{"id":"https://openalex.org/W7214129484","doi":null,"title":"Optimal transport driven flow matching: an efficient framework for volumetric generation","display_name":"Optimal transport driven flow matching: an efficient framework for volumetric generation","publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7214129484"},"language":"en","primary_location":{"id":"pmh:oai:amslaurea.cib.unibo.it:38635","doi":null,"is_oa":true,"landing_page_url":"https://amslaurea.unibo.it/view/cds/CDS9245/>","pdf_url":"https://amslaurea.unibo.it/id/eprint/38635/1/Optimal%20Transport%20Driven%20Flow%20Matching%20An%20Efficient%20Framework%20for%20Volumetric%20Generation.pdf","source":{"id":"https://openalex.org/S4306400235","display_name":"AMS Degree Thesis (University of Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9360294","host_organization_name":"University of Bologna","host_organization_lineage":["https://openalex.org/I9360294"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Tesi di laurea"},"volume":null,"type":"other","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://amslaurea.unibo.it/id/eprint/38635/1/Optimal%20Transport%20Driven%20Flow%20Matching%20An%20Efficient%20Framework%20for%20Volumetric%20Generation.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152522391","display_name":"Matteo Martelli","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Martelli, Matteo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5152522391"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9818999767303467,"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":0.9818999767303467,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.013500000350177288,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.0006000000284984708,"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/optimal-transport","display_name":"optimal transport","score":0.8140000104904175},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.9940000176429749},{"id":"https://openalex.org/keywords/medical-image-synthesis","display_name":"medical image synthesis","score":0.6809999942779541},{"id":"https://openalex.org/keywords/mode-collapse","display_name":"mode collapse","score":0.6909999847412109},{"id":"https://openalex.org/keywords/latent-diffusion-models","display_name":"latent diffusion models","score":0.7170000076293945},{"id":"https://openalex.org/keywords/anatomical-diversity","display_name":"anatomical diversity","score":0.6790000200271606},{"id":"https://openalex.org/keywords/3d-u-net","display_name":"3D U-Net","score":0.6830000281333923},{"id":"https://openalex.org/keywords/frechet-inception-distance","display_name":"Fr\u00e9chet Inception Distance","score":0.7129999995231628},{"id":"https://openalex.org/keywords/maximum-mean-discrepancy","display_name":"maximum mean discrepancy","score":0.9110000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6401000022888184},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6294999718666077},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4921000003814697},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4350999891757965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42969998717308044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40790000557899475},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3427000045776367},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.26330000162124634}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:amslaurea.cib.unibo.it:38635","doi":null,"is_oa":true,"landing_page_url":"https://amslaurea.unibo.it/view/cds/CDS9245/>","pdf_url":"https://amslaurea.unibo.it/id/eprint/38635/1/Optimal%20Transport%20Driven%20Flow%20Matching%20An%20Efficient%20Framework%20for%20Volumetric%20Generation.pdf","source":{"id":"https://openalex.org/S4306400235","display_name":"AMS Degree Thesis (University of Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9360294","host_organization_name":"University of Bologna","host_organization_lineage":["https://openalex.org/I9360294"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Tesi di laurea"}],"best_oa_location":{"id":"pmh:oai:amslaurea.cib.unibo.it:38635","doi":null,"is_oa":true,"landing_page_url":"https://amslaurea.unibo.it/view/cds/CDS9245/>","pdf_url":"https://amslaurea.unibo.it/id/eprint/38635/1/Optimal%20Transport%20Driven%20Flow%20Matching%20An%20Efficient%20Framework%20for%20Volumetric%20Generation.pdf","source":{"id":"https://openalex.org/S4306400235","display_name":"AMS Degree Thesis (University of Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9360294","host_organization_name":"University of Bologna","host_organization_lineage":["https://openalex.org/I9360294"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Tesi di laurea"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214129484.pdf","grobid_xml":"https://content.openalex.org/works/W7214129484.