{"id":"https://openalex.org/W4415535450","doi":"https://doi.org/10.1145/3746027.3755035","title":"SonicGauss: Position-Aware Physical Sound Synthesis for 3D Gaussian Representations","display_name":"SonicGauss: Position-Aware Physical Sound Synthesis for 3D Gaussian Representations","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415535450","doi":"https://doi.org/10.1145/3746027.3755035"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755035","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755035","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.19835","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027717952","display_name":"Chunshi Wang","orcid":"https://orcid.org/0009-0001-5994-2639"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chunshi Wang","raw_affiliation_strings":["Zhejiang University, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059537990","display_name":"H. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxing Li","raw_affiliation_strings":["Zhejiang University, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010961909","display_name":"Yawei Luo","orcid":"https://orcid.org/0000-0002-7037-1806"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yawei Luo","raw_affiliation_strings":["Zhejiang University, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027717952"],"corresponding_institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32124411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10886","last_page":"10895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9993000030517578,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/robustness","display_name":"Robustness (evolution)","score":0.6080999970436096},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5422999858856201},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.513700008392334},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4742000102996826},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.439300000667572},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.41920000314712524},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.36809998750686646},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.35830000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.619700014591217},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6080999970436096},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4404999911785126},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3343999981880188},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32359999418258667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.25859999656677246},{"id":"https://openalex.org/C2983864324","wikidata":"https://www.wikidata.org/wiki/Q16872183","display_name":"Line drawings","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755035","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755035","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"},{"id":"pmh:oai:arXiv.org:2507.19835","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19835","pdf_url":"https://arxiv.org/pdf/2507.19835","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.19835","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19835","pdf_url":"https://arxiv.org/pdf/2507.19835","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2134618463","https://openalex.org/W2159497557","https://openalex.org/W2963807156","https://openalex.org/W3046890131","https://openalex.org/W4312933868","https://openalex.org/W4385318467","https://openalex.org/W4387543562","https://openalex.org/W4393148714","https://openalex.org/W4399574574","https://openalex.org/W4402667891","https://openalex.org/W4402727915"],"related_works":[],"abstract_inverted_index":{"While":[0],"3D":[1,128],"Gaussian":[2,74],"representations":[3,43,130],"(3DGS)":[4],"have":[5],"proven":[6],"effective":[7],"for":[8,18,37],"modeling":[9],"the":[10,98,116],"geometry":[11],"and":[12,49,69,87,101,119,131],"appearance":[13],"of":[14,93],"objects,":[15],"their":[16,46],"potential":[17],"capturing":[19],"other":[20],"physical":[21],"attributes-such":[22],"as":[23],"sound-remains":[24],"largely":[25],"unexplored.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30,53],"present":[31],"a":[32,55,61,90,123],"novel":[33],"framework":[34],"dubbed":[35],"SonicGauss":[36],"synthesizing":[38],"impact":[39,85],"sounds":[40],"from":[41,73],"3DGS":[42],"by":[44],"leveraging":[45],"inherent":[47],"geometric":[48],"material":[50,67],"properties.":[51],"Specifically,":[52],"integrate":[54],"diffusion-based":[56],"sound":[57,81,133],"synthesis":[58],"model":[59],"with":[60],"PointTransformer-based":[62],"feature":[63],"extractor":[64],"to":[65],"infer":[66],"characteristics":[68],"spatial-acoustic":[70],"correlations":[71],"directly":[72],"ellipsoids.":[75],"Our":[76],"approach":[77],"supports":[78],"spatially":[79],"varying":[80],"responses":[82],"conditioned":[83],"on":[84,97],"locations":[86],"generalizes":[88],"across":[89],"wide":[91],"range":[92],"object":[94],"categories.":[95],"Experiments":[96],"ObjectFolder":[99],"dataset":[100],"real-world":[102],"recordings":[103],"demonstrate":[104],"that":[105],"our":[106],"method":[107],"produces":[108],"realistic,":[109],"position-aware":[110],"auditory":[111],"feedback.":[112],"The":[113],"results":[114],"highlight":[115],"framework's":[117],"robustness":[118],"generalization":[120],"ability,":[121],"offering":[122],"promising":[124],"step":[125],"toward":[126],"bridging":[127],"visual":[129],"interactive":[132],"synthesis.":[134]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}