{"id":"https://openalex.org/W4416507458","doi":"https://doi.org/10.1109/iccv51701.2025.00609","title":"Votesplat: Hough Voting Gaussian Splatting for 3D Scene Understanding","display_name":"Votesplat: Hough Voting Gaussian Splatting for 3D Scene Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416507458","doi":"https://doi.org/10.1109/iccv51701.2025.00609"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00609","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/2506.22799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083333365","display_name":"Minchao Jiang","orcid":"https://orcid.org/0000-0001-8057-4159"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minchao Jiang","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111068216","display_name":"Shunyu Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunyu Jia","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091559413","display_name":"Jiaming Gu","orcid":"https://orcid.org/0009-0001-8593-806X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Gu","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012646916","display_name":"Xiaoyuan Lu","orcid":"https://orcid.org/0009-0001-8328-9342"},"institutions":[{"id":"https://openalex.org/I4210132990","display_name":"State Key Laboratory of Cryptology","ror":"https://ror.org/02pn5rj08","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210132990"]},{"id":"https://openalex.org/I4210133493","display_name":"Shanghai Pudong Institute of Education Development","ror":"https://ror.org/04akv9b62","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210133493"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyuan Lu","raw_affiliation_strings":["Shanghai Pudong Cryptography Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Pudong Cryptography Research Institute","institution_ids":["https://openalex.org/I4210133493","https://openalex.org/I4210132990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028794275","display_name":"Guangming Zhu","orcid":"https://orcid.org/0000-0003-3214-4095"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Zhu","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058247970","display_name":"Anqi Dong","orcid":"https://orcid.org/0000-0002-0365-0733"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Anqi Dong","raw_affiliation_strings":["KTH Royal Institute of Technology,Department of Mathematics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Department of Mathematics","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425268","display_name":"Liang Zhang","orcid":"https://orcid.org/0000-0003-1566-4902"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6456","last_page":"6465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.7682999968528748,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.7682999968528748,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.041200000792741776,"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"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.030500000342726707,"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/voting","display_name":"Voting","score":0.5716000199317932},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5232999920845032},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5113000273704529},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4203999936580658},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41990000009536743},{"id":"https://openalex.org/keywords/swap","display_name":"Swap (finance)","score":0.39879998564720154},{"id":"https://openalex.org/keywords/reprojection-error","display_name":"Reprojection error","score":0.3328000009059906},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.32690000534057617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777400016784668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6919000148773193},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.620199978351593},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.5716000199317932},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5232999920845032},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C23903533","wikidata":"https://www.wikidata.org/wiki/Q17122739","display_name":"Reprojection error","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C44185422","wikidata":"https://www.wikidata.org/wiki/Q6002064","display_name":"Image-based modeling and rendering","level":3,"score":0.3125},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26589998602867126}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00609","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:2506.22799","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.22799","pdf_url":"https://arxiv.org/pdf/2506.22799","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2506.22799","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.22799","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2506.22799","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.22799","pdf_url":"https://arxiv.org/pdf/2506.22799","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://openalex.org/G2542735305","display_name":null,"funder_award_id":"24511106900","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G644447412","display_name":null,"funder_award_id":"62072358,62072352","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8865628898","display_name":null,"funder_award_id":"2024JCJCQN66","funder_id":"https://openalex.org/F4320321895","funder_display_name":"Government of Jiangxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320321895","display_name":"Government of Jiangxi Province","ror":"https://ror.org/02fzqav45"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,16,54,93,123,149,152,157],"Gaussian":[1,88],"Splatting":[2],"(3DGS)":[3],"has":[4],"become":[5],"horsepower":[6],"in":[7,147],"high-quality,":[8],"real-time":[9],"rendering":[10,44],"for":[11,71],"novel":[12,53],"view":[13],"synthesis":[14],"of":[15,145],"scenes.":[17],"However,":[18],"existing":[19],"methods":[20],"focus":[21],"primarily":[22],"on":[23],"geometric":[24],"and":[25,76,162],"appearance":[26],"modeling,":[27],"lacking":[28],"deeper":[29],"scene":[30,55],"understanding":[31,56],"while":[32,103,137],"also":[33],"incurring":[34],"high":[35],"training":[36,130],"costs":[37,131],"that":[38,58],"complicate":[39],"the":[40,110],"originally":[41],"streamlined":[42],"differentiable":[43],"pipeline.":[45],"To":[46],"this":[47],"end,":[48],"we":[49],"propose":[50],"VoteSplat,":[51],"a":[52],"framework":[57],"integrates":[59],"Hough":[60],"voting":[61,127],"with":[62,99,133],"3DGS.":[63],"Specifically,":[64],"Segment":[65],"Anything":[66],"Model":[67],"(SAM)":[68],"is":[69,167],"utilized":[70],"instance":[72,150],"segmentation,":[73,161],"extracting":[74],"objects,":[75],"generating":[77],"2D":[78,100,119],"vote":[79],"maps.":[80],"We":[81],"then":[82],"embed":[83],"spatial":[84,94],"offset":[85],"vectors":[86],"into":[87],"primitives.":[89],"These":[90],"offsets":[91],"construct":[92],"votes":[95],"by":[96],"associating":[97],"them":[98],"image":[101,120],"votes,":[102],"depth":[104,111],"distortion":[105],"constraints":[106],"refine":[107],"localization":[108],"along":[109],"axis.":[112],"For":[113],"open-vocabulary":[114,148],"object":[115,158],"localization,":[116,151,159],"VoteSplat":[117,146],"maps":[118],"semantics":[121],"to":[122],"point":[124,153],"clouds":[125],"via":[126],"points,":[128],"reducing":[129],"associated":[132],"high-dimensional":[134],"CLIP":[135],"features":[136],"preserving":[138],"semantic":[139],"unambiguity.":[140],"Extensive":[141],"experiments":[142],"demonstrate":[143],"effectiveness":[144],"cloud":[154],"understanding,":[155],"click-based":[156],"hierarchical":[160],"ablation":[163],"studies.":[164],"Our":[165],"code":[166],"available":[168],"at":[169],"https://sy-ja.github.io/votesplat/":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
