{"id":"https://openalex.org/W4415540426","doi":"https://doi.org/10.1145/3746027.3754728","title":"D <sup>2</sup> Gaussian: Dynamic Control with Discretized 3D View Modeling for Text-Driven 3D Gaussian Splatting Editing","display_name":"D <sup>2</sup> Gaussian: Dynamic Control with Discretized 3D View Modeling for Text-Driven 3D Gaussian Splatting Editing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540426","doi":"https://doi.org/10.1145/3746027.3754728"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754728","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5102726137","display_name":"Yefei Sheng","orcid":"https://orcid.org/0000-0002-2547-4646"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yefei Sheng","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, NanJing, China and Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2547-4646","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, NanJing, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440133","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0002-8662-9488"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8662-9488","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102776884","display_name":"Ming Tao","orcid":"https://orcid.org/0000-0002-4662-7170"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Tao","raw_affiliation_strings":["Nanjing University of Posts And Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4662-7170","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts And Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"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":"9296","last_page":"9305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9977999925613403,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9977999925613403,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9950000047683716,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/image-editing","display_name":"Image editing","score":0.6984000205993652},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5863000154495239},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5683000087738037},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5170999765396118},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4830999970436096},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.44609999656677246},{"id":"https://openalex.org/keywords/panning","display_name":"Panning (audio)","score":0.37950000166893005},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.33489999175071716},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33379998803138733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8395000100135803},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6984000205993652},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5024999976158142},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46399998664855957},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C108944566","wikidata":"https://www.wikidata.org/wiki/Q1524510","display_name":"Panning (audio)","level":4,"score":0.37950000166893005},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36230000853538513},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C173552908","wikidata":"https://www.wikidata.org/wiki/Q1366289","display_name":"Graphics pipeline","level":4,"score":0.33340001106262207},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754728","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8372243060","display_name":null,"funder_award_id":"No.62325206, 62206132","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W3215769467","https://openalex.org/W4200150166","https://openalex.org/W4214520160","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4378450585","https://openalex.org/W4385271281","https://openalex.org/W4385318467","https://openalex.org/W4386057725","https://openalex.org/W4386065887","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4389539682","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4390873294","https://openalex.org/W4390874575","https://openalex.org/W4412596323"],"related_works":[],"abstract_inverted_index":{"Current":[0],"advances":[1],"in":[2,32,84],"text-driven":[3,110],"3D":[4,11,40,79,98,111,127,172,195],"scene":[5,80],"editing":[6,53,107,153,166,173,196],"tasks":[7],"typically":[8],"render":[9],"the":[10,18,21,33,36,58,67,136,141,150,156],"representations":[12],"into":[13,130],"multi-view":[14,105,164,208],"images":[15,19],"and":[16,29,49,65,82,102,148,207],"modify":[17],"with":[20,87,155,178],"text":[22,60],"instructions.":[23],"Context":[24],"consistency":[25,31,209],"across":[26,62],"multiple":[27],"views":[28,64,81],"cross-modal":[30],"single-view":[34,72],"are":[35,144],"keys":[37],"to":[38,75,134,146,182,187],"effective":[39],"editing.":[41],"Accordingly,":[42],"existing":[43],"methods":[44],"introduce":[45,95,170],"additional":[46],"image":[47,152],"constraints":[48],"apply":[50],"pre-trained":[51,68],"2D":[52,69],"models.":[54],"However,":[55],"they":[56],"fix":[57],"same":[59],"instruction":[61],"all":[63],"freeze":[66],"model":[70,135,154],"for":[71,109,193],"editing,":[73,114],"leading":[74],"deficient":[76],"modeling":[77,100],"of":[78,159],"results":[83,206],"inconsistent":[85],"generations":[86],"visual":[88,205],"artifacts.":[89],"To":[90],"address":[91],"these":[92],"limitations,":[93],"we":[94,169],"a":[96,103,122,163,171,179,184],"discretized":[97],"view":[99,128],"method":[101,202],"diffusion-based":[104,151],"consistent":[106,165],"pipeline":[108],"gaussian":[112],"splatting":[113],"abbreviated":[115],"as":[116],"D2Gaussian.":[117],"Specifically,":[118],"our":[119,201],"approach":[120,176],"constructs":[121],"codebook":[123],"that":[124,200],"encodes":[125],"continuous":[126],"information":[129],"discrete":[131],"token":[132,142],"embeddings":[133,143],"spatial":[137],"feature":[138],"expressions.":[139],"Then,":[140],"proposed":[145],"guide":[147],"finetune":[149],"dynamic":[157],"addition":[158],"control":[160],"conditions,":[161],"yielding":[162],"pipeline.":[167],"Finally,":[168],"dataset":[174],"generation":[175],"along":[177],"3D-CLIP-SIM":[180],"metric":[181],"form":[183],"benchmark,":[185],"3D-MagicBrush,":[186],"provide":[188],"more":[189],"diverse":[190],"evaluation":[191],"scenarios":[192],"future":[194],"works.":[197],"Experiments":[198],"demonstrate":[199],"achieves":[203],"better":[204],"than":[210],"previous":[211],"state-of-the-art":[212],"methods.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}