{"id":"https://openalex.org/W7133556641","doi":"https://doi.org/10.48550/arxiv.2603.02351","title":"MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry","display_name":"MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133556641","doi":"https://doi.org/10.48550/arxiv.2603.02351"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.02351","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02351","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.02351","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036297582","display_name":"Leo K. Cheng","orcid":"https://orcid.org/0000-0003-2426-8987"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cheng, Leo Kaixuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128097647","display_name":"Abdus Shaikh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaikh, Abdus","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038948167","display_name":"Ruofan Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Ruofan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128081596","display_name":"Zhijie Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zhijie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120717637","display_name":"Yushi Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Yushi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5080873211","display_name":"Nandita Vijaykumar","orcid":"https://orcid.org/0000-0003-3315-9336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vijaykumar, Nandita","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036297582"],"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":0.7182999849319458,"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":0.7182999849319458,"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":0.049800001084804535,"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"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.0333000011742115,"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/bundle","display_name":"Bundle","score":0.4668999910354614},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.45680001378059387},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44029998779296875},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3573000133037567},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.3361000120639801},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.328900009393692},{"id":"https://openalex.org/keywords/bundle-adjustment","display_name":"Bundle adjustment","score":0.3165000081062317},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.30869999527931213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6929000020027161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.630299985408783},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5551000237464905},{"id":"https://openalex.org/C2778134712","wikidata":"https://www.wikidata.org/wiki/Q1047307","display_name":"Bundle","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3330000042915344},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C179458375","wikidata":"https://www.wikidata.org/wiki/Q1020763","display_name":"Bundle adjustment","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C29123130","wikidata":"https://www.wikidata.org/wiki/Q874709","display_name":"Computational geometry","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25220000743865967},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C32990609","wikidata":"https://www.wikidata.org/wiki/Q306542","display_name":"Transformation geometry","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.02351","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02351","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":"doi:10.48550/arxiv.2603.02351","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02351","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.5556526184082031}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2],"neural":[3,115],"visual":[4],"geometry,":[5],"including":[6,121],"transformer-based":[7],"models":[8,56],"such":[9],"as":[10],"VGGT":[11],"and":[12,68,94,109,127,137],"Pi3,":[13],"have":[14],"achieved":[15],"impressive":[16],"accuracy":[17],"on":[18,25],"3D":[19,103],"reconstruction":[20,133,141],"tasks.":[21],"However,":[22],"their":[23,61],"reliance":[24],"full":[26],"attention":[27],"makes":[28],"them":[29,37],"fundamentally":[30],"limited":[31],"by":[32],"GPU":[33],"memory":[34,63,135,146],"capacity,":[35],"preventing":[36],"from":[38],"scaling":[39],"to":[40,57],"large,":[41],"unordered":[42,70],"image":[43],"collections.":[44],"We":[45],"introduce":[46],"MERG3R,":[47],"a":[48,100],"training-free":[49],"divide-and-conquer":[50],"framework":[51,106],"that":[52,77],"enables":[53],"geometric":[54],"foundation":[55],"operate":[58],"far":[59],"beyond":[60],"native":[62],"limits.":[64,148],"MERG3R":[65,130],"first":[66],"reorders":[67],"partitions":[69],"images":[71],"into":[72],"overlapping,":[73],"geometrically":[74],"diverse":[75],"subsets":[76],"can":[78,110],"be":[79,111],"reconstructed":[80],"independently.":[81],"It":[82],"then":[83],"merges":[84],"the":[85,143],"resulting":[86],"local":[87],"reconstructions":[88],"through":[89],"an":[90],"efficient":[91],"global":[92],"alignment":[93],"confidence-weighted":[95],"bundle":[96],"adjustment":[97],"procedure,":[98],"producing":[99],"globally":[101],"consistent":[102],"model.":[104],"Our":[105],"is":[107],"model-agnostic":[108],"paired":[112],"with":[113],"existing":[114],"geometry":[116],"models.":[117],"Across":[118],"large-scale":[119],"datasets,":[120],"7-Scenes,":[122],"NRGBD,":[123],"Tanks":[124],"&":[125],"Temples,":[126],"Cambridge":[128],"Landmarks,":[129],"consistently":[131],"improves":[132],"accuracy,":[134],"efficiency,":[136],"scalability,":[138],"enabling":[139],"high-quality":[140],"when":[142],"dataset":[144],"exceeds":[145],"capacity":[147]},"counts_by_year":[],"updated_date":"2026-03-05T07:36:02.291473","created_date":"2026-03-05T00:00:00"}