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2467604901","https://openalex.org/W2895434480","https://openalex.org/W3110257065","https://openalex.org/W4297676498","https://openalex.org/W4303647933","https://openalex.org/W4308610041","https://openalex.org/W4319050105","https://openalex.org/W4415191264"],"related_works":["https://openalex.org/W7214164335","https://openalex.org/W7165405309","https://openalex.org/W7131067769","https://openalex.org/W4415191264","https://openalex.org/W7197033134","https://openalex.org/W7161754085","https://openalex.org/W7215012607","https://openalex.org/W7164820070","https://openalex.org/W4412939881","https://openalex.org/W7141109332"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,60,70,157,180,206],"robust":[3],"machine":[4],"learning":[5],"models":[6,42],"for":[7,75,227],"3D":[8,45,61,116,230],"medical":[9,231],"imaging":[10],"is":[11,201],"severely":[12],"hindered":[13],"by":[14,64],"data":[15,38],"scarcity,":[16],"privacy":[17],"regulations,":[18],"and":[19,30,84,96,126,195],"dataset":[20,108],"heterogeneity.":[21],"While":[22],"generative":[23,68],"artificial":[24],"intelligence,":[25],"particularly":[26],"Latent":[27],"Diffusion":[28],"Models":[29],"Flow":[31,90],"Matching,":[32],"represents":[33],"the":[34,57,66,71,106,146,154,178,181,202],"state-of-the-art":[35],"through":[36],"synthetic":[37],"generation,":[39],"scaling":[40],"these":[41],"to":[43,152],"high-dimensional":[44],"volumes":[46],"remains":[47],"a":[48,81,110],"demanding":[49],"computational":[50],"challenge.":[51],"In":[52],"this":[53,139,218],"thesis,":[54],"we":[55],"address":[56],"architectural":[58,215],"bottlenecks":[59],"volumetric":[62],"generation":[63,232],"optimizing":[65],"latent":[67],"core":[69],"MAISI":[72],"(Medical":[73],"AI":[74],"Synthetic":[76],"Imaging)":[77],"framework.":[78],"We":[79,136],"conduct":[80],"rigorous":[82],"theoretical":[83],"empirical":[85],"comparison":[86],"between":[87],"Independent":[88],"Conditional":[89],"Matching":[91],"(I-CFM),Variance-Preserving":[92],"CFM":[93,100],"(VP-CFM)":[94],",":[95],"Minibatch":[97],"Optimal":[98,169,221],"Transport":[99,170,222],"(OT-CFM).":[101],"Our":[102],"extensive":[103],"evaluation":[104],"on":[105],"CT-RATE":[107],"reveals":[109],"critical":[111],"\"Loss-Fidelity":[112],"Paradox\":":[113],"while":[114],"under-parameterized":[115],"U-Nets":[117],"achieve":[118],"similar":[119],"training":[120],"convergence":[121],"across":[122],"all":[123],"methods,":[124],"I-CFM":[125],"VP-CFM":[127],"suffer":[128],"from":[129],"severe":[130],"macroscopic":[131],"topological":[132],"failures":[133],"during":[134],"inference.":[135],"mathematically":[137],"diagnose":[138],"collapse":[140],"as":[141,223],"\"Mode":[142],"Averaging,\"":[143],"where":[144],"in":[145,233],"network\u2019s":[147],"limited":[148],"capacity":[149],"forces":[150],"it":[151],"predict":[153],"spatial":[155],"mean":[156],"highly":[158],"intersecting,":[159],"conflicting":[160],"target":[161],"trajectories,":[162],"drastically":[163],"reducing":[164],"inter-sample":[165],"diversity.":[166],"By":[167],"enforcing":[168],"coupling,":[171],"OT-CFM":[172,200],"globally":[173],"disentangles":[174],"probability":[175],"paths,":[176],"minimizing":[177],"variance":[179],"regression":[182],"target.":[183],"Quantitative":[184],"metrics,":[185],"including":[186],"Fr\u00e9chet":[187],"Inception":[188],"Distance":[189],"(FID),":[190],"Maximum":[191],"Mean":[192],"Discrepancy":[193],"(MMD),":[194],"Voxel-wise":[196],"Variance,":[197],"confirm":[198],"that":[199],"only":[203],"formulation":[204],"capable":[205],"preserving":[207],"true":[208],"patient-to-patient":[209],"anatomical":[210],"diversity":[211],"without":[212],"requiring":[213],"massive":[214],"scaling.":[216],"Ultimately,":[217],"work":[219],"establishes":[220],"an":[224],"indispensable":[225],"prerequisite":[226],"efficient,":[228],"high-fidelity":[229],"resource-constrained":[234],"settings.":[235]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-24T00:00:00"}