{"id":"https://openalex.org/W4415062365","doi":"https://doi.org/10.1109/iccv51701.2025.00571","title":"HORT: Monocular Hand-held Objects Reconstruction with Transformers","display_name":"HORT: Monocular Hand-held Objects Reconstruction with Transformers","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415062365","doi":"https://doi.org/10.1109/iccv51701.2025.00571"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00571","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/2503.21313","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029531490","display_name":"Zerui Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI","FR"],"is_corresponding":false,"raw_author_name":"Zerui Chen","raw_affiliation_strings":["Inria, École normale supérieure, CNRS, PSL Research University,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, École normale supérieure, CNRS, PSL Research University,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210103330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047299059","display_name":"Rolandos Alexandros Potamias","orcid":"https://orcid.org/0000-0003-0049-2589"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rolandos Alexandros Potamias","raw_affiliation_strings":["Imperial College London,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776086","display_name":"Shizhe Chen","orcid":"https://orcid.org/0000-0002-7313-9703"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI","FR"],"is_corresponding":false,"raw_author_name":"Shizhe Chen","raw_affiliation_strings":["Inria, École normale supérieure, CNRS, PSL Research University,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, École normale supérieure, CNRS, PSL Research University,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210103330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI","FR"],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["Inria, École normale supérieure, CNRS, PSL Research University,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, École normale supérieure, CNRS, PSL Research University,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210103330"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37054822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6046","last_page":"6057"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9632999897003174,"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/T11448","display_name":"Face recognition and analysis","score":0.9366000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.7475000023841858},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6097000241279602},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.5062000155448914},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.5052000284194946},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48500001430511475},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3991999924182892},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.39329999685287476},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3589000105857849}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7675999999046326},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.7475000023841858},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7337999939918518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6334999799728394},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3589000105857849},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3037000000476837},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C20885615","wikidata":"https://www.wikidata.org/wiki/Q825595","display_name":"Surface reconstruction","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.2621999979019165}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00571","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:2503.21313","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21313","pdf_url":"https://arxiv.org/pdf/2503.21313","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,"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.2503.21313","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.21313","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,"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:2503.21313","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21313","pdf_url":"https://arxiv.org/pdf/2503.21313","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,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reconstructing":[0],"hand-held":[1,71],"objects":[2],"in":[3,12],"3D":[4,21,34,67,109],"from":[5,85],"monocular":[6],"images":[7],"remains":[8],"a":[9,60,76,81,93],"significant":[10],"challenge":[11],"computer":[13],"vision.":[14],"Most":[15],"existing":[16],"approaches":[17],"rely":[18],"on":[19,136],"implicit":[20],"representations,":[22],"which":[23],"produce":[24],"overly":[25],"smooth":[26],"reconstructions":[27],"and":[28,88,119,139],"are":[29],"time-consuming":[30],"to":[31,63,112,123,157],"generate":[32],"explicit":[33],"shapes.":[35],"While":[36],"more":[37],"recent":[38],"methods":[39],"directly":[40],"reconstruct":[41,65],"point":[42,68,83,117],"clouds":[43,69],"with":[44,108,149],"diffusion":[45],"models,":[46],"the":[47,86,115,124],"multi-step":[48],"denoising":[49],"makes":[50],"high-resolution":[51],"reconstruction":[52,102],"inefficient.":[53],"To":[54,100],"address":[55],"these":[56],"limitations,":[57],"we":[58,104],"propose":[59],"transformer-based":[61],"model":[62,127],"efficiently":[64],"dense":[66,94],"of":[70],"objects.":[72],"Our":[73,126],"method":[74,145],"follows":[75],"coarse-to-fine":[77],"strategy,":[78],"first":[79],"generating":[80],"sparse":[82],"cloud":[84,118],"image":[87,98,106],"progressively":[89],"refining":[90],"it":[91],"into":[92],"representation":[95],"using":[96],"pixel-aligned":[97],"features.":[99],"enhance":[101],"accuracy,":[103],"integrate":[105],"features":[107],"hand":[110],"geometry":[111],"jointly":[113],"predict":[114],"object":[116],"its":[120],"pose":[121],"relative":[122],"hand.":[125],"is":[128],"trained":[129],"end-to-end":[130],"for":[131],"optimal":[132],"performance.":[133],"Experimental":[134],"results":[135],"both":[137],"synthetic":[138],"real":[140],"datasets":[141],"demonstrate":[142],"that":[143],"our":[144],"achieves":[146],"state-of-the-art":[147],"accuracy":[148],"much":[150],"faster":[151],"inference":[152],"speed,":[153],"while":[154],"generalizing":[155],"well":[156],"in-the-wild":[158],"images.":[159]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-11T00:00:00"}