{"id":"https://openalex.org/W6967087686","doi":"https://doi.org/10.48550/arxiv.2506.08334","title":"iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos","display_name":"iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W6967087686","doi":"https://doi.org/10.48550/arxiv.2506.08334"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2506.08334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.08334","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2506.08334","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Peng, Weikun","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Peng, Weikun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lv, Jun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lu, Cewu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Cewu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Savva, Manolis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Savva, Manolis","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":true,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.4293999969959259,"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":0.4293999969959259,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2215999960899353,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.06129999831318855,"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/object","display_name":"Object (grammar)","score":0.7401000261306763},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6370999813079834},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5404000282287598},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4781999886035919},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.44670000672340393},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.4083000123500824},{"id":"https://openalex.org/keywords/digital-video","display_name":"Digital video","score":0.37599998712539673}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.8023999929428101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7929999828338623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559000253677368},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7401000261306763},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6370999813079834},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5404000282287598},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4453999996185303},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C2988454689","wikidata":"https://www.wikidata.org/wiki/Q173131","display_name":"Digital video","level":3,"score":0.37599998712539673},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.31060001254081726},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3037000000476837},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2888000011444092},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2506.08334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.08334","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2506.08334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.08334","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"Articulated":[0],"objects":[1,12,28,146],"are":[2],"prevalent":[3],"in":[4,16,156],"daily":[5],"life.":[6],"Interactable":[7],"digital":[8,182],"twins":[9],"of":[10,47,66,121,141],"such":[11],"have":[13],"numerous":[14],"applications":[15],"embodied":[17],"AI":[18],"and":[19,36,44,90,93,117,188],"robotics.":[20],"Unfortunately,":[21],"current":[22],"methods":[23,166,184],"to":[24,75,87],"digitize":[25],"articulated":[26,49,71,180],"real-world":[27],"require":[29],"carefully":[30],"captured":[31,54,64,191],"data,":[32],"preventing":[33],"practical,":[34],"scalable,":[35],"generalizable":[37],"acquisition.":[38],"We":[39,159],"focus":[40],"on":[41,185],"motion":[42,92],"analysis":[43],"part-level":[45],"segmentation":[46],"an":[48,67,70],"object":[50,72,89,123,181],"from":[51,124],"a":[52,59,110,125,139],"casually":[53,63,190],"RGBD":[55,127,192],"video":[56,65,170],"shot":[57],"with":[58,69,100,164],"hand-held":[60],"camera.":[61],"A":[62],"interaction":[68],"is":[73,84,151],"easy":[74],"obtain":[76],"at":[77],"scale":[78],"using":[79],"smartphones.":[80],"However,":[81],"this":[82,134],"setting":[83],"challenging":[85],"due":[86],"simultaneous":[88],"camera":[91],"significant":[94],"occlusions":[95],"as":[96,171],"the":[97,101,122],"person":[98],"interacts":[99],"object.":[102],"To":[103,129],"tackle":[104],"these":[105],"challenges,":[106],"we":[107,137],"introduce":[108],"iTACO:":[109],"coarse-to-fine":[111],"framework":[112],"that":[113,150,167,176],"infers":[114],"joint":[115],"parameters":[116],"segments":[118],"movable":[119],"parts":[120],"dynamic":[126],"video.":[128],"evaluate":[130],"our":[131,162],"method":[132],"under":[133],"new":[135],"setting,":[136],"build":[138],"dataset":[140],"784":[142],"videos":[143],"containing":[144],"284":[145],"across":[147],"11":[148],"categories":[149],"20$\\times$":[152],"larger":[153],"than":[154],"available":[155],"prior":[157],"work.":[158],"then":[160],"compare":[161],"approach":[163],"existing":[165,179],"also":[168],"take":[169],"input.":[172],"Our":[173],"experiments":[174],"show":[175],"iTACO":[177],"outperforms":[178],"twin":[183],"both":[186],"synthetic":[187],"real":[189],"videos.":[193]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}