{"id":"https://openalex.org/W4403792256","doi":"https://doi.org/10.1145/3664647.3681289","title":"Edit3D: Elevating 3D Scene Editing with Attention-Driven Multi-Turn Interactivity","display_name":"Edit3D: Elevating 3D Scene Editing with Attention-Driven Multi-Turn Interactivity","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792256","doi":"https://doi.org/10.1145/3664647.3681289"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681289","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5101505982","display_name":"Peng Zhou","orcid":"https://orcid.org/0000-0002-0674-9296"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peng Zhou","raw_affiliation_strings":["College of Artificial Intelligence MoE Key Lab of Brain-Machine Intelligence Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence MoE Key Lab of Brain-Machine Intelligence Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110716516","display_name":"Dunbo Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dunbo Cai","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Company Limited, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Company Limited, Suzhou, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114068245","display_name":"Yujian Du","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujian Du","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Company Limited, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Company Limited, Suzhou, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084505306","display_name":"Runqing Zhang","orcid":"https://orcid.org/0000-0002-0503-7254"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runqing Zhang","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Company Limited, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Company Limited, Suzhou, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014362734","display_name":"Bingbing Ni","orcid":"https://orcid.org/0000-0001-7339-028X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingbing Ni","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061215231","display_name":"Jie Qin","orcid":"https://orcid.org/0000-0002-0306-534X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Qin","raw_affiliation_strings":["College of Artificial Intelligence MoE Key Lab of Brain-Machine Intelligence Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence MoE Key Lab of Brain-Machine Intelligence Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103211253","display_name":"Ling Qian","orcid":"https://orcid.org/0000-0001-5661-1722"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Qian","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Company Limited, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Company Limited, Suzhou, China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101505982"],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":0.7479,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73083321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3401","last_page":"3410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9991999864578247,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9991999864578247,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9970999956130981,"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/interactivity","display_name":"Interactivity","score":0.8270477652549744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7333410978317261},{"id":"https://openalex.org/keywords/turn","display_name":"Turn (biochemistry)","score":0.5572190284729004},{"id":"https://openalex.org/keywords/turn-taking","display_name":"Turn-taking","score":0.4820440709590912},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41436463594436646},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.41309860348701477},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3889974057674408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3632389307022095},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2320413589477539},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1262378990650177},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08653706312179565},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.06063303351402283}],"concepts":[{"id":"https://openalex.org/C144430266","wikidata":"https://www.wikidata.org/wiki/Q839721","display_name":"Interactivity","level":2,"score":0.8270477652549744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333410978317261},{"id":"https://openalex.org/C85641259","wikidata":"https://www.wikidata.org/wiki/Q290042","display_name":"Turn (biochemistry)","level":2,"score":0.5572190284729004},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.4820440709590912},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41436463594436646},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.41309860348701477},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3889974057674408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3632389307022095},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2320413589477539},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1262378990650177},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08653706312179565},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.06063303351402283},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681289","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":31,"referenced_works":["https://openalex.org/W2471768434","https://openalex.org/W2962858109","https://openalex.org/W3036167779","https://openalex.org/W3162926177","https://openalex.org/W3171249923","https://openalex.org/W3173859428","https://openalex.org/W3174525637","https://openalex.org/W3180391059","https://openalex.org/W3204971388","https://openalex.org/W3216352822","https://openalex.org/W4281485151","https://openalex.org/W4286611278","https://openalex.org/W4312388283","https://openalex.org/W4312511177","https://openalex.org/W4312747482","https://openalex.org/W4312933868","https://openalex.org/W4312956471","https://openalex.org/W4385008474","https://openalex.org/W4385318467","https://openalex.org/W4386057725","https://openalex.org/W4386071687","https://openalex.org/W4386072096","https://openalex.org/W4386076119","https://openalex.org/W4386076532","https://openalex.org/W4390871819","https://openalex.org/W4390872653","https://openalex.org/W4393148800","https://openalex.org/W4402753826","https://openalex.org/W6779823529","https://openalex.org/W6795288823","https://openalex.org/W6854781572"],"related_works":["https://openalex.org/W2900127165","https://openalex.org/W320957374","https://openalex.org/W2379107843","https://openalex.org/W3120641923","https://openalex.org/W2909654650","https://openalex.org/W3161619631","https://openalex.org/W4242512034","https://openalex.org/W3003178987","https://openalex.org/W4400912116","https://openalex.org/W562430061"],"abstract_inverted_index":{"With":[0],"the":[1,23,67,74,122,147,153,181],"rise":[2],"of":[3,25,118,173,183],"new":[4],"3D":[5,10,15,27,39,54,71,86,162,184],"representations":[6,28],"like":[7],"NeRF":[8],"and":[9,101,125,170],"Gaussian":[11],"splatting,":[12],"creating":[13],"realistic":[14],"scenes":[16,163],"is":[17,188],"easier":[18],"than":[19],"ever":[20],"before.":[21],"However,":[22],"incompatibility":[24],"these":[26,56,79],"with":[29,128],"existing":[30],"editing":[31,40,68,75,87,92,99,123,149,185],"software":[32],"has":[33],"also":[34],"introduced":[35],"unprecedented":[36],"challenges":[37],"to":[38,64,90,144],"tasks.":[41],"Although":[42],"recent":[43],"advances":[44],"in":[45,53,70,130],"text-to-image":[46],"generative":[47],"models":[48],"have":[49],"made":[50],"some":[51],"progress":[52],"editing,":[55,174],"methods":[57],"either":[58],"lack":[59],"precision":[60,124],"or":[61],"require":[62],"users":[63],"manually":[65],"specify":[66],"areas":[69,131],"space,":[72],"complicating":[73],"process.":[76],"To":[77],"overcome":[78],"issues,":[80],"we":[81,95,138],"propose":[82,96,139],"Edit3D,":[83],"an":[84,103],"innovative":[85],"method":[88],"designed":[89],"enhance":[91],"quality.":[93],"Specifically,":[94],"a":[97,140],"multi-turn":[98],"framework":[100],"introduce":[102],"attention-driven":[104],"open-set":[105],"segmentation":[106,117],"(ADSS)":[107],"technique":[108],"within":[109],"this":[110],"framework.":[111],"ADSS":[112],"allows":[113],"for":[114],"more":[115,177],"precise":[116],"parts,":[119],"which":[120],"enhances":[121],"minimizes":[126],"interference":[127],"pixels":[129],"that":[132,158],"are":[133],"not":[134],"being":[135],"edited.":[136],"Additionally,":[137],"fine-tuning":[141],"phase,":[142],"intended":[143],"further":[145],"improve":[146],"overall":[148],"quality":[150],"without":[151],"compromising":[152],"training":[154],"efficiency.":[155],"Experiments":[156],"demonstrate":[157],"Edit3D":[159],"effectively":[160],"adjusts":[161],"based":[164],"on":[165],"textual":[166],"instructions.":[167],"Through":[168],"continuous":[169],"multiple":[171],"turns":[172],"it":[175],"achieves":[176],"intricate":[178],"combinations,":[179],"enhancing":[180],"diversity":[182],"effects.":[186],"Code":[187],"available":[189],"at":[190],"https://github.com/PeterouZh/Edit3D.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
