{"id":"https://openalex.org/W4415536598","doi":"https://doi.org/10.1145/3746027.3755828","title":"Robust Photo-Realistic Hand Gesture Generation: from Single View to Multiple View","display_name":"Robust Photo-Realistic Hand Gesture Generation: from Single View to Multiple View","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536598","doi":"https://doi.org/10.1145/3746027.3755828"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755828","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.10576","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035672120","display_name":"Qifan Fu","orcid":"https://orcid.org/0000-0003-3505-9865"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Qifan Fu","raw_affiliation_strings":["Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom and School of Electrical Engineering and Computer Science, Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom and School of Electrical Engineering and Computer Science, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109802477","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0001-9925-2598"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["Digital Environment Research Institute, Queen Mary University of London, London, UK, United Kingdom and Department of Medicine, University of Cambridge, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Digital Environment Research Institute, Queen Mary University of London, London, UK, United Kingdom and Department of Medicine, University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103209260","display_name":"Muhammad Asad","orcid":"https://orcid.org/0000-0002-3672-2414"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Muhammad Asad","raw_affiliation_strings":["Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114549634","display_name":"Shanxin Yuan","orcid":"https://orcid.org/0000-0003-1447-0831"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shanxin Yuan","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Queen Mary University of London, London, United Kingdom and Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Queen Mary University of London, London, United Kingdom and Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103187625","display_name":"Changjae Oh","orcid":"https://orcid.org/0000-0002-6522-2451"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Changjae Oh","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Queen Mary University London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Queen Mary University London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037886447","display_name":"Greg Slabaugh","orcid":"https://orcid.org/0000-0003-4060-5226"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gregory Slabaugh","raw_affiliation_strings":["Digital Environment Research Institute, Queen Mary University London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Digital Environment Research Institute, Queen Mary University London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5035672120"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30069492,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10662","last_page":"10670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"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":0.9961000084877014,"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/gesture","display_name":"Gesture","score":0.7821000218391418},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6402000188827515},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5521000027656555},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4722000062465668},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4691999852657318},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.44510000944137573},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4318000078201294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803600013256073},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7821000218391418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6654000282287598},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.559499979019165},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5521000027656555},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4722000062465668},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.44510000944137573},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755828","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.10576","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.10576","pdf_url":"https://arxiv.org/pdf/2505.10576","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.10576","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.10576","pdf_url":"https://arxiv.org/pdf/2505.10576","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[{"id":"https://openalex.org/G1254255506","display_name":null,"funder_award_id":"202106960011","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G3321750416","display_name":"AI UK: Creating an International Ecosystem for Responsible AI Research and Innovation","funder_award_id":"EP/Y009800/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2194775991","https://openalex.org/W2768683308","https://openalex.org/W2884585870","https://openalex.org/W3168702146","https://openalex.org/W4312933868","https://openalex.org/W4386083180","https://openalex.org/W4390873054","https://openalex.org/W4393148505","https://openalex.org/W4393148714","https://openalex.org/W4402704593"],"related_works":[],"abstract_inverted_index":{"High-fidelity":[0],"hand":[1,31,101,146],"gesture":[2,23,46,161],"generation":[3,10,24],"represents":[4],"a":[5,16,83,134,151],"significant":[6],"challenge":[7],"in":[8,57,97,187],"human-centric":[9],"tasks.":[11],"Existing":[12],"methods":[13],"typically":[14],"employ":[15],"single-view":[17,38,74,78],"mesh-rendered":[18],"image":[19],"prior":[20,79,85,132],"to":[21,43,73,93,109,127,167,175],"enhancing":[22],"quality.":[25],"However,":[26],"the":[27,34,58,68,119,141,160,169,172,176],"spatial":[28,70],"complexity":[29],"of":[30,37,60,144,171],"gestures":[32],"and":[33,67,115,164,191],"inherent":[35,72],"limitations":[36],"rendering":[39,108],"make":[40],"it":[41],"difficult":[42],"capture":[44],"complete":[45,145],"information,":[47],"particularly":[48],"when":[49],"fingers":[50],"are":[51],"occluded.":[52],"The":[53,194],"fundamental":[54],"contradiction":[55],"lies":[56],"loss":[59],"3D":[61,100],"topological":[62],"relationships":[63],"through":[64],"2D":[65],"projection":[66],"incomplete":[69],"coverage":[71],"representations.":[75],"Diverging":[76],"from":[77],"approaches,":[80],"we":[81,104,149],"propose":[82],"multi-view":[84,131],"framework,":[86],"named":[87],"Multi-Modal":[88],"UNet-based":[89],"Feature":[90],"Encoder":[91],"(MUFEN),":[92],"guide":[94],"diffusion":[95],"models":[96],"learning":[98],"comprehensive":[99],"information.":[102],"Specifically,":[103],"extend":[105],"conventional":[106],"front-view":[107],"include":[110],"rear,":[111],"left,":[112],"right,":[113],"top,":[114],"bottom":[116],"perspectives,":[117],"selecting":[118],"most":[120],"information-rich":[121],"view":[122],"combination":[123],"as":[124],"training":[125],"priors":[126],"address":[128],"occlusion.":[129],"This":[130],"with":[133],"dedicated":[135],"dual":[136],"stream":[137],"encoder":[138],"significantly":[139],"improves":[140],"model's":[142],"understanding":[143],"features.":[147,178],"Furthermore,":[148],"design":[150],"bounding":[152],"box":[153],"feature":[154],"fusion":[155],"module,":[156],"which":[157],"can":[158],"fuse":[159],"localization":[162],"features":[163,166,174],"multi-modal":[165],"enhance":[168],"location-awareness":[170],"MUFEN":[173],"gesture-related":[177],"Experiments":[179],"demonstrate":[180],"that":[181],"our":[182],"method":[183],"achieves":[184],"state-of-the-art":[185],"performance":[186],"both":[188],"quantitative":[189],"metrics":[190],"qualitative":[192],"evaluations.":[193],"source":[195],"code":[196],"is":[197],"available":[198],"at":[199],"https://github.com/fuqifan/MUFEN.":[200]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}