{"id":"https://openalex.org/W7133329900","doi":"https://doi.org/10.48550/arxiv.2603.00443","title":"SesaHand: Enhancing 3D Hand Reconstruction via Controllable Generation with Semantic and Structural Alignment","display_name":"SesaHand: Enhancing 3D Hand Reconstruction via Controllable Generation with Semantic and Structural Alignment","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133329900","doi":"https://doi.org/10.48550/arxiv.2603.00443"},"language":"en","primary_location":{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-170324","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-170324","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00443","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127906479","display_name":"Zhuoran Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Zhuoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127962310","display_name":"Xianghao Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Xianghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127998134","display_name":"Linlin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Linlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127936301","display_name":"Zheng Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127896084","display_name":"Pan Hui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui, Pan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067715162","display_name":"Anyi Rao","orcid":"https://orcid.org/0000-0003-1004-7753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rao, Anyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.4081999957561493,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.4081999957561493,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.23010000586509705,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.09459999948740005,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6751000285148621},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5839999914169312},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5820000171661377},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47620001435279846},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4528999924659729},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.45159998536109924},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3589000105857849},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.3573000133037567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827000021934509},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6751000285148621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6244999766349792},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5839999914169312},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4092999994754791},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-170324","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-170324","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Preprint"},{"id":"doi:10.48550/arxiv.2603.00443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00443","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,"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":"doi:10.48550/arxiv.2603.00443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00443","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"studies":[1],"on":[2,22,172],"3D":[3,84,191],"hand":[4,27,56,73,85,123,148,161,173,192,197],"reconstruction":[5,193],"have":[6],"demonstrated":[7],"the":[8,108,147,150,169,195],"effectiveness":[9],"of":[10],"synthetic":[11],"training":[12],"data":[13],"to":[14,25,39,53,98,134,144,166],"improve":[15],"estimation":[16],"performance.":[17],"However,":[18],"most":[19],"methods":[20],"rely":[21],"game":[23],"engines":[24],"synthesize":[26],"images,":[28,57],"which":[29,70],"often":[30],"lack":[31],"diversity":[32],"in":[33,154,185],"textures":[34],"and":[35,37,79,117,149],"environments,":[36],"fail":[38],"include":[40],"crucial":[41],"components":[42],"like":[43],"arms":[44],"or":[45],"interacting":[46],"objects.":[47],"Generative":[48],"models":[49],"are":[50],"promising":[51],"alternatives":[52],"generate":[54],"diverse":[55],"but":[58,188],"still":[59],"suffer":[60],"from":[61,76,103],"misalignment":[62],"issues.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,91,129],"present":[68],"SesaHand,":[69],"enhances":[71],"controllable":[72],"image":[74,104,124],"generation":[75,186],"both":[77],"semantic":[78,89],"structural":[80,127,132,136],"alignment":[81],"perspectives":[82],"for":[83,88,122,141],"reconstruction.":[86],"Specifically,":[87],"alignment,":[90,128],"propose":[92,159],"a":[93,160],"pipeline":[94],"with":[95,138,194],"Chain-of-Thought":[96],"inference":[97],"extract":[99],"human":[100,152],"behavior":[101],"semantics":[102,112],"captions":[105],"generated":[106,155,196],"by":[107],"Vision-Language":[109],"Model.":[110],"This":[111],"suppresses":[113],"human-irrelevant":[114],"environmental":[115],"details":[116],"ensures":[118],"sufficient":[119],"human-centric":[120],"contexts":[121],"generation.":[125],"For":[126],"introduce":[130],"hierarchical":[131],"fusion":[133],"integrate":[135],"information":[137],"different":[139],"granularity":[140],"feature":[142],"refinement":[143],"better":[145],"align":[146],"overall":[151],"body":[153],"images.":[156,198],"We":[157],"further":[158],"structure":[162],"attention":[163,171],"enhancement":[164],"method":[165,179],"efficiently":[167],"enhance":[168],"model's":[170],"regions.":[174],"Experiments":[175],"demonstrate":[176],"that":[177],"our":[178],"not":[180],"only":[181],"outperforms":[182],"prior":[183],"work":[184],"performance":[187],"also":[189],"improves":[190]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-04T00:00:00"}