{"id":"https://openalex.org/W4415709625","doi":"https://doi.org/10.1109/icme59968.2025.11209070","title":"Rethinking 3D Robotic Perception: Elastic Voxel Representation with Splatting Distillation","display_name":"Rethinking 3D Robotic Perception: Elastic Voxel Representation with Splatting Distillation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709625","doi":"https://doi.org/10.1109/icme59968.2025.11209070"},"language":"en","primary_location":{"id":"doi:10.1109/icme59968.2025.11209070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100595952","display_name":"Shaohui Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaohui Pan","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107559842","display_name":"Yong Xu","orcid":"https://orcid.org/0009-0004-1113-8475"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037627177","display_name":"Ruotao Xu","orcid":"https://orcid.org/0000-0002-5277-9859"},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruotao Xu","raw_affiliation_strings":["Institute for Super Robotics (Huangpu),Guangzhou,China,510000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Super Robotics (Huangpu),Guangzhou,China,510000","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101957983","display_name":"Zihan Zhou","orcid":"https://orcid.org/0009-0002-9375-1905"},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Zhou","raw_affiliation_strings":["South China Agricultural University,School of College of Mathematics and Informatics,Guangzhou,China,510640"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Agricultural University,School of College of Mathematics and Informatics,Guangzhou,China,510640","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070982537","display_name":"Si Wu","orcid":"https://orcid.org/0000-0003-4022-0852"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Wu","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110615211","display_name":"Zhuliang Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuliang Yu","raw_affiliation_strings":["Institute for Super Robotics (Huangpu),Guangzhou,China,510000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Super Robotics (Huangpu),Guangzhou,China,510000","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108671287","display_name":"Patrick Le Callet","orcid":null},"institutions":[{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]},{"id":"https://openalex.org/I4210109587","display_name":"Laboratoire de Thermique et Energie de Nantes","ror":"https://ror.org/021fdyt09","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210095849","https://openalex.org/I4210109587","https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Le Callet","raw_affiliation_strings":["University of Nantes,Polytech Nantes,Nantes,France,44306"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nantes,Polytech Nantes,Nantes,France,44306","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I4210109587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100595952"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29256409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5008000135421753,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5008000135421753,"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":0.14249999821186066,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.08060000091791153,"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/representation","display_name":"Representation (politics)","score":0.5008999705314636},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4569000005722046},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.450300008058548},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4278999865055084},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3944000005722046},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.36910000443458557},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3434000015258789},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.3352000117301941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015000224113464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6794999837875366},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.557699978351593},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5008999705314636},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3434000015258789},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C121854251","wikidata":"https://www.wikidata.org/wiki/Q62932","display_name":"Elasticity (physics)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme59968.2025.11209070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05579474v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05579474","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Journal of Oceanic Engineering, 2025, 50 (2), pp.1-6. &#x27E8;10.1109/ICME59968.2025.11209070&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2019681680","https://openalex.org/W2082511574","https://openalex.org/W2909718913","https://openalex.org/W2930863966","https://openalex.org/W4283791038","https://openalex.org/W4312933868","https://openalex.org/W4312939545","https://openalex.org/W4362519817","https://openalex.org/W4384007539","https://openalex.org/W4385318467","https://openalex.org/W4385430679","https://openalex.org/W4390572330","https://openalex.org/W4401385891","https://openalex.org/W4402353985","https://openalex.org/W4402354166","https://openalex.org/W4402952516","https://openalex.org/W4404257432"],"related_works":[],"abstract_inverted_index":{"Language-guided":[0],"robotic":[1,49],"manipulation":[2,35,50,116],"is":[3],"advancing":[4],"rapidly":[5],"with":[6,68,118],"Vision-Language-Action":[7],"(VLA)":[8],"models,":[9],"yet":[10],"faces":[11],"fundamental":[12],"challenges":[13],"in":[14],"3D":[15,73,98,110],"perception.":[16],"This":[17],"paper":[18],"addresses":[19],"two":[20,54],"critical":[21],"challenges:":[22],"the":[23,38,133],"scale":[24],"elasticity":[25],"requirement":[26],"for":[27],"simultaneously":[28],"processing":[29,67],"coarse":[30],"environmental":[31],"context":[32],"and":[33,37,97],"fine":[34],"details,":[36],"scarcity":[39],"of":[40],"action-annotated":[41],"training":[42],"data.":[43],"We":[44],"present":[45],"Splat-Actor,":[46],"a":[47,85,125],"novel":[48],"framework":[51,89],"that":[52,64,90,122],"introduces":[53],"key":[55],"innovations.":[56],"First,":[57],"we":[58,83],"develop":[59],"an":[60],"elastic":[61],"voxel":[62],"encoder":[63],"combines":[65],"multi-scale":[66],"selective":[69],"tokenization,":[70],"enabling":[71],"efficient":[72],"spatial":[74],"reasoning":[75],"while":[76,131],"adaptively":[77],"focusing":[78],"on":[79],"informative":[80],"regions.":[81],"Second,":[82],"propose":[84],"depth-constrained":[86],"feature":[87],"distillation":[88],"leverages":[91],"Gaussian":[92],"Splatting":[93],"to":[94,108],"bridge":[95],"2D":[96],"representations,":[99],"transferring":[100],"rich":[101],"semantic":[102],"features":[103],"from":[104],"pre-trained":[105],"vision":[106],"models":[107],"enhance":[109],"understanding.":[111],"Extensive":[112],"experiments":[113],"across":[114],"10":[115],"tasks":[117],"166":[119],"variations":[120],"demonstrate":[121],"Splat-Actor":[123],"achieves":[124],"6.8%":[126],"improvement":[127],"over":[128],"state-of-the-art":[129],"methods":[130],"maintaining":[132],"computational":[134],"efficiency.":[135]},"counts_by_year":[],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-30T00:00:00"}
