{"id":"https://openalex.org/W4402979654","doi":"https://doi.org/10.1109/icme57554.2024.10687518","title":"PGDM: Multimodal Panoramic Image Generation with Diffusion Models","display_name":"PGDM: Multimodal Panoramic Image Generation with Diffusion Models","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979654","doi":"https://doi.org/10.1109/icme57554.2024.10687518"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001067375","display_name":"Depei Liu","orcid":"https://orcid.org/0009-0007-2398-3096"},"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":"Depei Liu","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074050730","display_name":"Hongjie Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I177955009","display_name":"China University of Political Science and Law","ror":"https://ror.org/00e49gy82","country_code":"CN","type":"education","lineage":["https://openalex.org/I177955009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjie Fan","raw_affiliation_strings":["China University of Political Science and Law,The Department of Science and Technology Teaching,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Political Science and Law,The Department of Science and Technology Teaching,Beijing,China","institution_ids":["https://openalex.org/I177955009"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023014733","display_name":"Junfei Liu","orcid":null},"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":"Junfei Liu","raw_affiliation_strings":["Peking University,National Engineering Research Center for Software Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,National Engineering Research Center for Software Engineering,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5259,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69805389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9896000027656555,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9896000027656555,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9868999719619751,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6613397598266602},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6120662689208984},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5813355445861816},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5579501986503601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4939013123512268},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05736356973648071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6613397598266602},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6120662689208984},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5813355445861816},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5579501986503601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4939013123512268},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05736356973648071},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2964339842","https://openalex.org/W3096831136","https://openalex.org/W3109585842","https://openalex.org/W3174807077","https://openalex.org/W3180355996","https://openalex.org/W4311802212","https://openalex.org/W4312933868","https://openalex.org/W4386076607","https://openalex.org/W4390871736","https://openalex.org/W4390874211"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Panoramic":[0],"image":[1],"generation":[2,39],"enhances":[3],"visual":[4],"representation":[5],"and":[6,22,102],"facilitates":[7,36],"immersive":[8],"experiences":[9],"across":[10,104],"various":[11],"fields.":[12],"However,":[13],"Existing":[14],"models":[15],"readily":[16],"gives":[17],"rise":[18],"to":[19,47,80],"error":[20],"accumulation":[21],"loop":[23],"closure.":[24],"To":[25],"overcome":[26],"these":[27],"limitations,":[28],"we":[29,67],"introduce":[30],"PGDM,":[31],"a":[32,57],"diffusion-based":[33],"framework":[34],"that":[35,92],"the":[37,53,69,82,95],"concurrent":[38],"of":[40,84],"visually":[41,62],"cohesive":[42],"panoramic":[43,85],"images.":[44,86,107],"In":[45],"order":[46],"achieve":[48],"modality":[49],"alignment,":[50],"PGDM":[51,93],"adopts":[52],"vision-language":[54],"model":[55],"as":[56],"Multimodal":[58],"Module":[59],"for":[60],"extracting":[61],"representative":[63],"text-aligned":[64],"features.":[65],"Additionally,":[66],"design":[68],"Multi-View":[70],"Attention":[71],"with":[72],"Camera":[73],"Pose":[74],"mechanism":[75],"between":[76],"each":[77],"UNet":[78],"layer":[79],"enhance":[81],"coherency":[83],"Our":[87],"extensive":[88],"experimental":[89],"results":[90],"demonstrate":[91],"achieves":[94],"state-of-the-art":[96],"performance":[97],"while":[98],"simultaneously":[99],"maintaining":[100],"diversity":[101],"consistency":[103],"multiple":[105],"view":[106]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
