{"id":"https://openalex.org/W4413158431","doi":"https://doi.org/10.1109/cvpr52734.2025.00352","title":"ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning","display_name":"ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413158431","doi":"https://doi.org/10.1109/cvpr52734.2025.00352"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5108972872","display_name":"Zhenyang Liu","orcid":"https://orcid.org/0009-0007-2079-1611"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyang Liu","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747432","display_name":"Yikai Wang","orcid":"https://orcid.org/0000-0001-6107-5063"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yikai Wang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090851249","display_name":"Sixiao Zheng","orcid":"https://orcid.org/0000-0001-8324-1528"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sixiao Zheng","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120391613","display_name":"Tongying Pan","orcid":"https://orcid.org/0000-0002-4700-1516"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongying Pan","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063691574","display_name":"Longfei Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I2800781119","display_name":"Pallium India","ror":"https://ror.org/022bs7z24","country_code":"IN","type":"nonprofit","lineage":["https://openalex.org/I2800781119"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Longfei Liang","raw_affiliation_strings":["NeuHelium Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NeuHelium Co., Ltd","institution_ids":["https://openalex.org/I2800781119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048403734","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-8670-2016"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Xue","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3718","last_page":"3727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9972000122070312,"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":0.9972000122070312,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9847000241279602,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.980400025844574,"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/computer-science","display_name":"Computer science","score":0.825167179107666},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5426289439201355},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5421257615089417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5124111771583557},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.41330254077911377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.825167179107666},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5426289439201355},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5421257615089417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5124111771583557},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.41330254077911377},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320337495","display_name":"Technology Development","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2028936041","https://openalex.org/W2128728535","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3133833192","https://openalex.org/W4200150166","https://openalex.org/W4212812504","https://openalex.org/W4214684415","https://openalex.org/W4312852845","https://openalex.org/W4321512591","https://openalex.org/W4385318467","https://openalex.org/W4385804899","https://openalex.org/W4386066792","https://openalex.org/W4386075561","https://openalex.org/W4386075819","https://openalex.org/W4386075898","https://openalex.org/W4390871962","https://openalex.org/W4390872240","https://openalex.org/W4390872744","https://openalex.org/W4390874575","https://openalex.org/W4394828156","https://openalex.org/W4401416853","https://openalex.org/W4402703038","https://openalex.org/W4402727529","https://openalex.org/W4402754134","https://openalex.org/W4402890475","https://openalex.org/W4403808973"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Open-vocabulary":[0],"3D":[1,47,79,92,110,166,179],"visual":[2],"grounding":[3,93,167,180],"and":[4,33,49,60,94,105,121,139,159,168],"reasoning":[5],"aim":[6],"to":[7,56],"localize":[8],"objects":[9,108],"in":[10,144,182],"a":[11,152],"scene":[12],"based":[13,86,129],"on":[14,44,87,130],"implicit":[15,98,140],"language":[16,141],"descriptions,":[17],"even":[18,143],"when":[19],"they":[20,41],"are":[21],"occluded.":[22],"This":[23],"ability":[24,55],"is":[25],"crucial":[26],"for":[27,64,83,163],"tasks":[28],"such":[29],"as":[30],"vision-language":[31,102],"navigation":[32],"autonomous":[34],"robotics.":[35],"However,":[36],"current":[37],"methods":[38],"struggle":[39],"because":[40],"rely":[42],"heavily":[43],"fine-tuning":[45],"with":[46],"annotations":[48,162],"mask":[50],"proposals,":[51],"which":[52],"limits":[53],"their":[54],"handle":[57],"diverse":[58],"semantics":[59],"common":[61],"knowledge":[62],"required":[63],"effective":[65],"reasoning.":[66,95],"In":[67],"this":[68],"work,":[69],"we":[70],"propose":[71],"ReasonGrounder,":[72],"an":[73],"LVLM-guided":[74],"framework":[75],"that":[76,175],"uses":[77],"hierarchical":[78],"feature":[80],"Gaussian":[81,111,127],"fields":[82],"adaptive":[84],"grouping":[85],"physical":[88],"scale,":[89,132],"enabling":[90,133],"open-vocabulary":[91,165],"ReasonGrounder":[96,125,176],"interprets":[97],"instructions":[99],"using":[100],"large":[101],"models":[103],"(LVLM)":[104],"localizes":[106],"occluded":[107,146],"through":[109,136],"splatting.":[112],"By":[113],"incorporating":[114],"2D":[115],"segmentation":[116],"masks":[117],"from":[118],"the":[119],"SAM":[120],"multi-view":[122],"CLIP":[123],"embeddings,":[124],"selects":[126],"groups":[128],"object":[131],"accurate":[134],"localization":[135],"both":[137],"explicit":[138],"understanding,":[142],"novel,":[145],"views.":[147],"We":[148],"also":[149],"contribute":[150],"ReasoningGD,":[151],"new":[153],"dataset":[154],"containing":[155],"over":[156],"10K":[157],"scenes":[158],"2":[160],"million":[161],"evaluating":[164],"amodal":[169],"perception":[170],"under":[171],"occlusion.":[172],"Experiments":[173],"show":[174],"significantly":[177],"improves":[178],"accuracy":[181],"real-world":[183],"scenarios.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}