{"id":"https://openalex.org/W2927673689","doi":"https://doi.org/10.1109/icip.2019.8803821","title":"Photorealistic Image Synthesis for Object Instance Detection","display_name":"Photorealistic Image Synthesis for Object Instance Detection","publication_year":2019,"publication_date":"2019-08-26","ids":{"openalex":"https://openalex.org/W2927673689","doi":"https://doi.org/10.1109/icip.2019.8803821","mag":"2927673689"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2019.8803821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8803821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.03334","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021750947","display_name":"Tom\u00e1\u0161 Hoda\u0148","orcid":"https://orcid.org/0000-0003-0576-9997"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Tomas Hodan","raw_affiliation_strings":["Czech Technical University, Prague, Czech Republic","FEE, Czech Technical University, Prague"],"affiliations":[{"raw_affiliation_string":"Czech Technical University, Prague, Czech Republic","institution_ids":["https://openalex.org/I44504214"]},{"raw_affiliation_string":"FEE, Czech Technical University, Prague","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045147286","display_name":"Vibhav Vineet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vibhav Vineet","raw_affiliation_strings":["Microsoft Research","Microsoft Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research#TAB#","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110897846","display_name":"Ran Gal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ran Gal","raw_affiliation_strings":["Microsoft Research","Microsoft Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research#TAB#","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083066877","display_name":"Emanuel Shalev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emanuel Shalev","raw_affiliation_strings":["Microsoft Research","Microsoft Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research#TAB#","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040844528","display_name":"Jon Hanzelka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jon Hanzelka","raw_affiliation_strings":["Microsoft Research","Microsoft Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research#TAB#","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027474877","display_name":"Treb Connell","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Treb Connell","raw_affiliation_strings":["Microsoft Research","Microsoft Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research#TAB#","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009471971","display_name":"Pedro Urbina","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pedro Urbina","raw_affiliation_strings":["Microsoft Research","Microsoft Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research#TAB#","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090341044","display_name":"Sudipta N. Sinha","orcid":"https://orcid.org/0000-0002-4186-3289"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sudipta N. Sinha","raw_affiliation_strings":["Microsoft Research","Microsoft Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research#TAB#","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060197083","display_name":"Brian Guenter","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Brian Guenter","raw_affiliation_strings":["Microsoft Research","Microsoft Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research#TAB#","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5021750947"],"corresponding_institution_ids":["https://openalex.org/I44504214"],"apc_list":null,"apc_paid":null,"fwci":2.0433,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.89695288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.8473491668701172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.802391529083252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7554534673690796},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6935895085334778},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6920742392539978},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5460656881332397},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5371143817901611},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.536666750907898},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.516676664352417},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.5028697848320007},{"id":"https://openalex.org/keywords/3d-rendering","display_name":"3D rendering","score":0.43951335549354553},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.356245219707489},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.25501954555511475}],"concepts":[{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.8473491668701172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802391529083252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7554534673690796},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6935895085334778},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6920742392539978},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5460656881332397},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5371143817901611},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.536666750907898},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.516676664352417},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.5028697848320007},{"id":"https://openalex.org/C36816356","wikidata":"https://www.wikidata.org/wiki/Q16911860","display_name":"3D