{"id":"https://openalex.org/W4416750745","doi":"https://doi.org/10.1109/iros60139.2025.11247126","title":"Synthetica: Large Scale Synthetic Data Generation for Robot Perception","display_name":"Synthetica: Large Scale Synthetic Data Generation for Robot Perception","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750745","doi":"https://doi.org/10.1109/iros60139.2025.11247126"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5056045969","display_name":"Ritvik Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ritvik Singh","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101968036","display_name":"Jason Liu","orcid":"https://orcid.org/0000-0002-1864-8281"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Jingzhou Liu","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080936481","display_name":"Karl Van Wyk","orcid":"https://orcid.org/0000-0001-5535-949X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karl Van Wyk","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067607006","display_name":"Yu-Wei Chao","orcid":"https://orcid.org/0000-0002-5476-4343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Wei Chao","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075893457","display_name":"Jean-Francois Lafleche","orcid":"https://orcid.org/0000-0003-4232-1390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Francois Lafleche","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010648258","display_name":"Florian Shkurti","orcid":"https://orcid.org/0000-0002-5672-5831"},"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":"Florian Shkurti","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017897684","display_name":"Nathan Ratliff","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathan Ratliff","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055942061","display_name":"Ankur Handa","orcid":"https://orcid.org/0000-0001-5170-1323"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankur Handa","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5056045969"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4461,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96885177,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7810","last_page":"7817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6833999752998352,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6833999752998352,"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":0.08799999952316284,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.025299999862909317,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/robotics","display_name":"Robotics","score":0.6966000199317932},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.583899974822998},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5443999767303467},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5249999761581421},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4970000088214874},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4878999888896942},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4593999981880188},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.45660001039505005},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.37040001153945923},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.364300012588501}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7318000197410583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7166000008583069},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6966000199317932},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5443999767303467},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.45660001039505005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44429999589920044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.37040001153945923},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.364300012588501},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C173552908","wikidata":"https://www.wikidata.org/wiki/Q1366289","display_name":"Graphics pipeline","level":4,"score":0.3165000081062317},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2580726517","https://openalex.org/W2963188159","https://openalex.org/W2964321964","https://openalex.org/W2970399728","https://openalex.org/W2982770724","https://openalex.org/W2990747716","https://openalex.org/W3096609285","https://openalex.org/W3176659256","https://openalex.org/W3177069133","https://openalex.org/W3201312429","https://openalex.org/W4200634150","https://openalex.org/W4221167977","https://openalex.org/W4226303217","https://openalex.org/W4226344024","https://openalex.org/W4285102264","https://openalex.org/W4312443924","https://openalex.org/W4313026212","https://openalex.org/W4321377343","https://openalex.org/W4362703401","https://openalex.org/W4383108265","https://openalex.org/W4385805054","https://openalex.org/W4386075660","https://openalex.org/W4390872359","https://openalex.org/W4391547487","https://openalex.org/W4402727764","https://openalex.org/W4402754209","https://openalex.org/W4402774769","https://openalex.org/W4402776403"],"related_works":[],"abstract_inverted_index":{"Vision-based":[0],"object":[1,16,95,166],"detectors":[2,170],"are":[3],"a":[4,76,118,140,199],"crucial":[5],"basis":[6],"for":[7,45,55,65,78,83,106,155,194,201,210,228],"robotics":[8,195],"applications":[9,196],"as":[10,59,103,112],"they":[11],"provide":[12],"valuable":[13],"information":[14,242],"about":[15],"localization":[17],"in":[18,27,38,203],"the":[19,92,104,163,181,188,204,221,234],"environment.":[20],"These":[21],"need":[22],"to":[23,67,131,151],"ensure":[24],"high":[25],"reliability":[26],"different":[28],"lighting":[29],"conditions,":[30],"occlusions,":[31],"and":[32,41,52,145,240],"visual":[33],"artifacts,":[34],"all":[35],"while":[36,168,232],"running":[37],"real-time.":[39],"Collecting":[40],"annotating":[42],"real-world":[43],"data":[44,81,116,125,147,226],"these":[46],"networks":[47],"is":[48,176],"prohibitively":[49],"time":[50],"consuming":[51],"costly,":[53],"especially":[54],"custom":[56,208],"assets,":[57],"such":[58,111],"industrial":[60],"objects,":[61],"making":[62],"it":[63],"untenable":[64],"generalization":[66],"in-the-wild":[68],"scenarios.":[69],"To":[70],"this":[71],"end,":[72],"we":[73,122],"present":[74,139],"Synthetica,":[75],"method":[77],"large-scale":[79],"synthetic":[80,225],"generation":[82,227],"training":[84,192],"robust":[85,152,229],"state":[86,108],"estimators.":[87],"This":[88],"paper":[89],"focuses":[90],"on":[91,162],"task":[93,164],"of":[94,142,165,190,223],"detection,":[96],"an":[97],"important":[98],"problem":[99],"which":[100,175,211],"can":[101,243],"serve":[102],"front-end":[105],"most":[107],"estimation":[109],"problems,":[110],"pose":[113],"estimation.":[114],"Leveraging":[115],"from":[117],"photorealistic":[119],"ray-tracing":[120],"renderer,":[121],"scale":[123],"up":[124],"generation,":[126],"generating":[127],"2.7":[128],"million":[129],"images,":[130],"train":[132],"highly":[133],"accurate":[134],"real-time":[135,236],"detection":[136,167],"transformers.":[137],"We":[138,158,185],"collection":[141],"rendering":[143],"randomization":[144],"training-time":[146],"augmentation":[148],"techniques":[149],"conducive":[150],"sim-to-real":[153,230],"performance":[154,161],"vision":[156],"tasks.":[157],"demonstrate":[159,187],"state-of-the-art":[160,183],"having":[169],"that":[171],"run":[172],"at":[173,246],"50\u2013100Hz":[174],"9":[177],"times":[178],"faster":[179],"than":[180],"prior":[182,216],"(SOTA).":[184],"further":[186],"usefulness":[189],"our":[191],"methodology":[193],"by":[197],"showcasing":[198],"pipeline":[200],"use":[202],"real":[205],"world":[206],"with":[207],"objects":[209],"there":[212],"do":[213],"not":[214],"exist":[215],"datasets.":[217],"Our":[218],"work":[219],"highlights":[220],"importance":[222],"scaling":[224],"transfer":[231],"achieving":[233],"fastest":[235],"inference":[237],"speeds.":[238],"Videos":[239],"supplementary":[241],"be":[244],"found":[245],"https://sites.google.com/view/synthetica-vision":[247]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-11-28T00:00:00"}