{"id":"https://openalex.org/W4408354091","doi":"https://doi.org/10.1109/icassp49660.2025.10890721","title":"ES-NeRF: Enhancing Segmentation in NeRF with CLIP","display_name":"ES-NeRF: Enhancing Segmentation in NeRF with CLIP","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354091","doi":"https://doi.org/10.1109/icassp49660.2025.10890721"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103091913","display_name":"Chong Zhao","orcid":"https://orcid.org/0000-0001-7108-9311"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Zhao","raw_affiliation_strings":["Engineering Quality Education Center of Undergraduate School, Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Quality Education Center of Undergraduate School, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594472","display_name":"Pengcheng Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Hou","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102141475","display_name":"Yan Zhai","orcid":"https://orcid.org/0009-0002-1173-9655"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhai","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xing Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Wei","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100688910","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-4269-128X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055158285","display_name":"Xiang Bi","orcid":"https://orcid.org/0000-0002-2736-4563"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bi","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03113624,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8883000016212463,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8883000016212463,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.8823999762535095,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8170999884605408,"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":0.46806469559669495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46806469559669495}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W2102605133","https://openalex.org/W2504335775","https://openalex.org/W2560023338","https://openalex.org/W2886934227","https://openalex.org/W2964288609","https://openalex.org/W2979826702","https://openalex.org/W3109585842","https://openalex.org/W3159481202","https://openalex.org/W3182236906","https://openalex.org/W3187664142","https://openalex.org/W3196651696","https://openalex.org/W3203570626","https://openalex.org/W3209945042","https://openalex.org/W3210613940","https://openalex.org/W3215769467","https://openalex.org/W4221151978","https://openalex.org/W4321512591","https://openalex.org/W4385490361","https://openalex.org/W4386065379","https://openalex.org/W4390871886","https://openalex.org/W4390874575","https://openalex.org/W4392908899","https://openalex.org/W4392910803","https://openalex.org/W4402915908","https://openalex.org/W4402961794","https://openalex.org/W6739901393","https://openalex.org/W6776044926","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6839087412","https://openalex.org/W6852501939"],"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":{"Recently,":[0],"the":[1,25,42,53,60,75,87],"mutual":[2],"combination":[3],"of":[4,27,62,90,130,138],"Neural":[5],"Radiance":[6],"Fields":[7],"(NeRF)":[8],"and":[9,29,110],"Segment":[10],"Anything":[11],"Model":[12],"(SAM)":[13],"in":[14,33,45],"3D":[15,126],"semantic":[16,65,88],"segmentation":[17,54],"has":[18],"achieved":[19],"impressive":[20],"results.":[21],"However,":[22],"they":[23],"face":[24],"challenge":[26],"accurately":[28],"consistently":[30],"segmenting":[31],"objects":[32],"complex":[34],"scenarios.":[35],"To":[36],"address":[37],"this":[38],"issue,":[39],"we":[40,68],"introduce":[41],"Enhancing":[43],"Segmentation":[44],"NeRF":[46,114],"with":[47,59,101],"CLIP(ES-NeRF),":[48],"which":[49,73],"aims":[50],"to":[51,85,106,117],"improve":[52],"quality":[55],"through":[56],"feature":[57,108],"fusion":[58,109],"help":[61],"CLIP\u2019s":[63],"powerful":[64],"comprehension.":[66],"Specifically,":[67],"propose":[69],"a":[70,136],"CLIP2SAM":[71],"module,":[72],"utilizes":[74],"image-text":[76],"features":[77,89,96],"extracted":[78,103],"by":[79,104,135],"CLIP":[80,91],"for":[81],"cross-modal":[82],"multi-scale":[83],"interactions":[84],"obtain":[86],"on":[92],"rough":[93],"segmentation.":[94,112,127],"These":[95],"will":[97],"then":[98],"be":[99],"aligned":[100],"those":[102],"SAM":[105],"achieve":[107],"complete":[111],"Finally,":[113],"is":[115,133],"employed":[116],"aggregate":[118],"masks":[119],"from":[120],"disparate":[121],"viewpoints,":[122],"thereby":[123],"attaining":[124],"high-quality":[125],"The":[128],"efficacy":[129],"our":[131],"method":[132],"substantiated":[134],"multitude":[137],"experimental":[139],"results,":[140],"demonstrating":[141],"its":[142],"superiority":[143],"over":[144],"existing":[145],"techniques.":[146]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}