{"id":"https://openalex.org/W7161255291","doi":"https://doi.org/10.48550/arxiv.2605.14315","title":"TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention","display_name":"TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161255291","doi":"https://doi.org/10.48550/arxiv.2605.14315"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.14315","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14315","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.14315","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136226068","display_name":"David Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082901351","display_name":"Guile Wu","orcid":"https://orcid.org/0000-0001-7319-473X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Guile","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057694255","display_name":"Chengjie Huang","orcid":"https://orcid.org/0009-0003-1025-7774"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Chengjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136253615","display_name":"Bingbing Liu","orcid":"https://orcid.org/0000-0003-4209-006X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Bingbing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136234010","display_name":"Dongfeng Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Dongfeng","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/T10531","display_name":"Advanced Vision and Imaging","score":0.4296000003814697,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.4296000003814697,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.36390000581741333,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.09860000014305115,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/scalability","display_name":"Scalability","score":0.5199000239372253},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.41920000314712524},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.40790000557899475},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3952000141143799},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.38040000200271606},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.3528999984264374},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.3418999910354614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6876999735832214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5320000052452087},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5117999911308289},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.38040000200271606},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C70958404","wikidata":"https://www.wikidata.org/wiki/Q7512728","display_name":"Signal reconstruction","level":4,"score":0.31299999356269836},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C2779898584","wikidata":"https://www.wikidata.org/wiki/Q7820109","display_name":"Reconstruction algorithm","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2632000148296356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.14315","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14315","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.14315","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14315","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4125337302684784,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"feed-forward":[1],"3D":[2,108,190],"reconstruction":[3,22,38,191,199,203],"methods,":[4],"such":[5],"as":[6],"visual":[7,52,98],"geometry":[8,53,99,160],"transformers,":[9],"have":[10,55],"substantially":[11],"advanced":[12],"the":[13,61,144],"traditional":[14],"per-scene":[15],"optimization":[16],"paradigm":[17],"by":[18,123],"enabling":[19],"effective":[20],"multi-view":[21,107,198],"in":[23],"a":[24,35,91],"single":[25],"forward":[26],"pass.":[27],"However,":[28],"most":[29],"existing":[30],"methods":[31],"struggle":[32],"to":[33,72,77,82,127,136],"achieve":[34],"balance":[36],"between":[37],"quality":[39,204],"and":[40,47,67,69,133,178],"computational":[41],"efficiency,":[42],"which":[43],"limits":[44],"their":[45],"scalability":[46],"efficiency.":[48],"Although":[49],"some":[50],"efficient":[51,97],"transformers":[54],"recently":[56],"emerged,":[57],"they":[58],"typically":[59],"use":[60],"same":[62],"sparsity":[63,125,156],"ratio":[64],"across":[65,131,167],"layers":[66,170],"frames":[68,132],"lack":[70],"mechanisms":[71],"adaptively":[73,150],"learn":[74],"representative":[75,152],"tokens":[76,153,172],"capture":[78,128],"global":[79,120,129,147,159,179],"relationships,":[80],"leading":[81],"suboptimal":[83],"performance.":[84],"In":[85,143],"this":[86],"work,":[87],"we":[88],"propose":[89],"TurboVGGT,":[90],"novel":[92],"approach":[93],"that":[94,163,194],"employs":[95,112],"an":[96,113],"transformer":[100],"with":[101,117,154,206],"adaptive":[102,118,124,145],"alternating":[103],"attention":[104,121,135,169],"for":[105,158],"fast":[106,197],"reconstruction.":[109],"Specifically,":[110],"TurboVGGT":[111,149,195],"end-to-end":[114],"trainable":[115],"framework":[116],"sparse":[119,146],"guided":[122],"selection":[126],"relationships":[130],"frame":[134],"aggregate":[137],"local":[138],"details":[139],"within":[140],"each":[141],"frame.":[142],"attention,":[148],"learns":[151],"varying":[155],"levels":[157,175],"modeling,":[161],"considering":[162],"token":[164],"importance":[165],"varies":[166],"frames,":[168],"operate":[171],"at":[173],"different":[174],"of":[176],"abstraction,":[177],"dependencies":[180],"rely":[181],"on":[182,188],"structurally":[183],"informative":[184],"regions.":[185],"Extensive":[186],"experiments":[187],"multiple":[189],"benchmarks":[192],"demonstrate":[193],"achieves":[196],"while":[200],"maintaining":[201],"competitive":[202],"compared":[205],"state-of-the-art":[207],"methods.":[208],"Project":[209],"page:":[210],"https://turbovggt.github.io/.":[211]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-16T00:00:00"}