{"id":"https://openalex.org/W7136722490","doi":"https://doi.org/10.3390/jimaging12030132","title":"Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Maps","display_name":"Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Maps","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7136722490","doi":"https://doi.org/10.3390/jimaging12030132","pmid":"https://pubmed.ncbi.nlm.nih.gov/41892934"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging12030132","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12030132","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/jimaging12030132","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111766104","display_name":"E. Caruso","orcid":"https://orcid.org/0009-0004-9693-5755"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Caruso","raw_affiliation_strings":["Department of Engineering, Free University of Bozen-Bolzano, 39100 Bozen-Bolzano, Italy"],"raw_orcid":"https://orcid.org/0009-0004-9693-5755","affiliations":[{"raw_affiliation_string":"Department of Engineering, Free University of Bozen-Bolzano, 39100 Bozen-Bolzano, Italy","institution_ids":["https://openalex.org/I171543936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004954324","display_name":"Francesco Pelosin","orcid":"https://orcid.org/0000-0002-5548-2620"},"institutions":[{"id":"https://openalex.org/I4210128203","display_name":"Krankenhaus Brixen","ror":"https://ror.org/0356gcm38","country_code":"IT","type":"healthcare","lineage":["https://openalex.org/I4210128203"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Pelosin","raw_affiliation_strings":["Covision Lab Scarl, 39042 Brixen-Bressanone, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5548-2620","affiliations":[{"raw_affiliation_string":"Covision Lab Scarl, 39042 Brixen-Bressanone, Italy","institution_ids":["https://openalex.org/I4210128203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039276971","display_name":"Alessandro Simoni","orcid":"https://orcid.org/0000-0003-3095-3294"},"institutions":[{"id":"https://openalex.org/I4210128203","display_name":"Krankenhaus Brixen","ror":"https://ror.org/0356gcm38","country_code":"IT","type":"healthcare","lineage":["https://openalex.org/I4210128203"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Simoni","raw_affiliation_strings":["Covision Lab Scarl, 39042 Brixen-Bressanone, Italy"],"raw_orcid":"https://orcid.org/0000-0003-3095-3294","affiliations":[{"raw_affiliation_string":"Covision Lab Scarl, 39042 Brixen-Bressanone, Italy","institution_ids":["https://openalex.org/I4210128203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057476577","display_name":"Oswald Lanz","orcid":"https://orcid.org/0000-0003-4793-4276"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Oswald Lanz","raw_affiliation_strings":["Department of Engineering, Free University of Bozen-Bolzano, 39100 Bozen-Bolzano, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4793-4276","affiliations":[{"raw_affiliation_string":"Department of Engineering, Free University of Bozen-Bolzano, 39100 Bozen-Bolzano, Italy","institution_ids":["https://openalex.org/I171543936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":17.5325,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98559248,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"12","issue":"3","first_page":"132","last_page":"132"},"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":0.7450000047683716,"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":0.7450000047683716,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0794999971985817,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.025299999862909317,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/segmentation","display_name":"Segmentation","score":0.7753999829292297},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6004999876022339},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.590399980545044},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.578000009059906},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.48660001158714294},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4702000021934509},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4456000030040741},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.42899999022483826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109999895095825},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7753999829292297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6583999991416931},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.590399980545044},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.578000009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.48660001158714294},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4702000021934509},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4172999858856201},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.38280001282691956},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.30640000104904175},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.27730000019073486},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25519999861717224}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/jimaging12030132","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12030132","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:41892934","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41892934","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":null},{"id":"pmh:oai:doaj.org/article:42b308ad6bdc460681ae1478a904c2e8","is_oa":true,"landing_page_url":"https://doaj.org/article/42b308ad6bdc460681ae1478a904c2e8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 12, Iss 3, p 132 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13027772","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13027772/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/jimaging12030132","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12030132","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6249155402183533,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2397830550","https://openalex.org/W2431874326","https://openalex.org/W2905065306","https://openalex.org/W2923486253","https://openalex.org/W2953989358","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2965833116","https://openalex.org/W2983248633","https://openalex.org/W3096831136","https://openalex.org/W3153381206","https://openalex.org/W3161307971","https://openalex.org/W4283641915","https://openalex.org/W4284969353","https://openalex.org/W4312995674","https://openalex.org/W4385800797","https://openalex.org/W4386075742","https://openalex.org/W4386076027","https://openalex.org/W4386076403","https://openalex.org/W4388821383","https://openalex.org/W4390873054","https://openalex.org/W4391919472","https://openalex.org/W4402727378","https://openalex.org/W4402754201","https://openalex.org/W4402916399","https://openalex.org/W4403012098","https://openalex.org/W4409262012","https://openalex.org/W4413556737"],"related_works":[],"abstract_inverted_index":{"Synthetic":[0],"dataset":[1],"generation":[2],"in":[3],"Computer":[4],"Vision,":[5],"particularly":[6],"for":[7,16,40],"industrial":[8,43,125],"applications,":[9],"is":[10,26],"still":[11],"underexplored.":[12],"Industrial":[13],"defect":[14,68,79],"segmentation,":[15],"instance,":[17],"requires":[18],"highly":[19],"accurate":[20],"labels,":[21],"yet":[22],"acquiring":[23],"such":[24],"data":[25],"costly":[27],"and":[28,65,81,96,108,123,130],"time-consuming.":[29],"To":[30],"address":[31],"this":[32],"challenge,":[33],"we":[34],"propose":[35],"a":[36,101],"novel":[37],"diffusion-based":[38,115],"pipeline":[39],"generating":[41],"high-fidelity":[42],"datasets":[44],"with":[45],"minimal":[46],"supervision.":[47],"Our":[48,111],"approach":[49,77],"conditions":[50],"the":[51,91,119],"diffusion":[52],"model":[53],"on":[54,100,106],"enriched":[55],"bounding-box":[56],"representations":[57],"to":[58,71,89],"produce":[59],"precise":[60],"segmentation":[61,103,132],"masks,":[62],"ensuring":[63],"realistic":[64],"accurately":[66],"localized":[67],"synthesis.":[69],"Compared":[70],"existing":[72],"layout-conditioned":[73],"generative":[74],"methods,":[75],"our":[76,94],"improves":[78],"consistency":[80],"spatial":[82],"accuracy.":[83],"We":[84],"introduce":[85],"two":[86],"quantitative":[87],"metrics":[88],"evaluate":[90],"effectiveness":[92],"of":[93],"method":[95],"assess":[97],"its":[98],"impact":[99],"downstream":[102],"task":[104],"trained":[105],"real":[107],"synthetic":[109],"data.":[110],"results":[112],"demonstrate":[113],"that":[114],"synthesis":[116],"can":[117],"bridge":[118],"gap":[120],"between":[121],"artificial":[122],"real-world":[124],"data,":[126],"fostering":[127],"more":[128],"reliable":[129],"cost-efficient":[131],"models.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2026-03-17T00:00:00"}