{"id":"https://openalex.org/W6948351959","doi":"https://doi.org/10.48550/arxiv.2501.07104","title":"RMAvatar: Photorealistic Human Avatar Reconstruction from Monocular Video Based on Rectified Mesh-embedded Gaussians","display_name":"RMAvatar: Photorealistic Human Avatar Reconstruction from Monocular Video Based on Rectified Mesh-embedded Gaussians","publication_year":2025,"publication_date":"2025-01-13","ids":{"openalex":"https://openalex.org/W6948351959","doi":"https://doi.org/10.48550/arxiv.2501.07104"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2501.07104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.07104","pdf_url":"https://arxiv.org/pdf/2501.07104","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.07104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Peng, Sen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Peng, Sen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xie, Weixing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Weixing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Zilong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zilong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Guo, Xiaohu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Xiaohu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Zhonggui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhonggui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yang, Baorong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Baorong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Dong, Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Xiao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":true,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.07750000059604645,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.07750000059604645,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.03229999914765358,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.02290000021457672,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.708899974822998},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.67330002784729},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5911999940872192},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5903000235557556},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.552299976348877},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.453900009393692},{"id":"https://openalex.org/keywords/virtual-actor","display_name":"Virtual actor","score":0.40450000762939453},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.35420000553131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534999847412109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7490000128746033},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.746999979019165},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.708899974822998},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.67330002784729},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5911999940872192},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5903000235557556},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.552299976348877},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.49880000948905945},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.453900009393692},{"id":"https://openalex.org/C150303390","wikidata":"https://www.wikidata.org/wiki/Q1983852","display_name":"Virtual actor","level":3,"score":0.40450000762939453},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.35420000553131104},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3357999920845032},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C2781089380","wikidata":"https://www.wikidata.org/wiki/Q5936753","display_name":"Human-body model","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C36816356","wikidata":"https://www.wikidata.org/wiki/Q16911860","display_name":"3D rendering","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C116921373","wikidata":"https://www.wikidata.org/wiki/Q2816483","display_name":"Real-time rendering","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C181095308","wikidata":"https://www.wikidata.org/wiki/Q1541599","display_name":"Geometric primitive","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2501.07104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.07104","pdf_url":"https://arxiv.org/pdf/2501.07104","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.07104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.07104","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.07104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.07104","pdf_url":"https://arxiv.org/pdf/2501.07104","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W6948351959.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,22,58,98,120],"introduce":[1],"RMAvatar,":[2],"a":[3,19,34,101],"novel":[4],"human":[5,36,89],"avatar":[6,17],"representation":[7],"with":[8,41],"Gaussian":[9,42,51,55,103],"splatting":[10],"embedded":[11],"on":[12,124,131],"mesh":[13,26],"to":[14,28,82,93,106],"learn":[15,107],"clothed":[16],"from":[18],"monocular":[20],"video.":[21],"utilize":[23],"the":[24,69,79,83,88,113,118],"explicit":[25],"geometry":[27],"represent":[29],"motion":[30,67,74],"and":[31,37,54,64,75,115,135],"shape":[32],"of":[33,47,78,85,117],"virtual":[35],"implicit":[38],"appearance":[39],"rendering":[40,133],"Splatting.":[43],"Our":[44],"method":[45],"consists":[46],"two":[48],"main":[49],"modules:":[50],"initialization":[52],"module":[53,105],"rectification":[56,104],"module.":[57],"embed":[59],"Gaussians":[60],"into":[61],"triangular":[62],"faces":[63],"control":[65,94],"their":[66],"through":[68],"mesh,":[70],"which":[71],"ensures":[72],"low-frequency":[73],"surface":[76],"deformation":[77],"avatar.":[80,119],"Due":[81],"limitations":[84],"LBS":[86],"formula,":[87],"skeleton":[90],"is":[91],"hard":[92],"complex":[95],"non-rigid":[96,109],"transformations.":[97],"then":[99],"design":[100],"pose-related":[102],"fine-detailed":[108],"deformations,":[110],"further":[111],"improving":[112],"realism":[114],"expressiveness":[116],"conduct":[121],"extensive":[122],"experiments":[123],"public":[125],"datasets,":[126],"RMAvatar":[127],"shows":[128],"state-of-the-art":[129],"performance":[130],"both":[132],"quality":[134],"quantitative":[136],"evaluations.":[137],"Please":[138],"see":[139],"our":[140],"project":[141],"page":[142],"at":[143],"https://rm-avatar.github.io.":[144]},"counts_by_year":[],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}