{"id":"https://openalex.org/W4405787569","doi":"https://doi.org/10.1109/iros58592.2024.10802157","title":"Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation","display_name":"Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405787569","doi":"https://doi.org/10.1109/iros58592.2024.10802157"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5007823246","display_name":"Francesco Di Felice","orcid":"https://orcid.org/0000-0002-5682-6034"},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Di Felice","raw_affiliation_strings":["Scuola Superiore Sant’Anna,Mechanical Intelligence Institute,Department of Excellence in Robotics & AI,Pisa,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scuola Superiore Sant’Anna,Mechanical Intelligence Institute,Department of Excellence in Robotics & AI,Pisa,Italy","institution_ids":["https://openalex.org/I162290304"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083388316","display_name":"Alberto Remus","orcid":"https://orcid.org/0000-0001-8812-0960"},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Remus","raw_affiliation_strings":["Scuola Superiore Sant’Anna,Mechanical Intelligence Institute,Department of Excellence in Robotics & AI,Pisa,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scuola Superiore Sant’Anna,Mechanical Intelligence Institute,Department of Excellence in Robotics & AI,Pisa,Italy","institution_ids":["https://openalex.org/I162290304"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000701918","display_name":"Stefano Gasperini","orcid":"https://orcid.org/0000-0002-7841-1569"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefano Gasperini","raw_affiliation_strings":["Technical University of Munich,TUM School of Computation, Information and Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,TUM School of Computation, Information and Technology,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067135033","display_name":"Benjamin Busam","orcid":"https://orcid.org/0000-0002-0620-5774"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin Busam","raw_affiliation_strings":["Technical University of Munich,TUM School of Computation, Information and Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,TUM School of Computation, Information and Technology,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033725695","display_name":"Lionel Ott","orcid":"https://orcid.org/0000-0001-6554-0575"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lionel Ott","raw_affiliation_strings":["ETH,Autonomous Systems Lab,Department of Mechanical and Process Engineering,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH,Autonomous Systems Lab,Department of Mechanical and Process Engineering,Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041092666","display_name":"Federico Tombari","orcid":"https://orcid.org/0000-0001-5598-5212"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Federico Tombari","raw_affiliation_strings":["Technical University of Munich,TUM School of Computation, Information and Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,TUM School of Computation, Information and Technology,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083003222","display_name":"Roland Siegwart","orcid":"https://orcid.org/0000-0002-2760-7983"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Roland Siegwart","raw_affiliation_strings":["ETH,Autonomous Systems Lab,Department of Mechanical and Process Engineering,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH,Autonomous Systems Lab,Department of Mechanical and Process Engineering,Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086535808","display_name":"Carlo Alberto Avizzano","orcid":"https://orcid.org/0000-0001-5802-541X"},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Carlo Alberto Avizzano","raw_affiliation_strings":["Scuola Superiore Sant’Anna,Mechanical Intelligence Institute,Department of Excellence in Robotics & AI,Pisa,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scuola Superiore Sant’Anna,Mechanical Intelligence Institute,Department of Excellence in Robotics & AI,Pisa,Italy","institution_ids":["https://openalex.org/I162290304"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0936,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7973424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"14204","last_page":"14211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/zero","display_name":"Zero (linguistics)","score":0.6902985572814941},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5710073113441467},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5552492141723633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5480494499206543},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.543299674987793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5371518731117249}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6902985572814941},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5710073113441467},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5552492141723633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5480494499206543},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.543299674987793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5371518731117249},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros58592.2024.10802157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.iris.sssup.it:11382/587780","is_oa":false,"landing_page_url":"https://hdl.handle.net/11382/587780","pdf_url":null,"source":{"id":"https://openalex.org/S4377196376","display_name":"CINECA IRIS Institutional Research Information System (Sant'Anna School of Advanced Studies)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162290304","host_organization_name":"Scuola Superiore Sant'Anna","host_organization_lineage":["https://openalex.org/I162290304"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1991544872","https://openalex.org/W2128019145","https://openalex.org/W2949924544","https://openalex.org/W2963188159","https://openalex.org/W2963892972","https://openalex.org/W3109585842","https://openalex.org/W3127593632","https://openalex.org/W3159481202","https://openalex.org/W3163945288","https://openalex.org/W3166285241","https://openalex.org/W3177069133","https://openalex.org/W3180720907","https://openalex.org/W3196466825","https://openalex.org/W3202538459","https://openalex.org/W4200604336","https://openalex.org/W4221151978","https://openalex.org/W4221167997","https://openalex.org/W4281557677","https://openalex.org/W4312296985","https://openalex.org/W4312359138","https://openalex.org/W4312445439","https://openalex.org/W4312933868","https://openalex.org/W4320002827","https://openalex.org/W4385318467","https://openalex.org/W4385489525","https://openalex.org/W4385805054","https://openalex.org/W4386065887","https://openalex.org/W4386066268","https://openalex.org/W4386075660","https://openalex.org/W4390190811","https://openalex.org/W4390872210","https://openalex.org/W4390873331","https://openalex.org/W4401417458","https://openalex.org/W4402623738","https://openalex.org/W4402667888","https://openalex.org/W4402716094","https://openalex.org/W4402716134","https://openalex.org/W4402754209","https://openalex.org/W4403842181","https://openalex.org/W6631190155","https://openalex.org/W6754227600","https://openalex.org/W6779823529","https://openalex.org/W6797770180","https://openalex.org/W6848478783","https://openalex.org/W6851800889","https://openalex.org/W6852616512","https://openalex.org/W6852930566","https://openalex.org/W6853660671","https://openalex.org/W6857221871","https://openalex.org/W6857532327","https://openalex.org/W6858294596","https://openalex.org/W6858885967","https://openalex.org/W6859063602","https://openalex.org/W6990034122"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Estimating":[0],"the":[1,15,25,81,86,138,148,168],"pose":[2,96,115,157],"of":[3,27,31,88,147,150],"objects":[4,67],"through":[5,119,165],"vision":[6],"is":[7,58,71,117],"essential":[8],"to":[9,24,84,111,128],"make":[10],"robotic":[11],"platforms":[12],"interact":[13],"with":[14,103,130],"environment.":[16],"Yet,":[17],"it":[18],"presents":[19,79],"many":[20],"challenges,":[21],"often":[22],"related":[23],"lack":[26],"flexibility":[28],"and":[29,43,160],"generalizability":[30],"state-of-the-art":[32],"solutions.":[33],"Diffusion":[34,89],"models":[35],"are":[36],"a":[37,55,113,136],"cutting-edge":[38],"neural":[39],"architecture":[40],"transforming":[41],"2D":[42],"3D":[44,63],"computer":[45],"vision,":[46],"outlining":[47],"remarkable":[48],"performances":[49],"in":[50,68,92,125,143,153],"zero-shot":[51,154],"novel-view":[52],"synthesis.":[53],"Such":[54],"use":[56],"case":[57],"particularly":[59],"intriguing":[60],"for":[61],"reconstructing":[62],"objects.":[64],"However,":[65],"localizing":[66],"unstructured":[69],"environments":[70],"rather":[72],"unexplored.":[73],"To":[74],"this":[75,77,126],"end,":[76],"work":[78,83,127],"Zero123-6D,":[80],"first":[82],"demonstrate":[85],"utility":[87],"Model-based":[90],"novel-view-synthesizers":[91],"enhancing":[93],"RGB":[94],"6D":[95,156],"estimation":[97,158],"at":[98],"category-level,":[99],"by":[100],"integrating":[101],"them":[102],"feature":[104],"extraction":[105],"techniques.":[106],"Novel":[107],"View":[108],"Synthesis":[109],"allows":[110],"obtain":[112],"coarse":[114],"that":[116],"refined":[118],"an":[120],"online":[121],"optimization":[122],"method":[123,140],"introduced":[124],"deal":[129],"intra-category":[131],"geometric":[132],"differences.":[133],"In":[134],"such":[135],"way,":[137],"outlined":[139],"shows":[141],"reduction":[142],"data":[144],"requirements,":[145],"removal":[146],"necessity":[149],"depth":[151],"information":[152],"category-level":[155],"task,":[159],"increased":[161],"performance,":[162],"quantitatively":[163],"demonstrated":[164],"experiments":[166],"on":[167],"CO3D":[169],"dataset.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}