"achieves":[119],"state-of-the-art":[120],"performance":[121],"FID":[123],"score,":[124],"well":[126],"consistently":[128],"better":[129],"results":[130],"downstream":[132],"BEV":[133],"segmentation":[134],"object":[137],"detection":[138],"tasks.":[139]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}