{"id":"https://openalex.org/W4414630894","doi":"https://doi.org/10.48550/arxiv.2504.15329","title":"Vision6D: 3D-to-2D Interactive Visualization and Annotation Tool for 6D Pose Estimation","display_name":"Vision6D: 3D-to-2D Interactive Visualization and Annotation Tool for 6D Pose Estimation","publication_year":2025,"publication_date":"2025-04-21","ids":{"openalex":"https://openalex.org/W4414630894","doi":"https://doi.org/10.48550/arxiv.2504.15329"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.15329","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15329","pdf_url":"https://arxiv.org/pdf/2504.15329","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,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.15329","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061555941","display_name":"Yike Zhang","orcid":"https://orcid.org/0000-0003-3503-2996","observed_orcids":["https://orcid.org/0000-0003-3503-2996"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yike","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070427577","display_name":"Eduardo Davalos","orcid":"https://orcid.org/0000-0001-7190-7273","observed_orcids":["https://orcid.org/0000-0001-7190-7273"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davalos, Eduardo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000197945","display_name":"Jack H. Noble","orcid":"https://orcid.org/0000-0002-0973-505X","observed_orcids":["https://orcid.org/0000-0002-0973-505X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noble, Jack","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":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":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7612000107765198,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7612000107765198,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.09309999644756317,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.03290000185370445,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/6d-pose-estimation","display_name":"6D pose estimation","score":0.9980000257492065},{"id":"https://openalex.org/keywords/3d-user-interfaces","display_name":"3D user interfaces","score":0.8320000171661377},{"id":"https://openalex.org/keywords/object-pose-estimation","display_name":"object pose estimation","score":0.5080000162124634},{"id":"https://openalex.org/keywords/linemod","display_name":"LINEMOD","score":0.7369999885559082},{"id":"https://openalex.org/keywords/user-study","display_name":"user study","score":0.7200000286102295},{"id":"https://openalex.org/keywords/3d-object-manipulation","display_name":"3D object manipulation","score":0.45500001311302185}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8374999761581421},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8163999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829999923706055},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6990000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6542999744415283},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5523999929428101},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.5307000279426575},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.48420000076293945},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31029999256134033},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C64073096","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Interactive visualization","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.15329","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15329","pdf_url":"https://arxiv.org/pdf/2504.15329","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,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.15329","doi":"https://doi.org/10.48550/arxiv.2504.15329","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.15329","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.15329","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15329","pdf_url":"https://arxiv.org/pdf/2504.15329","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,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414630894.pdf","grobid_xml":"https://content.openalex.org/works/W4414630894.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2795999188","https://openalex.org/W2909314588","https://openalex.org/W2949611725","https://openalex.org/W2963177347","https://openalex.org/W2963188159","https://openalex.org/W2963756608","https://openalex.org/W4377088309","https://openalex.org/W4389666682","https://openalex.org/W4393307873","https://openalex.org/W4403922306","https://openalex.org/W4407385251","https://openalex.org/W4409231217"],"related_works":["https://openalex.org/W4416039977","https://openalex.org/W4407128659","https://openalex.org/W6979358207","https://openalex.org/W4285048975","https://openalex.org/W4400067121","https://openalex.org/W7160861701","https://openalex.org/W4399764961","https://openalex.org/W6979306053","https://openalex.org/W4312305968","https://openalex.org/W7128918499"],"abstract_inverted_index":{"Accurate":[0],"6D":[1,34,77,224],"pose":[2,35,79,147,161,189,225],"estimation":[3,36,148,162],"has":[4],"gained":[5],"more":[6],"attention":[7],"over":[8],"the":[9,33,40,45,49,109,113,131,170,205],"years":[10],"for":[11,218],"robotics-assisted":[12],"tasks":[13],"that":[14,52,185],"require":[15],"precise":[16],"interaction":[17],"with":[18,68,175],"physical":[19],"objects.":[20],"This":[21,73,135,200],"paper":[22],"presents":[23],"an":[24,195,215],"interactive":[25],"3D-to-2D":[26],"visualization":[27],"and":[28,57,86,93,115,144,165,211,220,233],"annotation":[29,80,99,124,226],"tool":[30,51],"to":[31,55,89,183,203,222],"support":[32],"research":[37],"community.":[38],"To":[39],"best":[41],"of":[42,125],"our":[43],"knowledge,":[44],"proposed":[46],"work":[47],"is":[48,103,118,231],"first":[50],"allows":[53],"users":[54],"visualize":[56],"manipulate":[58],"3D":[59,197,212],"objects":[60,117],"interactively":[61],"on":[62],"a":[63,69,139],"2D":[64,208],"real-world":[65],"scene,":[66],"along":[67],"comprehensive":[70],"user":[71,179,198],"study.":[72],"system":[74],"supports":[75],"robust":[76],"camera":[78,114,132,173],"by":[81,157],"providing":[82],"both":[83],"visual":[84,192],"cues":[85,193],"spatial":[87],"relationships":[88],"determine":[90],"object":[91],"position":[92],"orientation":[94],"in":[95,101,106,142,194],"various":[96,151],"environments.":[97],"The":[98,229],"feature":[100],"Vision6D":[102,186],"particularly":[104],"helpful":[105],"scenarios":[107],"where":[108],"transformation":[110],"matrix":[111],"between":[112,169,207],"world":[116],"unknown,":[119],"as":[120,138],"it":[121],"enables":[122],"accurate":[123,188],"these":[126],"objects'":[127],"poses":[128,174],"using":[129],"only":[130],"intrinsic":[133],"matrix.":[134],"capability":[136],"serves":[137],"foundational":[140],"step":[141],"developing":[143],"training":[145],"advanced":[146],"models":[149],"across":[150],"domains.":[152],"We":[153],"evaluate":[154],"Vision6D's":[155],"effectiveness":[156],"utilizing":[158],"widely-used":[159],"open-source":[160,232],"datasets":[163],"Linemod":[164],"HANDAL":[166],"through":[167],"comparisons":[168],"default":[171],"ground-truth":[172],"manual":[176],"annotations.":[177],"A":[178],"study":[180],"was":[181],"performed":[182],"show":[184],"generates":[187],"annotations":[190],"via":[191],"intuitive":[196],"interface.":[199],"approach":[201],"aims":[202],"bridge":[204],"gap":[206],"scene":[209],"projections":[210],"scenes,":[213],"offering":[214],"effective":[216],"way":[217],"researchers":[219],"developers":[221],"solve":[223],"related":[227],"problems.":[228],"software":[230],"publicly":[234],"available":[235],"at":[236],"https://github.com/InteractiveGL/vision6D.":[237]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}
