{"id":"https://openalex.org/W4404986904","doi":"https://doi.org/10.1109/iccv51701.2025.01423","title":"PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs","display_name":"PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404986904","doi":"https://doi.org/10.1109/iccv51701.2025.01423"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.15867","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001633121","display_name":"Teng Zhou","orcid":"https://orcid.org/0000-0003-1941-5348"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Zhou","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419414","display_name":"Xiaoyu Zhang","orcid":"https://orcid.org/0000-0002-5933-1977"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028964","display_name":"Yongchuan Tang","orcid":"https://orcid.org/0000-0001-9344-0491"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongchuan Tang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I168879160"],"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.8169999718666077,"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/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.8169999718666077,"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":0.8052999973297119,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.7907000184059143,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/security-token","display_name":"Security token","score":0.8365867733955383},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6000535488128662},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3671191930770874}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8365867733955383},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6000535488128662},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3671191930770874}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.15867","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.15867","pdf_url":"https://arxiv.org/pdf/2411.15867","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.15867","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.15867","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":"pmh:oai:arXiv.org:2411.15867","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.15867","pdf_url":"https://arxiv.org/pdf/2411.15867","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700"],"abstract_inverted_index":{"Panoramic":[0],"Image":[1],"Generation":[2],"(PIG)":[3],"aims":[4],"to":[5,33,55,72,78,112],"create":[6],"coherent":[7,95],"images":[8],"of":[9,117],"arbitrary":[10],"lengths.":[11],"Most":[12],"existing":[13,65,118],"methods":[14,152],"fall":[15],"in":[16,124,139],"the":[17,76,99,114,132],"joint":[18],"diffusion":[19],"paradigm,":[20],"but":[21],"their":[22,31],"complex":[23],"and":[24,94,127,143,160],"heuristic":[25],"crop":[26],"connection":[27],"designs":[28],"often":[29],"limit":[30],"ability":[32],"achieve":[34],"multilevel":[35],"coherence.":[36],"By":[37],"deconstructing":[38],"this":[39,83],"challenge":[40],"into":[41],"its":[42],"core":[43],"components,":[44],"we":[45,85,167],"find":[46],"it":[47],"naturally":[48],"aligns":[49],"with":[50,98,172],"next-token":[51],"prediction,":[52],"leading":[53],"us":[54],"adopt":[56],"an":[57],"autoregressive":[58,100],"(AR)":[59],"paradigm":[60],"for":[61,183],"PIG":[62,133,151,184],"modeling.":[63],"However,":[64],"visual":[66],"AR":[67],"(VAR)":[68],"models":[69],"are":[70],"limited":[71],"fixed-size":[73],"generation,":[74],"lacking":[75],"capability":[77],"produce":[79],"panoramic":[80],"images.":[81],"In":[82],"paper,":[84],"propose":[86],"PanoLlama,":[87],"a":[88,105,170,179],"novel":[89],"framework":[90],"that":[91,108],"achieves":[92],"endless":[93],"panorama":[96],"generation":[97],"paradigm.":[101],"Our":[102],"approach":[103],"develops":[104],"training-free":[106],"strategy":[107],"utilizes":[109],"token":[110],"redirection":[111],"overcome":[113],"size":[115],"limitations":[116],"VAR":[119],"models,":[120],"enabling":[121],"next-crop":[122],"prediction":[123],"both":[125],"horizontal":[126],"vertical":[128],"directions.":[129],"This":[130],"refreshes":[131],"pipeline":[134],"while":[135],"achieving":[136],"SOTA":[137],"performance":[138],"coherence":[140],"(47.50%),":[141],"fidelity(28.16%),":[142],"aesthetics":[144],"(15%).":[145],"Additionally,":[146],"PanoLlama":[147],"supports":[148],"applications":[149],"other":[150],"cannot":[153],"achieve,":[154],"including":[155],"mask-free":[156],"layout":[157],"control,":[158],"multi-scale":[159],"multi-guidance":[161],"synthesis.":[162],"To":[163],"facilitate":[164],"standardized":[165],"evaluation,":[166],"also":[168],"establish":[169],"dataset":[171],"1,000":[173],"prompts":[174],"spanning":[175],"100+":[176],"themes,":[177],"providing":[178],"new":[180],"testing":[181],"benchmark":[182],"research.":[185],"The":[186],"code":[187],"is":[188],"available":[189],"at":[190],"https://github.com/0606zt/PanoLlama.":[191]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}