{"id":"https://openalex.org/W4404990375","doi":"https://doi.org/10.1109/iccv51701.2025.00595","title":"Manual-PA: Learning 3D Part Assembly from Instruction Diagrams","display_name":"Manual-PA: Learning 3D Part Assembly from Instruction Diagrams","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404990375","doi":"https://doi.org/10.1109/iccv51701.2025.00595"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.18011","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100445497","display_name":"Jiahao Zhang","orcid":"https://orcid.org/0000-0003-0398-7755"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiahao Zhang","raw_affiliation_strings":["The Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024613828","display_name":"Anoop Cherian","orcid":"https://orcid.org/0000-0002-5566-0351"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Anoop Cherian","raw_affiliation_strings":["Mitsubishi Electric Research Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Labs","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cristian Rodriguez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Cristian Rodriguez","raw_affiliation_strings":["The Australian Institute for Machine Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian Institute for Machine Learning","institution_ids":["https://openalex.org/I4210127558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065550142","display_name":"Weijian Deng","orcid":"https://orcid.org/0000-0003-1565-742X"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weijian Deng","raw_affiliation_strings":["The Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071663279","display_name":"Stephen Jay Gould","orcid":"https://orcid.org/0000-0001-8929-7899"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Stephen Gould","raw_affiliation_strings":["The Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6304","last_page":"6314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9869999885559082,"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":0.9807999730110168,"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/computer-science","display_name":"Computer science","score":0.5213019251823425},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.47445639967918396},{"id":"https://openalex.org/keywords/engineering-drawing","display_name":"Engineering drawing","score":0.43598994612693787},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2659601867198944},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20698308944702148}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5213019251823425},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.47445639967918396},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.43598994612693787},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2659601867198944},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20698308944702148}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.18011","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.18011","pdf_url":"https://arxiv.org/pdf/2411.18011","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.2411.18011","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.18011","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.18011","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.18011","pdf_url":"https://arxiv.org/pdf/2411.18011","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Assembling":[0],"furniture":[1,12,73,144,198],"amounts":[2],"to":[3,14,41,56,79,86,109,141,178,195],"solving":[4],"the":[5,11,62,72,81,88,118,127,132,142,147,151,160,169,172,175,185,188,201],"discrete-continuous":[6],"optimization":[7],"task":[8,45,59],"of":[9,135,153,174,187],"selecting":[10],"parts":[13,113,176],"assemble":[15,42],"and":[16,92,130,171],"estimating":[17],"their":[18,115],"connecting":[19],"poses":[20],"in":[21,66,83,117,146,181],"a":[22,43,99,121],"physically":[23],"realistic":[24],"manner.":[25],"The":[26],"problem":[27,89],"is":[28,78],"hampered":[29],"by":[30,60],"its":[31],"combinatorially":[32],"large":[33],"yet":[34],"sparse":[35],"solution":[36],"space":[37],"thus":[38],"making":[39],"learning":[40,49,123],"challenging":[44],"for":[46],"current":[47],"machine":[48],"models.":[50],"In":[51],"this":[52,58],"paper,":[53],"we":[54,96,156],"attempt":[55],"solve":[57],"leveraging":[61],"assembly":[63,128,182,199],"instructions":[64],"provided":[65],"diagrammatic":[67],"manuals":[68,119],"that":[69,107,167],"typically":[70],"accompany":[71],"parts.":[74],"Our":[75,164],"key":[76],"insight":[77],"use":[80],"cues":[82],"these":[84],"diagrams":[85,170],"split":[87],"into":[90],"discrete":[91],"continuous":[93],"phases.":[94],"Specifically,":[95],"present":[97],"Manual-PA,":[98],"transformer-based":[100],"instruction":[101],"Manual-guided":[102],"3D":[103,112],"Part":[104],"Assembly":[105],"framework":[106],"learns":[108],"semantically":[110],"align":[111],"with":[114],"illustrations":[116],"using":[120,168],"contrastive":[122],"backbone":[124],"towards":[125],"predicting":[126],"order":[129,173],"infers":[131],"6D":[133],"pose":[134],"each":[136],"part":[137],"via":[138],"relating":[139],"it":[140],"final":[143],"depicted":[145],"manual.":[148],"To":[149],"validate":[150],"efficacy":[152],"our":[154],"method,":[155],"conduct":[157],"experiments":[158],"on":[159,200],"benchmark":[161],"PartNet":[162],"dataset.":[163,203],"results":[165],"show":[166],"lead":[177],"significant":[179],"improvements":[180],"performance":[183],"against":[184],"state":[186],"art.":[189],"Further,":[190],"Manual-PA":[191],"demonstrates":[192],"strong":[193],"generalization":[194],"real-world":[196],"IKEA":[197],"IKEA-Manual":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}