{"id":"https://openalex.org/W4409156941","doi":"https://doi.org/10.1109/ieeeconf60004.2024.10942735","title":"Generative Multiplane Image (GMPI): Text to Volumetric Representation","display_name":"Generative Multiplane Image (GMPI): Text to Volumetric Representation","publication_year":2024,"publication_date":"2024-10-27","ids":{"openalex":"https://openalex.org/W4409156941","doi":"https://doi.org/10.1109/ieeeconf60004.2024.10942735"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf60004.2024.10942735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf60004.2024.10942735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"article","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/A5055020146","display_name":"Dewei Hu","orcid":"https://orcid.org/0000-0001-7203-4136"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dewei Hu","raw_affiliation_strings":["Vanderbilt University,Nashville,Tennessee,USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Nashville,Tennessee,USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063166583","display_name":"Dae Yeol Lee","orcid":"https://orcid.org/0000-0001-9990-5253"},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dae Yeol Lee","raw_affiliation_strings":["Dolby Laboratories, Inc.,Sunnyvale,California,USA"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories, Inc.,Sunnyvale,California,USA","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012578054","display_name":"Guan\u2010Ming Su","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guan-Ming Su","raw_affiliation_strings":["Dolby Laboratories, Inc.,Sunnyvale,California,USA"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories, Inc.,Sunnyvale,California,USA","institution_ids":["https://openalex.org/I4210093996"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055020146"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":0.643,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83924446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"288","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.6808000206947327,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.6808000206947327,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.6660000085830688,"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":0.6068000197410583,"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/representation","display_name":"Representation (politics)","score":0.6738017201423645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6624199151992798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6477124691009521},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6015563011169434},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5664061903953552},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5120816826820374},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46653443574905396},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4148050844669342},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3817756175994873}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6738017201423645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6624199151992798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6477124691009521},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6015563011169434},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5664061903953552},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5120816826820374},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46653443574905396},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4148050844669342},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3817756175994873},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf60004.2024.10942735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf60004.2024.10942735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Asilomar Conference on Signals, Systems, and Computers","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":14,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2982763192","https://openalex.org/W3096831136","https://openalex.org/W4200150166","https://openalex.org/W4312933868","https://openalex.org/W4392980508","https://openalex.org/W4398163664","https://openalex.org/W4402904164","https://openalex.org/W4403421039","https://openalex.org/W6779823529","https://openalex.org/W6791479011","https://openalex.org/W6795288823","https://openalex.org/W6838639034","https://openalex.org/W6838668483"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"In":[0],"this":[1,90],"paper,":[2],"we":[3,31,92,121,136],"propose":[4],"a":[5,13,33],"novel":[6,128],"framework":[7],"for":[8,148,178],"generating":[9],"volumetric":[10,175],"representation":[11,37],"from":[12],"text":[14,158,181],"prompt.":[15,159],"Our":[16],"method":[17,165],"leverages":[18],"Stable":[19],"Diffusion":[20],"to":[21,27,67,109,126,143,156],"initially":[22],"generate":[23,94],"an":[24,106,173],"image":[25,35],"corresponding":[26],"the":[28,39,81,123,145,149,157,179],"text.":[29],"Then,":[30,135],"construct":[32],"multiplane":[34],"(MPI)":[36],"of":[38,42,77,84,97,112,186],"image,":[40],"consisting":[41],"fronto-parallel":[43],"planes":[44,61],"at":[45],"discrete":[46],"depth":[47],"intervals.":[48],"Each":[49],"MPI":[50,78,125,168],"plane":[51],"holds":[52],"RGB":[53,86],"textures":[54,111],"and":[55,65,153],"alpha":[56],"opacity":[57,102],"(A)":[58],"information.":[59],"These":[60],"can":[62],"be":[63],"warped":[64],"rendered":[66,150],"simulate":[68],"views":[69,129],"on":[70,130],"other":[71],"camera":[72,133],"poses.":[73,134],"The":[74],"key":[75],"challenge":[76],"lies":[79],"in":[80],"accurate":[82],"reconstruction":[83],"occluded":[85],"textures.":[87],"To":[88],"address":[89],"issue,":[91],"first":[93],"occlusion":[95],"mask":[96],"each":[98],"layer":[99],"using":[100],"scene":[101],"information,":[103],"then":[104],"employ":[105],"inpainting":[107,146],"network":[108,147],"restore":[110],"these":[113],"regions":[114],"under":[115],"multi-perspective,":[116],"text-guided":[117],"supervision.":[118],"More":[119],"specifically,":[120],"use":[122],"inpainted":[124],"render":[127],"randomly":[131],"sampled":[132],"compute":[137],"score":[138],"distillation":[139],"sampling":[140],"(SDS)":[141],"loss":[142],"update":[144],"scenes'":[151],"realism":[152],"their":[154],"adherence":[155],"Experimental":[160],"results":[161],"demonstrate":[162],"that":[163],"our":[164],"effectively":[166],"generates":[167],"with":[169],"disoccluded":[170],"textures,":[171],"providing":[172],"immersive":[174],"viewing":[176],"experience":[177],"given":[180],"prompt":[182],"across":[183],"wide":[184],"range":[185],"viewpoints.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
