{"id":"https://openalex.org/W4416051511","doi":"https://doi.org/10.1109/3dv69130.2026.00058","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","display_name":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W4416051511","doi":"https://doi.org/10.1109/3dv69130.2026.00058"},"language":"en","primary_location":{"id":"doi:10.1109/3dv69130.2026.00058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.15769","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yanxu Meng","orcid":null},"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"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Yanxu Meng","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I4210164862","https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039135087","display_name":"Haoning Wu","orcid":"https://orcid.org/0009-0001-8717-338X"},"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"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Haoning Wu","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I4210164862","https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342828","display_name":"Ya Zhang","orcid":"https://orcid.org/0000-0002-5390-9053"},"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"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Ya Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I4210164862","https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053549250","display_name":"Weidi Xie","orcid":"https://orcid.org/0009-0002-8609-6826"},"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"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Weidi Xie","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I4210164862","https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00877245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"543","last_page":"553"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7911999821662903,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7911999821662903,"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":0.06759999692440033,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.02710000053048134,"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/encoder","display_name":"Encoder","score":0.6560999751091003},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6524999737739563},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.5407999753952026},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4595000147819519},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.40849998593330383},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3986000120639801},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.37560001015663147},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.34310001134872437},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.32829999923706055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789999842643738},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6560999751091003},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6524999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985999703407288},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5569999814033508},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3082999885082245},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.25189998745918274},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/3dv69130.2026.00058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.15769","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.15769","pdf_url":"https://arxiv.org/pdf/2508.15769","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"},{"id":"doi:10.48550/arxiv.2508.15769","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.15769","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.15769","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.15769","pdf_url":"https://arxiv.org/pdf/2508.15769","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416051511.pdf","grobid_xml":"https://content.openalex.org/works/W4416051511.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,30,63,116,181],"content":[1,182],"generation":[2,114,149],"has":[3],"recently":[4],"attracted":[5],"significant":[6],"research":[7],"interest,":[8],"driven":[9],"by":[10],"its":[11,186],"critical":[12],"applications":[13,188],"in":[14,123,189],"VR/AR":[15],"and":[16,54,67,92,98,118,156,160,166,194],"embodied":[17],"AI.":[18],"In":[19],"this":[20,111,173],"work,":[21],"we":[22,43,82,129],"tackle":[23],"the":[24,102,113,164],"challenging":[25],"task":[26],"of":[27,115,168],"synthesizing":[28],"multiple":[29,62,152],"assets":[31,64,117],"within":[32,101],"a":[33,46,51,84,108,124,176],"single":[34,125],"scene":[35,52,94],"image.":[36],"Concretely,":[37],"our":[38,145,169],"contributions":[39],"are":[40,154],"fourfold:":[41],"(i)":[42],"present":[44],"SceneGen,":[45],"novel":[47,85,177],"framework":[48],"that":[49,89],"takes":[50],"image":[53],"corresponding":[55],"object":[56],"masks":[57],"as":[58],"input,":[59],"simultaneously":[60],"producing":[61],"with":[65,72,107],"geometry":[66],"texture.":[68],"Notably,":[69],"SceneGen":[70],"operates":[71],"no":[73],"need":[74],"for":[75,179],"extra":[76],"optimization":[77],"or":[78],"asset":[79],"retrieval;":[80],"(ii)":[81],"introduce":[83],"feature":[86,103],"aggregation":[87],"module":[88],"integrates":[90],"local":[91],"global":[93],"information":[95],"from":[96],"visual":[97],"geometric":[99],"encoders":[100],"extraction":[104],"module.":[105],"Coupled":[106],"position":[109],"head,":[110],"enables":[112],"their":[119],"relative":[120],"spatial":[121],"positions":[122],"feedforward":[126],"pass;":[127],"(iii)":[128],"demonstrate":[130],"SceneGen's":[131],"direct":[132],"extensibility":[133],"to":[134],"multi-image":[135],"input":[136],"scenarios.":[137],"Despite":[138],"being":[139],"trained":[140],"solely":[141],"on":[142],"single-image":[143],"inputs,":[144],"architecture":[146],"yields":[147],"improved":[148],"performance":[150],"when":[151],"images":[153],"provided;":[155],"(iv)":[157],"extensive":[158],"quantitative":[159],"qualitative":[161],"evaluations":[162],"confirm":[163],"efficiency":[165],"robustness":[167],"approach.":[170],"We":[171],"believe":[172],"paradigm":[174],"offers":[175],"solution":[178],"high-quality":[180],"generation,":[183],"potentially":[184],"advancing":[185],"practical":[187],"downstream":[190],"tasks.":[191],"The":[192],"code":[193],"model":[195],"will":[196],"be":[197],"publicly":[198],"available":[199],"at:":[200],"https://mengmouxu.github.io/SceneGen.":[201],"\u201cEverything":[202],"you":[203],"can":[204],"imagine":[205],"is":[206],"real.\u201d":[207],"\u2014Pablo":[208],"Picasso":[209]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}