{"id":"https://openalex.org/W4416047844","doi":"https://doi.org/10.1109/iccv51701.2025.01537","title":"What Makes for Text to 360-Degree Panorama Generation with Stable Diffusion?","display_name":"What Makes for Text to 360-Degree Panorama Generation with Stable Diffusion?","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416047844","doi":"https://doi.org/10.1109/iccv51701.2025.01537"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01537","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/2505.22129","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086057132","display_name":"Jinhong Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jinhong Ni","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chang-Bin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chang-Bin Zhang","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102028427","display_name":"Qiang Zhang","orcid":"https://orcid.org/0000-0003-0409-5871"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Zhang","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083051735","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0003-4242-2677"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":"1","last_page":"10"},"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":0.4271000027656555,"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":0.4271000027656555,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.290800005197525,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0544000007212162,"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/panorama","display_name":"Panorama","score":0.930400013923645},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6599000096321106},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5964000225067139},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5288000106811523},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4120999872684479},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3833000063896179},{"id":"https://openalex.org/keywords/mirroring","display_name":"Mirroring","score":0.3788999915122986},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.37560001015663147}],"concepts":[{"id":"https://openalex.org/C2780580889","wikidata":"https://www.wikidata.org/wiki/Q41363","display_name":"Panorama","level":2,"score":0.930400013923645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734499990940094},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6599000096321106},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5964000225067139},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4122999906539917},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.37560001015663147},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32510000467300415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2531000077724457}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01537","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:2505.22129","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.22129","pdf_url":"https://arxiv.org/pdf/2505.22129","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.22129","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.22129","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":"pmh:oai:arXiv.org:2505.22129","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.22129","pdf_url":"https://arxiv.org/pdf/2505.22129","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416047844.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"prosperity":[1],"of":[2,25,172],"text-to-image":[3],"diffusion":[4,33,91],"models,":[5],"e.g.":[6],"Stable":[7],"Diffusion,":[8],"has":[9,21],"stimulated":[10],"research":[11],"to":[12,15,35,83,127,143,196],"adapt":[13],"them":[14],"360-degree":[16],"panorama":[17,128,155,205],"generation.":[18,156],"Prior":[19],"work":[20],"demonstrated":[22],"the":[23,40,52,64,85,89,96,99,105,118,132,144,170],"feasibility":[24],"using":[26],"conventional":[27],"low-rank":[28],"adaptation":[29,78],"techniques":[30],"on":[31,72],"pre-trained":[32,90,141],"models":[34],"generate":[36],"panoramic":[37,47,73,119,145],"images.":[38],"However,":[39],"substantial":[41],"domain":[42],"gap":[43],"between":[44,117],"perspective":[45,121],"and":[46,61,75,101,120,130,134,192],"images":[48],"raises":[49],"questions":[50],"about":[51],"underlying":[53],"mechanisms":[54],"enabling":[55],"this":[56],"empirical":[57],"success.":[58],"We":[59,157],"hypothesize":[60],"examine":[62],"that":[63,113],"trainable":[65],"counterparts":[66],"exhibit":[67],"distinct":[68],"behaviors":[69],"when":[70],"fine-tuned":[71],"data,":[74],"such":[76],"an":[77,174],"conceals":[79],"some":[80],"intrinsic":[81],"mechanism":[82],"leverage":[84],"prior":[86,197],"knowledge":[87,142],"within":[88],"models.":[92],"Our":[93],"analysis":[94],"reveals":[95],"following:":[97],"1)":[98],"query":[100],"key":[102],"matrices":[103,137],"in":[104,139],"attention":[106],"modules":[107],"are":[108,124],"responsible":[109],"for":[110,154,177,203],"common":[111],"information":[112],"can":[114],"be":[115,213],"shared":[116],"domains,":[122],"thus":[123],"less":[125],"relevant":[126],"generation;":[129],"2)":[131],"value":[133],"output":[135],"weight":[136],"specialize":[138],"adapting":[140],"domain,":[146],"playing":[147],"a":[148,164],"more":[149],"critical":[150],"role":[151],"during":[152],"fine-tuning":[153],"empirically":[158],"verify":[159],"these":[160],"insights":[161],"by":[162],"introducing":[163],"simple":[165],"framework":[166],"called":[167],"UniPano,":[168],"with":[169,207],"objective":[171],"establishing":[173],"elegant":[175],"baseline":[176],"future":[178],"research.":[179],"UniPano":[180],"not":[181],"only":[182],"outperforms":[183],"existing":[184],"methods":[185],"but":[186],"also":[187],"significantly":[188],"reduces":[189],"memory":[190],"usage":[191],"training":[193],"time":[194],"compared":[195],"dual-branch":[198],"approaches,":[199],"making":[200],"it":[201],"scalable":[202],"end-to-end":[204],"generation":[206],"higher":[208],"resolution.":[209],"The":[210],"code":[211],"will":[212],"released.":[214]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}