{"id":"https://openalex.org/W7220662575","doi":"https://doi.org/10.48550/arxiv.2610.04722","title":"NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis","display_name":"NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis","publication_year":2026,"publication_date":"2026-10-03","ids":{"openalex":"https://openalex.org/W7220662575","doi":"https://doi.org/10.48550/arxiv.2610.04722"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.04722","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04722","pdf_url":"https://arxiv.org/pdf/2610.04722","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.04722","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123308422","display_name":"Ramil Khafizov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khafizov, Ramil","raw_affiliation_strings":["Applied AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied AI Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157701236","display_name":"Ilya Statsenko","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Statsenko, Ilya","raw_affiliation_strings":["T-Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T-Tech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050898339","display_name":"Ruslan Rakhimov","orcid":"https://orcid.org/0000-0002-6763-3510","observed_orcids":["https://orcid.org/0000-0002-6763-3510"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rakhimov, Ruslan","raw_affiliation_strings":["T-Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T-Tech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039196567","display_name":"Artem Komarichev","orcid":"https://orcid.org/0000-0003-0047-8402","observed_orcids":["https://orcid.org/0000-0003-0047-8402"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Komarichev, Artem","raw_affiliation_strings":["Applied AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied AI Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076768552","display_name":"Peter Wonka","orcid":"https://orcid.org/0000-0003-0627-9746","observed_orcids":["https://orcid.org/0000-0003-0627-9746"]},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Wonka, Peter","raw_affiliation_strings":["KAUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAUST","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5144031514","display_name":"Evgeny Burnaev","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Burnaev, Evgeny","raw_affiliation_strings":["AXXX","Applied AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AXXX","institution_ids":[]},{"raw_affiliation_string":"Applied AI Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"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":0.548799991607666,"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":0.548799991607666,"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":0.44209998846054077,"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":0.004399999976158142,"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/multi-view-image-synthesis","display_name":"multi-view image synthesis","score":0.8529999852180481},{"id":"https://openalex.org/keywords/camera-geometry","display_name":"camera geometry","score":0.6110000014305115},{"id":"https://openalex.org/keywords/cross-attention","display_name":"cross-attention","score":0.7369999885559082},{"id":"https://openalex.org/keywords/coarse-to-fine-generation","display_name":"coarse-to-fine generation","score":0.7319999933242798},{"id":"https://openalex.org/keywords/3d-content-creation","display_name":"3D content creation","score":0.7540000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705299973487854},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6765000224113464},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.617900013923645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5275999903678894},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.47209998965263367},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47029998898506165},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4496999979019165},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.37770000100135803},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.36739999055862427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.04722","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04722","pdf_url":"https://arxiv.org/pdf/2610.04722","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.04722","doi":"https://doi.org/10.48550/arxiv.2610.04722","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.04722","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.04722","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04722","pdf_url":"https://arxiv.org/pdf/2610.04722","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220662575.pdf","grobid_xml":"https://content.openalex.org/works/W7220662575.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6910694243","https://openalex.org/W7214777386","https://openalex.org/W4379919676","https://openalex.org/W7154855849","https://openalex.org/W4415056089","https://openalex.org/W7162528916","https://openalex.org/W4394625497","https://openalex.org/W4409262188","https://openalex.org/W4391621773","https://openalex.org/W4389501323"],"abstract_inverted_index":{"Sparse-view":[0],"novel":[1],"view":[2],"synthesis":[3,37],"is":[4,165],"a":[5,30,56,166],"central":[6],"problem":[7],"in":[8,74,137],"3D":[9],"content":[10],"creation,":[11],"but":[12],"diffusion-based":[13,135],"approaches":[14],"remain":[15],"limited":[16],"by":[17],"iterative":[18],"denoising,":[19,49],"making":[20],"multi-view":[21,35,175],"generation":[22,79],"expensive":[23],"at":[24,105,185],"inference":[25],"time.":[26],"We":[27],"introduce":[28],"NAMVIS,":[29],"diffusion-free":[31],"framework":[32],"that":[33,161],"reformulates":[34],"image":[36],"as":[38],"geometry-conditioned":[39,162],"next-scale":[40,163],"autoregression.":[41],"Instead":[42],"of":[43,59],"generating":[44],"target":[45,72,95],"views":[46,73],"through":[47,55],"repeated":[48],"NAMVIS":[50,108,133],"predicts":[51],"discrete":[52],"visual":[53],"tokens":[54,66],"small":[57],"number":[58],"coarse-to-fine":[60],"scale":[61,69],"steps,":[62],"while":[63,124,142],"sampling":[64],"all":[65],"within":[67],"each":[68],"and":[70,94,102,131,140,168,181],"across":[71],"parallel.":[75],"To":[76],"anchor":[77],"this":[78],"process":[80],"to":[81,120,171],"explicit":[82],"camera":[83,96],"geometry,":[84],"we":[85],"propose":[86],"Multi-scale":[87],"Projective":[88],"Pose":[89],"Encoding,":[90],"which":[91],"injects":[92],"source":[93],"transformations":[97],"into":[98],"both":[99],"target-view":[100,126],"self-attention":[101],"source-to-target":[103],"cross-attention":[104],"every":[106],"resolution.":[107],"further":[109],"combines":[110],"global":[111],"conditioning":[112],"with":[113],"dense":[114],"geometry-aware":[115],"cross-attention,":[116],"enabling":[117],"the":[118,149,154],"model":[119],"preserve":[121],"source-view":[122],"appearance":[123],"maintaining":[125],"consistency.":[127],"Across":[128],"Objaverse,":[129],"GSO,":[130],"OmniObject3D,":[132],"outperforms":[134],"baselines":[136,152],"PSNR,":[138],"SSIM,":[139],"LPIPS,":[141],"running":[143],"over":[144],"3":[145],"times":[146],"faster":[147],"than":[148],"evaluated":[150],"diffusion":[151,172],"under":[153],"same":[155],"evaluation":[156],"setting.":[157],"These":[158],"results":[159],"suggest":[160],"autoregression":[164],"promising":[167],"efficient":[169],"alternative":[170],"for":[173],"sparse-view":[174],"synthesis.":[176],"Additional":[177],"qualitative":[178],"results,":[179],"videos,":[180],"resources":[182],"are":[183],"available":[184],"https://corl-team.github.io/namvis/":[186]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-07T00:00:00"}