{"id":"https://openalex.org/W4417125294","doi":"https://doi.org/10.1145/3757377.3763951","title":"PhysHMR: Learning Humanoid Control Policies from Vision for Physically Plausible Human Motion Reconstruction","display_name":"PhysHMR: Learning Humanoid Control Policies from Vision for Physically Plausible Human Motion Reconstruction","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417125294","doi":"https://doi.org/10.1145/3757377.3763951"},"language":null,"primary_location":{"id":"doi:10.1145/3757377.3763951","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","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/A5077253274","display_name":"Qiao Feng","orcid":"https://orcid.org/0000-0003-0625-651X"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiao Feng","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, USA"],"raw_orcid":"https://orcid.org/0000-0003-0625-651X","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I79576946","https://openalex.org/I922845939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031311257","display_name":"Yiming Huang","orcid":"https://orcid.org/0009-0004-4001-0630"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Huang","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, USA"],"raw_orcid":"https://orcid.org/0009-0004-4001-0630","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I79576946","https://openalex.org/I922845939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022514312","display_name":"Yufu Wang","orcid":"https://orcid.org/0000-0001-9907-8382"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufu Wang","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, USA"],"raw_orcid":"https://orcid.org/0000-0001-9907-8382","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I79576946","https://openalex.org/I922845939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112542984","display_name":"Jiatao Gu","orcid":"https://orcid.org/0000-0003-3578-2711"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatao Gu","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, USA"],"raw_orcid":"https://orcid.org/0000-0003-3578-2711","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I79576946","https://openalex.org/I922845939"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087345525","display_name":"Lingjie Liu","orcid":"https://orcid.org/0000-0003-4301-1474"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingjie Liu","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, USA"],"raw_orcid":"https://orcid.org/0000-0003-4301-1474","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I79576946","https://openalex.org/I922845939"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4136,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86622206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.42559999227523804,"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":0.42559999227523804,"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/T12290","display_name":"Human Motion and Animation","score":0.40959998965263367,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.07090000063180923,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6977999806404114},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6211000084877014},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5608000159263611},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.4936000108718872},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4325999915599823},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.420199990272522},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4138999879360199},{"id":"https://openalex.org/keywords/structure-from-motion","display_name":"Structure from motion","score":0.4004000127315521}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7430999875068665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228999733924866},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6977999806404114},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6371999979019165},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6211000084877014},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5608000159263611},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.4936000108718872},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4325999915599823},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.4004000127315521},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3569999933242798},{"id":"https://openalex.org/C111151474","wikidata":"https://www.wikidata.org/wiki/Q1653368","display_name":"iCub","level":4,"score":0.32910001277923584},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757377.3763951","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2101032778","https://openalex.org/W2158782408","https://openalex.org/W2483862638","https://openalex.org/W2796290181","https://openalex.org/W2894766094","https://openalex.org/W2956061722","https://openalex.org/W2963355540","https://openalex.org/W2963873475","https://openalex.org/W2971856312","https://openalex.org/W2978956737","https://openalex.org/W3035581100","https://openalex.org/W3053462477","https://openalex.org/W3106857494","https://openalex.org/W3147968035","https://openalex.org/W3176327543","https://openalex.org/W3178350420","https://openalex.org/W4214679856","https://openalex.org/W4296606964","https://openalex.org/W4312261745","https://openalex.org/W4312517483","https://openalex.org/W4312518484","https://openalex.org/W4312562660","https://openalex.org/W4312915483","https://openalex.org/W4368755539","https://openalex.org/W4386076086","https://openalex.org/W4386076106","https://openalex.org/W4386076574","https://openalex.org/W4389574939","https://openalex.org/W4390873292","https://openalex.org/W4390873515","https://openalex.org/W4390874171","https://openalex.org/W4390874306","https://openalex.org/W4394625720","https://openalex.org/W4402702971","https://openalex.org/W4402715826","https://openalex.org/W4402727827","https://openalex.org/W4403624672","https://openalex.org/W4404526366","https://openalex.org/W4414982840"],"related_works":[],"abstract_inverted_index":{"Reconstructing":[0],"physically":[1,96,204,216],"plausible":[2,217],"human":[3],"motion":[4,53,91,189,218],"from":[5,157,191],"monocular":[6],"videos":[7],"remains":[8],"a":[9,74,80,87,158,184,192],"challenging":[10],"problem":[11],"in":[12,86,225],"computer":[13],"vision":[14],"and":[15,98,123,170,229],"graphics.":[16],"Existing":[17],"methods":[18,42],"primarily":[19],"focus":[20],"on":[21,46,143],"kinematics-based":[22,52],"pose":[23,139,169],"estimation,":[24],"often":[25],"leading":[26],"to":[27,31,164,195],"unrealistic":[28],"results":[29],"due":[30],"the":[32,50,64,102,112,162,175,196],"lack":[33],"of":[34,108,178],"physical":[35,230],"constraints.":[36],"To":[37,173],"address":[38],"such":[39],"artifacts,":[40],"prior":[41,223],"have":[43],"typically":[44],"relied":[45],"physics-based":[47,88],"post-processing":[48],"following":[49],"initial":[51],"estimation.":[54],"However,":[55],"this":[56,69],"two-stage":[57],"design":[58],"introduces":[59],"error":[60],"accumulation,":[61],"ultimately":[62],"limiting":[63],"overall":[65],"reconstruction":[66,92],"quality.":[67],"In":[68],"paper,":[70],"we":[71,181],"present":[72],"PhysHMR,":[73],"unified":[75],"framework":[76],"that":[77,93,187,212],"directly":[78],"learns":[79],"visual-to-action":[81],"policy":[82,134,163],"for":[83],"humanoid":[84],"control":[85],"simulator,":[89],"enabling":[90],"is":[94,111,200],"both":[95,167,226],"grounded":[97],"visually":[99],"aligned":[100],"with":[101,153],"input":[103],"video.":[104],"A":[105],"key":[106],"component":[107],"our":[109],"approach":[110],"pixel-as-ray":[113],"strategy,":[114],"which":[115,199],"lifts":[116],"2D":[117],"keypoints":[118],"into":[119,126],"3D":[120,145],"spatial":[121],"rays":[122,130],"transforms":[124],"them":[125],"global":[127,138,150,171],"space.":[128],"These":[129],"are":[131],"incorporated":[132],"as":[133],"inputs,":[135],"providing":[136],"robust":[137],"guidance":[140],"without":[141],"depending":[142],"noisy":[144],"root":[146],"predictions.":[147],"This":[148],"soft":[149],"grounding,":[151],"combined":[152],"local":[154],"visual":[155,227],"features":[156],"pretrained":[159],"encoder,":[160],"allows":[161],"reason":[165],"over":[166],"detailed":[168],"positioning.":[172],"overcome":[174],"sample":[176],"inefficiency":[177],"reinforcement":[179,206],"learning,":[180],"further":[182],"introduce":[183],"distillation":[185],"scheme":[186],"transfers":[188],"knowledge":[190],"mocap-trained":[193],"expert":[194],"vision-conditioned":[197],"policy,":[198],"then":[201],"refined":[202],"using":[203],"motivated":[205],"learning":[207],"rewards.":[208],"Extensive":[209],"experiments":[210],"demonstrate":[211],"PhysHMR":[213],"produces":[214],"high-fidelity,":[215],"across":[219],"diverse":[220],"scenarios,":[221],"outperforming":[222],"approaches":[224],"accuracy":[228],"realism.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-08T00:00:00"}