{"id":"https://openalex.org/W7165130834","doi":"https://doi.org/10.48550/arxiv.2606.19019","title":"FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity","display_name":"FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity","publication_year":2026,"publication_date":"2026-06-17","ids":{"openalex":"https://openalex.org/W7165130834","doi":"https://doi.org/10.48550/arxiv.2606.19019"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.19019","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19019","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.19019","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064085801","display_name":"Yuchen Rao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rao, Yuchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070006320","display_name":"Xuqian Ren","orcid":"https://orcid.org/0000-0002-3811-0235"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Xuqian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051467266","display_name":"Yinyu Nie","orcid":"https://orcid.org/0000-0001-7023-6797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Yinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054501788","display_name":"Sayan Sarkar","orcid":"https://orcid.org/0000-0002-6074-0057"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sarkar, Sayan Deb","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138942976","display_name":"Biao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Biao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070382607","display_name":"Vincent Lepetit","orcid":"https://orcid.org/0000-0001-9985-4433"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lepetit, Vincent","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068079834","display_name":"Friedrich Fraundorfer","orcid":"https://orcid.org/0000-0002-5805-8892"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fraundorfer, Friedrich","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.49000000953674316,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.49000000953674316,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.42730000615119934,"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/T11448","display_name":"Face recognition and analysis","score":0.033900000154972076,"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/prior-probability","display_name":"Prior probability","score":0.7713000178337097},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6396999955177307},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5742999911308289},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5519999861717224},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4683000147342682},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.46650001406669617},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43230000138282776}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7713000178337097},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6044999957084656},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5742999911308289},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5029000043869019},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4683000147342682},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.311599999666214},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C23131810","wikidata":"https://www.wikidata.org/wiki/Q818574","display_name":"Observational study","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.19019","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19019","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.19019","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19019","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recovering":[0],"complete":[1],"3D":[2,16,56,84],"representations":[3],"of":[4,46,107,114],"objects":[5],"from":[6,34],"few":[7],"casual":[8],"image":[9],"captures":[10],"remains":[11],"a":[12,44,79,87,95,108,130],"significant":[13],"challenge.":[14],"Recent":[15],"generative":[17,119,141,179],"models,":[18],"particularly":[19],"those":[20],"based":[21],"on":[22,63,148],"Flow-Matching":[23],"(FM),":[24],"can":[25],"synthesize":[26],"high-quality":[27],"textured":[28],"assets;":[29],"however,":[30],"they":[31],"often":[32,158],"suffer":[33],"''synthetic":[35],"bias''":[36],"where":[37],"learned":[38,118],"priors":[39,120],"override":[40],"observational":[41,165],"evidence,":[42],"alongside":[43],"lack":[45],"alignment":[47],"with":[48,125],"the":[49,101,112,137],"observed":[50],"instance.":[51],"Conversely,":[52],"optimization-based":[53,182],"methods":[54,157],"like":[55],"Gaussian":[57],"Splatting":[58],"(3DGS)":[59],"provide":[60],"high":[61],"fidelity":[62],"visible":[64],"surfaces":[65],"but":[66],"fail":[67],"to":[68,99,160],"reason":[69],"about":[70],"unobserved":[71],"geometry.":[72],"In":[73,172],"this":[74],"paper,":[75],"we":[76],"present":[77],"FlowObject,":[78],"framework":[80],"that":[81,154],"reformulates":[82],"sparse-view":[83],"reconstruction":[85],"as":[86],"training-free,":[88],"guided":[89],"inverse":[90],"problem.":[91],"Our":[92],"approach":[93],"applies":[94],"dual-space":[96],"guidance":[97],"strategy":[98],"steer":[100],"Ordinary":[102],"Differential":[103],"Equation":[104],"(ODE)":[105],"trajectory":[106],"flow-matching":[109],"model,":[110],"enabling":[111],"completion":[113],"unseen":[115],"regions":[116],"through":[117],"while":[121],"enforcing":[122],"strict":[123],"consistency":[124,166],"real-world":[126,151],"observations.":[127],"By":[128],"integrating":[129],"3DGS":[131],"refinement":[132],"stage,":[133],"FlowObject":[134],"further":[135],"bridges":[136],"gap":[138],"between":[139],"''synthetic-looking''":[140],"outputs":[142],"and":[143,150,164,181,188],"photorealistic":[144],"reconstructions.":[145],"Comprehensive":[146],"benchmarks":[147],"synthetic":[149],"datasets":[152],"demonstrate":[153],"current":[155],"state-of-the-art":[156,178],"struggle":[159],"achieve":[161],"geometric":[162,186],"completeness":[163,187],"simultaneously,":[167],"especially":[168],"under":[169],"severe":[170],"occlusions.":[171],"contrast,":[173],"our":[174],"method":[175],"significantly":[176],"outperforms":[177],"models":[180],"frameworks":[183],"in":[184],"both":[185],"view-dependent":[189],"appearance":[190],"fidelity.":[191]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-19T00:00:00"}