{"id":"https://openalex.org/W4401416369","doi":"https://doi.org/10.1109/icra57147.2024.10611235","title":"From Bird\u2019s-Eye to Street View: Crafting Diverse and Condition-Aligned Images with Latent Diffusion Model","display_name":"From Bird\u2019s-Eye to Street View: Crafting Diverse and Condition-Aligned Images with Latent Diffusion Model","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416369","doi":"https://doi.org/10.1109/icra57147.2024.10611235"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611235","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10611235","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 Robotics and Automation (ICRA)","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/A5037481266","display_name":"Xiaojie Xu","orcid":"https://orcid.org/0000-0002-3614-1070"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Xiaojie Xu","raw_affiliation_strings":["The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026716341","display_name":"Tianshuo Xu","orcid":"https://orcid.org/0009-0006-2142-4664"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tianshuo Xu","raw_affiliation_strings":["The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051297619","display_name":"Fulong Ma","orcid":"https://orcid.org/0000-0002-3681-9611"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fulong Ma","raw_affiliation_strings":["The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101938761","display_name":"Ying-Cong Chen","orcid":"https://orcid.org/0000-0002-9565-8205"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yingcong Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037481266"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.5248,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64773647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"16795","last_page":"16802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9934999942779541,"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/diffusion","display_name":"Diffusion","score":0.6112158298492432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5476691722869873},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43338069319725037},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.41574159264564514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3242051303386688},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1081748902797699}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6112158298492432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5476691722869873},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43338069319725037},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.41574159264564514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3242051303386688},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1081748902797699},{"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/icra57147.2024.10611235","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10611235","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 Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1991742456","https://openalex.org/W2054389289","https://openalex.org/W2475287302","https://openalex.org/W2735039185","https://openalex.org/W2737258237","https://openalex.org/W2952716587","https://openalex.org/W2962819541","https://openalex.org/W2962974533","https://openalex.org/W2963066677","https://openalex.org/W2963073614","https://openalex.org/W2964294967","https://openalex.org/W2970562905","https://openalex.org/W3016121695","https://openalex.org/W3035172746","https://openalex.org/W3035574168","https://openalex.org/W3105636206","https://openalex.org/W3109395584","https://openalex.org/W3162926177","https://openalex.org/W3168867926","https://openalex.org/W3180355996","https://openalex.org/W3203076355","https://openalex.org/W3203158837","https://openalex.org/W3203593958","https://openalex.org/W3211490618","https://openalex.org/W4226125322","https://openalex.org/W4281485151","https://openalex.org/W4301206121","https://openalex.org/W4312641958","https://openalex.org/W4312894406","https://openalex.org/W4312933868","https://openalex.org/W4313015712","https://openalex.org/W4313484219","https://openalex.org/W4385245566","https://openalex.org/W4386047807","https://openalex.org/W4386072096","https://openalex.org/W4390873054","https://openalex.org/W4392016505","https://openalex.org/W6679045638","https://openalex.org/W6738824914","https://openalex.org/W6755312952","https://openalex.org/W6765779288","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6796581206","https://openalex.org/W6801880476","https://openalex.org/W6810940779","https://openalex.org/W6811013733","https://openalex.org/W6838633692","https://openalex.org/W6838639034"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"We":[0],"explore":[1],"Bird\u2019s-Eye":[2],"View":[3,125,134],"(BEV)":[4],"generation,":[5],"converting":[6],"a":[7,99,107,114,168,172],"BEV":[8,25,38,115,139,154],"map":[9,140],"into":[10,141],"its":[11,18],"corresponding":[12],"multi-view":[13,143],"street":[14,205],"images.":[15,207],"Valued":[16],"for":[17,28,42,92,110],"unified":[19],"spatial":[20],"representation":[21],"aiding":[22],"multi-sensor":[23],"fusion,":[24],"is":[26,40],"pivotal":[27],"various":[29],"autonomous":[30],"driving":[31,49],"applications.":[32],"Creating":[33],"accurate":[34],"street-view":[35],"images":[36,112],"from":[37,113],"maps":[39,146],"essential":[41],"portraying":[43],"complex":[44],"traffic":[45,198],"scenarios":[46],"and":[47,66,78,127,155,183,203],"enhancing":[48],"algorithms.":[50],"Concurrently,":[51],"diffusion-based":[52],"conditional":[53,94],"image":[54],"generation":[55,95],"models":[56,74,196],"have":[57],"demonstrated":[58],"remarkable":[59],"outcomes,":[60],"adept":[61],"at":[62],"producing":[63],"diverse,":[64],"high-quality,":[65],"condition-aligned":[67],"results.":[68],"Nonetheless,":[69],"the":[70,123,128,138,149,153,159,189],"training":[71],"of":[72,192],"these":[73,86,165],"demands":[75],"substantial":[76],"data":[77],"computational":[79],"resources.":[80],"Hence,":[81],"exploring":[82],"methods":[83],"to":[84,170],"fine-tune":[85],"advanced":[87],"models,":[88],"like":[89],"Stable":[90],"Diffusion,":[91],"specific":[93],"tasks":[96],"emerges":[97],"as":[98,167],"promising":[100],"avenue.":[101],"In":[102],"this":[103],"paper,":[104],"we":[105],"introduce":[106],"practical":[108],"framework":[109],"generating":[111],"layout.":[116],"Our":[117,186],"approach":[118],"comprises":[119],"two":[120],"main":[121],"components:":[122],"Neural":[124,133],"Transformation":[126,135],"Street":[129,160],"Image":[130,161],"Generation.":[131],"The":[132],"phase":[136,163],"converts":[137],"aligned":[142],"semantic":[144],"segmentation":[145],"by":[147],"learning":[148],"shape":[150],"correspondence":[151],"between":[152],"perspective":[156],"views.":[157],"Subsequently,":[158],"Generation":[162],"utilizes":[164],"segmentations":[166],"condition":[169],"guide":[171],"fine-tuned":[173],"latent":[174],"diffusion":[175,195],"model.":[176],"This":[177],"finetuning":[178],"process":[179],"ensures":[180],"both":[181],"view":[182,206],"style":[184],"consistency.":[185],"model":[187],"leverages":[188],"generative":[190],"capacity":[191],"large":[193],"pretrained":[194],"within":[197],"contexts,":[199],"effectively":[200],"yielding":[201],"diverse":[202],"condition-coherent":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}