{"id":"https://openalex.org/W4400582185","doi":"https://doi.org/10.1145/3641519.3657493","title":"DiffSound: Differentiable Modal Sound Rendering and Inverse Rendering for Diverse Inference Tasks","display_name":"DiffSound: Differentiable Modal Sound Rendering and Inverse Rendering for Diverse Inference Tasks","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400582185","doi":"https://doi.org/10.1145/3641519.3657493"},"language":"en","primary_location":{"id":"doi:10.1145/3641519.3657493","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.13486","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043651872","display_name":"Xutong Jin","orcid":"https://orcid.org/0000-0001-9017-4618"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xutong Jin","raw_affiliation_strings":["School of Computer Science, Peking University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104423663","display_name":"Chenxi Xu","orcid":"https://orcid.org/0009-0006-3102-6336"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Xu","raw_affiliation_strings":["School of Computer Science, Peking University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102907601","display_name":"Ruohan Gao","orcid":"https://orcid.org/0000-0002-8346-1114"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruohan Gao","raw_affiliation_strings":["University of Maryland College Park, United States of America and Stanford University, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Maryland College Park, United States of America and Stanford University, United States of America","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621605","display_name":"Jiajun Wu","orcid":"https://orcid.org/0000-0002-4176-343X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajun Wu","raw_affiliation_strings":["Stanford University, United States of America"],"affiliations":[{"raw_affiliation_string":"Stanford University, United States of America","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115588322","display_name":"Guoping Wang","orcid":"https://orcid.org/0000-0001-7819-0076"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoping Wang","raw_affiliation_strings":["School of Computer Science, Peking University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100359825","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0002-8901-2184"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["School of Computer Science, Peking University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5043651872"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.4986,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6314032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9962000250816345,"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/rendering","display_name":"Rendering (computer graphics)","score":0.8270402550697327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6930835843086243},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6231849789619446},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5777924656867981},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4650726318359375},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.40159109234809875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3106280267238617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.164108544588089}],"concepts":[{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.8270402550697327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930835843086243},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6231849789619446},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5777924656867981},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4650726318359375},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.40159109234809875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3106280267238617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.164108544588089},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3641519.3657493","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.13486","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.13486","pdf_url":"https://arxiv.org/pdf/2409.13486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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:2409.13486","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.13486","pdf_url":"https://arxiv.org/pdf/2409.13486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1585667180","https://openalex.org/W1975523646","https://openalex.org/W2011049085","https://openalex.org/W2011863937","https://openalex.org/W2017020016","https://openalex.org/W2021074531","https://openalex.org/W2039528058","https://openalex.org/W2043506339","https://openalex.org/W2067910404","https://openalex.org/W2069087214","https://openalex.org/W2078118823","https://openalex.org/W2084858263","https://openalex.org/W2099332139","https://openalex.org/W2156410578","https://openalex.org/W2159497557","https://openalex.org/W2556096037","https://openalex.org/W2587288333","https://openalex.org/W2797927349","https://openalex.org/W2911237314","https://openalex.org/W2966193718","https://openalex.org/W2988986133","https://openalex.org/W2997251730","https://openalex.org/W3092676848","https://openalex.org/W3109585842","https://openalex.org/W3109952375","https://openalex.org/W3110492994","https://openalex.org/W3121771029","https://openalex.org/W3127216876","https://openalex.org/W3168575721","https://openalex.org/W3174011998","https://openalex.org/W3213433499","https://openalex.org/W3215927878","https://openalex.org/W4248315330","https://openalex.org/W4286611264","https://openalex.org/W4311806037"],"related_works":["https://openalex.org/W291250033","https://openalex.org/W2035757446","https://openalex.org/W3137044537","https://openalex.org/W2008385118","https://openalex.org/W880955280","https://openalex.org/W2106647072","https://openalex.org/W2172753644","https://openalex.org/W2170209930","https://openalex.org/W4246858109","https://openalex.org/W54172855"],"abstract_inverted_index":{"Accurately":[0],"estimating":[1],"and":[2,24,103,133,168],"simulating":[3],"the":[4,19,27,52,67,72,120,123,140,151],"physical":[5,69,127],"properties":[6,70],"of":[7,14,21,56,71,115,122,142],"objects":[8],"from":[9],"real-world":[10],"sound":[11,48,80,86,153,166],"recordings":[12],"is":[13,89],"great":[15],"practical":[16],"importance":[17],"in":[18,29,154],"fields":[20],"vision,":[22],"graphics,":[23],"robotics.":[25],"However,":[26],"progress":[28],"these":[30],"directions":[31],"has":[32],"been":[33],"limited\u2014prior":[34],"differentiable":[35,79,105],"rigid":[36],"or":[37],"soft":[38],"body":[39],"simulation":[40],"techniques":[41],"cannot":[42],"be":[43],"directly":[44],"applied":[45],"to":[46,51,119,148],"modal":[47,85],"synthesis":[49,167],"due":[50],"high":[53],"sampling":[54],"rate":[55],"audio,":[57],"while":[58],"previous":[59],"audio":[60,106],"synthesizers":[61],"often":[62],"do":[63],"not":[64],"fully":[65],"model":[66],"accurate":[68],"sounding":[73],"objects.":[74],"We":[75],"propose":[76],"DiffSound,":[77],"a":[78,96,104,112,155,161],"rendering":[81],"framework":[82,109],"for":[83,164],"physics-based":[84,156],"synthesis,":[87],"which":[88],"based":[90],"on":[91],"an":[92],"implicit":[93],"shape":[94,131],"representation,":[95],"new":[97],"high-order":[98],"finite":[99],"element":[100],"analysis":[101,169],"module,":[102],"synthesizer.":[107],"Our":[108],"can":[110],"solve":[111],"wide":[113],"range":[114],"inverse":[116],"problems":[117],"thanks":[118],"differentiability":[121],"entire":[124],"pipeline,":[125],"including":[126],"parameter":[128],"estimation,":[129],"geometric":[130],"reasoning,":[132],"impact":[134],"position":[135],"prediction.":[136],"Experimental":[137],"results":[138],"demonstrate":[139],"effectiveness":[141],"our":[143],"approach,":[144],"highlighting":[145],"its":[146],"ability":[147],"accurately":[149],"reproduce":[150],"target":[152],"manner.":[157],"DiffSound":[158],"serves":[159],"as":[160],"valuable":[162],"tool":[163],"various":[165],"applications.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2024-07-13T00:00:00"}