rendering","level":3,"score":0.43951335549354553},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.356245219707489},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25501954555511475}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icip.2019.8803821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8803821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.03334","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.03334","pdf_url":"https://arxiv.org/pdf/1902.03334","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2927673689","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1902.03334","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1902.03334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.03334","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.03334","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.03334","pdf_url":"https://arxiv.org/pdf/1902.03334","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4818322051","display_name":null,"funder_award_id":"019/0000765","funder_id":"https://openalex.org/F4320334253","funder_display_name":"Research Center for Informatics, Czech Technical University in Prague"}],"funders":[{"id":"https://openalex.org/F4320334253","display_name":"Research Center for Informatics, Czech Technical University in Prague","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2927673689.pdf","grobid_xml":"https://content.openalex.org/works/W2927673689.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W132147841","https://openalex.org/W639708223","https://openalex.org/W764651262","https://openalex.org/W1526868886","https://openalex.org/W1591870335","https://openalex.org/W1769933788","https://openalex.org/W1861492603","https://openalex.org/W2054170361","https://openalex.org/W2141364309","https://openalex.org/W2194775991","https://openalex.org/W2221752211","https://openalex.org/W2274287116","https://openalex.org/W2299591120","https://openalex.org/W2312004824","https://openalex.org/W2315410813","https://openalex.org/W2341569833","https://openalex.org/W2397830550","https://openalex.org/W2431874326","https://openalex.org/W2487365028","https://openalex.org/W2557728737","https://openalex.org/W2563100679","https://openalex.org/W2567101557","https://openalex.org/W2604236302","https://openalex.org/W2605102758","https://openalex.org/W2613718673","https://openalex.org/W2744438518","https://openalex.org/W2756073160","https://openalex.org/W2766993077","https://openalex.org/W2768840867","https://openalex.org/W2768879211","https://openalex.org/W2780351918","https://openalex.org/W2796981088","https://openalex.org/W2883820570","https://openalex.org/W2885656008","https://openalex.org/W2888277922","https://openalex.org/W2888752296","https://openalex.org/W2893763910","https://openalex.org/W2895439318","https://openalex.org/W2952869966"],"related_works":["https://openalex.org/W2970399728","https://openalex.org/W3125969836","https://openalex.org/W3203085311","https://openalex.org/W2144321908","https://openalex.org/W3195981687","https://openalex.org/W2580705004","https://openalex.org/W948739665","https://openalex.org/W2402296773","https://openalex.org/W2961520609","https://openalex.org/W3128091920","https://openalex.org/W2139386916","https://openalex.org/W3035374068","https://openalex.org/W2521020239","https://openalex.org/W2760531487","https://openalex.org/W3139700972","https://openalex.org/W1564726434","https://openalex.org/W2150612176","https://openalex.org/W3108325989","https://openalex.org/W3019764284","https://openalex.org/W3186509740"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"approach":[3,31],"to":[4,16,116,142],"synthesize":[5],"highly":[6],"photorealistic":[7],"images":[8,76,86,122,159],"of":[9,45,57,73,103,131,156],"3D":[10,37,43],"object":[11,38,95,127,145],"models,":[12],"which":[13],"we":[14],"use":[15],"train":[17,144],"a":[18,62,99,117,137],"convolutional":[19],"neural":[20],"network":[21],"for":[22,164],"detecting":[23],"the":[24,74,89,92,120,173],"objects":[25,58],"in":[26,42,61],"real":[27,152],"images.":[28,153],"The":[29],"proposed":[30,90],"has":[32],"three":[33],"key":[34],"ingredients:":[35],"(1)":[36],"models":[39,44,128],"are":[40,123],"rendered":[41],"complete":[46],"scenes":[47],"with":[48,160],"realistic":[49],"materials":[50],"and":[51,59,69,109],"lighting,":[52],"(2)":[53],"plausible":[54],"geometric":[55],"configuration":[56],"cameras":[60],"scene":[63],"is":[64,77,136],"generated":[65],"using":[66],"physics":[67],"simulation,":[68],"(3)":[70],"high":[71],"photorealism":[72],"synthesized":[75,87,124],"achieved":[78],"by":[79,88,125],"physically":[80],"based":[81],"rendering.":[82],"When":[83],"trained":[84],"on":[85,105,111,129,172],"approach,":[91],"Faster":[93],"R-CNN":[94],"detector":[96],"[1]":[97],"achieves":[98],"24%":[100],"absolute":[101],"improvement":[102],"mAP@.75IoU":[104],"Rutgers":[106],"APC":[107],"[2]":[108],"11%":[110],"LineMod-Occluded":[112],"[3]":[113],"datasets,":[114],"compared":[115],"baseline":[118],"where":[119],"training":[121],"rendering":[126],"top":[130],"random":[132],"photographs.":[133],"This":[134],"work":[135],"step":[138],"towards":[139],"being":[140],"able":[141],"effectively":[143],"detectors":[146],"without":[147],"capturing":[148],"or":[149],"annotating":[150],"any":[151],"A":[154],"dataset":[155],"400K":[157],"synthetic":[158],"ground":[161],"truth":[162],"annotations":[163],"various":[165],"computer":[166],"vision":[167],"tasks":[168],"will":[169],"be":[170],"released":[171],"project":[174],"website:":[175],"thodan.github.io/objectsynth.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}