{"id":"https://openalex.org/W4415311892","doi":"https://doi.org/10.48550/arxiv.2506.14471","title":"Dense360: Dense Understanding from Omnidirectional Panoramas","display_name":"Dense360: Dense Understanding from Omnidirectional Panoramas","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4415311892","doi":"https://doi.org/10.48550/arxiv.2506.14471"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.14471","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14471","pdf_url":"https://arxiv.org/pdf/2506.14471","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.14471","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104162474","display_name":"Yikang Zhou","orcid":"https://orcid.org/0000-0001-8326-5925","observed_orcids":["https://orcid.org/0000-0001-8326-5925"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Yikang","raw_affiliation_strings":["Insta360","Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insta360","institution_ids":[]},{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038618198","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-4053-9209","observed_orcids":["https://orcid.org/0000-0002-4053-9209"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Tao","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Dizhe","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Dizhe","raw_affiliation_strings":["Insta360"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insta360","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031588692","display_name":"Shunping Ji","orcid":"https://orcid.org/0000-0002-3088-1481","observed_orcids":["https://orcid.org/0000-0002-3088-1481"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji, Shunping","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089900108","display_name":"Xiangtai Li","orcid":"https://orcid.org/0000-0002-0550-8247","observed_orcids":["https://orcid.org/0000-0002-0550-8247"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Xiangtai","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100665481","display_name":"Qi Lu","orcid":"https://orcid.org/0000-0003-1683-888X","observed_orcids":["https://orcid.org/0000-0003-1683-888X"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi, Lu","raw_affiliation_strings":["Insta360","Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insta360","institution_ids":[]},{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.8859999775886536},{"id":"https://openalex.org/keywords/equirectangular-projection","display_name":"equirectangular projection","score":0.9120000004768372},{"id":"https://openalex.org/keywords/entity-grounding","display_name":"entity grounding","score":0.6899999976158142},{"id":"https://openalex.org/keywords/referring-expressions","display_name":"referring expressions","score":0.7409999966621399},{"id":"https://openalex.org/keywords/positional-encoding","display_name":"positional encoding","score":0.7310000061988831},{"id":"https://openalex.org/keywords/vision-language-understanding","display_name":"visual language understanding","score":0.4580000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922999858856201},{"id":"https://openalex.org/C24027999","wikidata":"https://www.wikidata.org/wiki/Q2176348","display_name":"Omnidirectional antenna","level":3,"score":0.6841999888420105},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6660000085830688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6234999895095825},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4113999903202057},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C3018151503","wikidata":"https://www.wikidata.org/wiki/Q608487","display_name":"Hand position","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C2777953668","wikidata":"https://www.wikidata.org/wiki/Q684116","display_name":"Omnidirectional camera","level":4,"score":0.2685000002384186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.14471","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14471","pdf_url":"https://arxiv.org/pdf/2506.14471","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.2506.14471","doi":"https://doi.org/10.48550/arxiv.2506.14471","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.14471","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.14471","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14471","pdf_url":"https://arxiv.org/pdf/2506.14471","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415311892.pdf","grobid_xml":"https://content.openalex.org/works/W4415311892.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2273396394","https://openalex.org/W3094502228","https://openalex.org/W3168867926","https://openalex.org/W4366330503","https://openalex.org/W4376312115","https://openalex.org/W4387294588","https://openalex.org/W4392538638","https://openalex.org/W4401307635","https://openalex.org/W4402727764","https://openalex.org/W4403370767","https://openalex.org/W4403576244","https://openalex.org/W4403853618","https://openalex.org/W4404569270","https://openalex.org/W4405172832","https://openalex.org/W4405655184","https://openalex.org/W4406231658","https://openalex.org/W4407310662","https://openalex.org/W4407359580","https://openalex.org/W4407794264","https://openalex.org/W4407806605","https://openalex.org/W4409367028","https://openalex.org/W4413948760","https://openalex.org/W4414634784","https://openalex.org/W4415161148","https://openalex.org/W4415306945","https://openalex.org/W4415537998","https://openalex.org/W4415797672","https://openalex.org/W4416014077","https://openalex.org/W4416119099","https://openalex.org/W4416749631","https://openalex.org/W4417098228","https://openalex.org/W4417227396","https://openalex.org/W6948372171","https://openalex.org/W6948439803","https://openalex.org/W6967068517","https://openalex.org/W7160122410","https://openalex.org/W7172399305"],"related_works":["https://openalex.org/W4415022865","https://openalex.org/W7134920146","https://openalex.org/W7166739581","https://openalex.org/W4417300135","https://openalex.org/W4416707831","https://openalex.org/W7161174261","https://openalex.org/W7090694215","https://openalex.org/W7128096872","https://openalex.org/W7129232221","https://openalex.org/W7166563770"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"require":[5],"comprehensive":[6,54,157],"visual":[7,29],"inputs":[8,30],"to":[9,81],"achieve":[10],"dense":[11,40,67,161],"understanding":[12,23,41,163],"of":[13,56,101,115],"the":[14,36,99,113,144],"physical":[15],"world.":[16],"While":[17],"existing":[18],"MLLMs":[19,149],"demonstrate":[20],"impressive":[21],"world":[22],"capabilities":[24],"through":[25,94,128],"limited":[26],"field-of-view":[27],"(FOV)":[28],"(e.g.,":[31],"70":[32],"degree),":[33],"we":[34,141],"take":[35],"first":[37,46,145],"step":[38],"toward":[39],"from":[42],"omnidirectional":[43,49,151],"panoramas.":[44],"We":[45,124],"introduce":[47,142],"an":[48],"panoramas":[50,64,84],"dataset":[51,61],"featuring":[52],"a":[53,130,156],"suite":[55],"reliability-scored":[57],"annotations.":[58],"Specifically,":[59],"our":[60],"contains":[62],"160K":[63],"with":[65],"5M":[66],"entity-level":[68],"captions,":[69],"1M":[70],"unique":[71],"referring":[72],"expressions,":[73],"and":[74,90,117,153],"100K":[75],"entity-grounded":[76],"panoramic":[77,137,165],"scene":[78,92],"descriptions.":[79],"Compared":[80],"multi-view":[82],"alternatives,":[83],"can":[85],"provide":[86],"more":[87],"complete,":[88],"compact,":[89],"continuous":[91],"representations":[93],"equirectangular":[95],"projections":[96],"(ERP).":[97],"However,":[98],"use":[100],"ERP":[102],"introduces":[103],"two":[104],"key":[105],"challenges":[106,127],"for":[107,136,147,159],"MLLMs:":[108],"i)":[109],"spatial":[110],"continuity":[111],"along":[112],"circle":[114],"latitude,":[116],"ii)":[118],"latitude-dependent":[119],"variation":[120],"in":[121,164],"information":[122],"density.":[123],"address":[125],"these":[126],"ERP-RoPE,":[129],"position":[131],"encoding":[132],"scheme":[133],"specifically":[134],"designed":[135],"ERP.":[138],"In":[139],"addition,":[140],"Dense360-Bench,":[143],"benchmark":[146],"evaluating":[148],"on":[150],"captioning":[152],"grounding,":[154],"establishing":[155],"framework":[158],"advancing":[160],"visual-language":[162],"settings.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-18T00:00:00"}