{"id":"https://openalex.org/W4417025507","doi":"https://doi.org/10.1145/3756884.3770540","title":"SketchTo3DGen : GenAI Powered Articulation Ready 3D Asset Ideation using 3D Sketches and Audio Descriptions","display_name":"SketchTo3DGen : GenAI Powered Articulation Ready 3D Asset Ideation using 3D Sketches and Audio Descriptions","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4417025507","doi":"https://doi.org/10.1145/3756884.3770540"},"language":null,"primary_location":{"id":"doi:10.1145/3756884.3770540","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756884.3770540","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3756884.3770540","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 31st ACM Symposium on Virtual Reality Software and Technology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3756884.3770540","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110069917","display_name":"S. Shukla","orcid":"https://orcid.org/0009-0000-2482-8441"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shivam Ashok Shukla","raw_affiliation_strings":["TCS Research, Tata Consultancy Services, Kolkata, West Bengal, India"],"raw_orcid":"https://orcid.org/0009-0000-2482-8441","affiliations":[{"raw_affiliation_string":"TCS Research, Tata Consultancy Services, Kolkata, West Bengal, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Raghav Mittal","orcid":"https://orcid.org/0009-0006-4861-4767"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raghav Mittal","raw_affiliation_strings":["Tata Consultancy Services - Research, New Delhi, India"],"raw_orcid":"https://orcid.org/0009-0006-4861-4767","affiliations":[{"raw_affiliation_string":"Tata Consultancy Services - Research, New Delhi, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063808403","display_name":"Lokender Tiwari","orcid":"https://orcid.org/0000-0002-9217-4248"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lokender Tiwari","raw_affiliation_strings":["TCS Research, New Delhi, India"],"raw_orcid":"https://orcid.org/0000-0002-9217-4248","affiliations":[{"raw_affiliation_string":"TCS Research, New Delhi, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080835883","display_name":"Brojeshwar Bhowmick","orcid":"https://orcid.org/0000-0001-9291-5889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brojeshwar Bhowmick","raw_affiliation_strings":["TCS Research, Kolkata, India"],"raw_orcid":"https://orcid.org/0000-0001-9291-5889","affiliations":[{"raw_affiliation_string":"TCS Research, Kolkata, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110069917"],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3722176,"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":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.5580000281333923,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.5580000281333923,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.05829999968409538,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.0494999997317791,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/headset","display_name":"Headset","score":0.8579000234603882},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.7347999811172485},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6635000109672546},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.652400016784668},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5464000105857849},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.5041000247001648},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.49549999833106995},{"id":"https://openalex.org/keywords/ideation","display_name":"Ideation","score":0.47040000557899475},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.4185999929904938}],"concepts":[{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.8579000234603882},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.7347999811172485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7186999917030334},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6635000109672546},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.652400016784668},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5928999781608582},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.49549999833106995},{"id":"https://openalex.org/C170477896","wikidata":"https://www.wikidata.org/wiki/Q17039022","display_name":"Ideation","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C76178495","wikidata":"https://www.wikidata.org/wiki/Q4808784","display_name":"Asset (computer security)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C2776977519","wikidata":"https://www.wikidata.org/wiki/Q4636326","display_name":"3D interaction","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2777526259","wikidata":"https://www.wikidata.org/wiki/Q221836","display_name":"Flash (photography)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C2779495148","wikidata":"https://www.wikidata.org/wiki/Q487378","display_name":"Delphi","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C499572226","wikidata":"https://www.wikidata.org/wiki/Q1937950","display_name":"Sound design","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3756884.3770540","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756884.3770540","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3756884.3770540","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 31st ACM Symposium on Virtual Reality Software and Technology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3756884.3770540","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756884.3770540","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3756884.3770540","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 31st ACM Symposium on Virtual Reality Software and Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417025507.pdf","grobid_xml":"https://content.openalex.org/works/W4417025507.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,115],"present":[1],"SketchTo3DGen,":[2],"a":[3,12,31,36,56,75,90,97],"novel":[4],"system":[5,40],"for":[6,45],"rapid":[7],"3D":[8,18,26,57,83,98,140,146,154],"content":[9,47],"ideation":[10],"on":[11,30],"VR":[13,84,110,129,141],"headset.":[14],"SketchTo3DGen":[15],"combines":[16],"freehand":[17],"sketching":[19],"and":[20,61,70,94,122,143],"audio":[21],"descriptions":[22],"to":[23],"generate":[24],"photo-realistic":[25],"assets":[27],"on-the-fly.":[28],"Running":[29],"Meta":[32],"Quest":[33],"headset":[34],"with":[35,111],"Unity":[37],"application,":[38],"our":[39,67],"leverages":[41],"remote":[42],"GPU-accelerated":[43],"services":[44],"AI-driven":[46],"creation":[48],"using":[49,100,132],"intuitive":[50,133],"inputs.":[51],"The":[52,104],"user":[53,123],"can":[54],"draw":[55],"sketch":[58,142],"in":[59,109,135],"mid-air":[60],"describe":[62,116],"the":[63,72,82,117,136,149],"intended":[64],"asset":[65],"verbally;":[66],"pipeline":[68],"transcribes":[69],"normalizes":[71],"speech":[73],"into":[74],"text":[76],"prompt,":[77],"selects":[78],"informative":[79],"viewpoints":[80],"of":[81,126,138,151],"sketch,":[85],"generates":[86],"corresponding":[87],"images":[88],"via":[89],"state-of-the-art":[91],"text-to-image":[92],"model,":[93],"finally":[95],"reconstructs":[96],"mesh":[99],"an":[101],"image-to-3D":[102],"generator.":[103],"entire":[105],"workflow":[106],"is":[107],"experienced":[108],"minimal":[112],"interface":[113],"elements.":[114],"design":[118],"motivations,":[119],"technical":[120],"pipeline,":[121,131],"interaction":[124],"details":[125],"SketchTo3DGen.":[127],"This":[128],"in-headset":[130],"inputs":[134],"form":[137],"hand-drawn":[139],"speech,":[144],"streamlines":[145],"modeling,":[147],"accelerating":[148],"generation":[150],"articulation":[152],"ready":[153],"assets.":[155]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-12-05T00:00:00"}
