{"id":"https://openalex.org/W4405785944","doi":"https://doi.org/10.1109/iros58592.2024.10801488","title":"Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors","display_name":"Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785944","doi":"https://doi.org/10.1109/iros58592.2024.10801488"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801488","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":"conference-paper","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/A5002312564","display_name":"Nikolaos Tsagkas","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nikolaos Tsagkas","raw_affiliation_strings":["University of Edinburgh,School of Informatics,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,School of Informatics,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080243432","display_name":"Jack Rome","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jack Rome","raw_affiliation_strings":["University of Edinburgh,School of Informatics,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,School of Informatics,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071122608","display_name":"Subramanian Ramamoorthy","orcid":"https://orcid.org/0000-0002-6300-5103"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Subramanian Ramamoorthy","raw_affiliation_strings":["University of Edinburgh,School of Informatics,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,School of Informatics,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063600180","display_name":"Oisin Mac Aodha","orcid":"https://orcid.org/0000-0002-5787-5073"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oisin Mac Aodha","raw_affiliation_strings":["University of Edinburgh,School of Informatics,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,School of Informatics,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030505775","display_name":"Chris Xiaoxuan Lu","orcid":"https://orcid.org/0000-0002-3733-4480"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chris Xiaoxuan Lu","raw_affiliation_strings":["University College London,Department of Computer Science,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,Department of Computer Science,UK","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11610","last_page":"11617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9977999925613403,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9825000166893005,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9790999889373779,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/grasp","display_name":"GRASP","score":0.8314375877380371},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6863381862640381},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6858389377593994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.652886152267456},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4954785108566284},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4863753616809845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45238518714904785},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3910813629627228},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14444184303283691},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11053797602653503},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0683782696723938}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8314375877380371},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6863381862640381},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6858389377593994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652886152267456},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4954785108566284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4863753616809845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45238518714904785},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3910813629627228},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14444184303283691},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11053797602653503},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0683782696723938},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801488","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2991276239","https://openalex.org/W3090004508","https://openalex.org/W3159481202","https://openalex.org/W3207427042","https://openalex.org/W4221155806","https://openalex.org/W4285096920","https://openalex.org/W4312396403","https://openalex.org/W4312933868","https://openalex.org/W4383097638","https://openalex.org/W4383108296","https://openalex.org/W4385430678","https://openalex.org/W4386057725","https://openalex.org/W4386075819","https://openalex.org/W4386113271","https://openalex.org/W4387764390","https://openalex.org/W4390872669","https://openalex.org/W4390874575","https://openalex.org/W4401413764","https://openalex.org/W4401414715","https://openalex.org/W4402660104","https://openalex.org/W4402753712","https://openalex.org/W4402890475","https://openalex.org/W6727179250","https://openalex.org/W6752823625","https://openalex.org/W6783068448","https://openalex.org/W6791353385","https://openalex.org/W6801810553","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6840815571","https://openalex.org/W6848774630","https://openalex.org/W6850787431","https://openalex.org/W6851800889","https://openalex.org/W6852224567","https://openalex.org/W6852690433","https://openalex.org/W6852935954","https://openalex.org/W6853251676","https://openalex.org/W6853281718","https://openalex.org/W6853660567","https://openalex.org/W6854738657","https://openalex.org/W6854929498","https://openalex.org/W6855158220","https://openalex.org/W6856048422","https://openalex.org/W6857159348","https://openalex.org/W6858866458"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W4387804363","https://openalex.org/W2019547100","https://openalex.org/W2477150073","https://openalex.org/W2515493494"],"abstract_inverted_index":{"Precise":[0],"manipulation":[1,51],"that":[2],"is":[3],"generalizable":[4],"across":[5],"scenes":[6],"and":[7,120],"objects":[8,32],"remains":[9],"a":[10,24,53,71,80,85,91,95,99,125],"persistent":[11],"challenge":[12],"in":[13,52,124],"robotics.":[14],"Current":[15],"approaches":[16],"for":[17,49,83,138],"this":[18],"task":[19],"heavily":[20],"depend":[21],"on":[22],"having":[23],"significant":[25],"number":[26],"of":[27,45,98,103,132],"training":[28],"instances":[29],"to":[30],"handle":[31],"with":[33],"pronounced":[34],"visual":[35],"and/or":[36],"geometric":[37],"part":[38,47,74],"ambiguities.":[39],"Our":[40,77],"work":[41],"explores":[42],"the":[43,65,104,116,130],"grounding":[44],"fine-grained":[46],"descriptors":[48],"precise":[50],"zero-shot":[54],"setting":[55],"by":[56,67],"utilizing":[57],"web-trained":[58],"text-to-image":[59],"diffusion-based":[60],"generative":[61],"models.":[62],"We":[63,107],"tackle":[64],"problem":[66],"framing":[68],"it":[69],"as":[70,89,113],"dense":[72],"semantic":[73],"correspondence":[75],"task.":[76],"model":[78],"returns":[79],"gripper":[81],"pose":[82],"manipulating":[84],"specific":[86],"part,":[87],"using":[88],"reference":[90],"user-defined":[92],"click":[93],"from":[94],"source":[96],"image":[97],"visually":[100],"different":[101],"instance":[102],"same":[105],"object.":[106],"require":[108],"no":[109],"manual":[110],"grasping":[111],"demonstrations":[112],"we":[114],"leverage":[115],"intrinsic":[117],"object":[118],"geometry":[119],"features.":[121],"Practical":[122],"experiments":[123],"real-world":[126],"tabletop":[127],"scenario":[128],"validate":[129],"efficacy":[131],"our":[133],"approach,":[134],"demonstrating":[135],"its":[136],"potential":[137],"advancing":[139],"semantic-aware":[140],"robotics":[141],"manipulation.Web":[142],"page:":[143],"https://tsagkas.github.io/click2grasp":[144]},"counts_by_year":[{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}