{"id":"https://openalex.org/W4415540059","doi":"https://doi.org/10.1145/3746027.3755132","title":"HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation","display_name":"HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540059","doi":"https://doi.org/10.1145/3746027.3755132"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755132","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755132","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":["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/A5100592137","display_name":"Wenqi Dong","orcid":"https://orcid.org/0009-0005-2373-2647"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenqi Dong","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018138574","display_name":"Bangbang Yang","orcid":"https://orcid.org/0000-0001-7604-5553"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bangbang Yang","raw_affiliation_strings":["ByteDance, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100523038","display_name":"Zesong Yang","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zesong Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101026842","display_name":"Yuan Li","orcid":"https://orcid.org/0009-0007-4267-7297"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao Hu","orcid":"https://orcid.org/0000-0001-6978-6994"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Hu","raw_affiliation_strings":["ByteDance, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance, San Jose, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059021869","display_name":"Hujun Bao","orcid":"https://orcid.org/0000-0002-2662-0334"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hujun Bao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779182","display_name":"Yuewen Ma","orcid":"https://orcid.org/0009-0003-7734-7053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuewen Ma","raw_affiliation_strings":["ByteDance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075311772","display_name":"Zhaopeng Cui","orcid":"https://orcid.org/0000-0002-7130-439X"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaopeng Cui","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100592137"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52605816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9783","last_page":"9792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9986000061035156,"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":0.9976999759674072,"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/object","display_name":"Object (grammar)","score":0.6279000043869019},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4235000014305115},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4212000072002411},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.412200003862381},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3840999901294708},{"id":"https://openalex.org/keywords/spatial-coherence","display_name":"Spatial coherence","score":0.3767000138759613},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3425999879837036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663999795913696},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6444000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6381999850273132},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6279000043869019},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C2985909886","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Spatial coherence","level":3,"score":0.3767000138759613},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.358599990606308},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3425999879837036},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C193581530","wikidata":"https://www.wikidata.org/wiki/Q683778","display_name":"Structured light","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C44185422","wikidata":"https://www.wikidata.org/wiki/Q6002064","display_name":"Image-based modeling and rendering","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755132","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755132","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/G957166398","display_name":null,"funder_award_id":"62441222","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2078807908","https://openalex.org/W2105038642","https://openalex.org/W2121927366","https://openalex.org/W2295936755","https://openalex.org/W3167260844","https://openalex.org/W3175375202","https://openalex.org/W3198766663","https://openalex.org/W3216352822","https://openalex.org/W4366603017","https://openalex.org/W4385318467","https://openalex.org/W4386065887","https://openalex.org/W4386075660","https://openalex.org/W4389334989","https://openalex.org/W4390873331","https://openalex.org/W4390874211","https://openalex.org/W4390874575","https://openalex.org/W4394805495","https://openalex.org/W4400582299","https://openalex.org/W4400818704","https://openalex.org/W4400822286","https://openalex.org/W4402727155","https://openalex.org/W4402727912","https://openalex.org/W4402733585","https://openalex.org/W4402753875","https://openalex.org/W4404966675","https://openalex.org/W4412673735","https://openalex.org/W4413156287"],"related_works":[],"abstract_inverted_index":{"Scene-level":[0],"3D":[1,53,102],"generation":[2,51,55],"represents":[3],"a":[4,40,80,84,125],"critical":[5],"frontier":[6],"in":[7],"multimedia":[8],"and":[9,28,52,56,63,116,134,138,161,173],"computer":[10],"graphics.":[11],"While":[12],"existing":[13],"approaches":[14],"have":[15],"achieved":[16],"encouraging":[17],"progress,":[18],"they":[19],"still":[20],"face":[21],"challenges":[22],"such":[23],"as":[24,73,83],"constrained":[25],"object":[26,54,86,159,163],"diversity":[27],"limited":[29],"support":[30],"for":[31,166],"interactive":[32,167],"editing.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,123],"present":[38],"HiScene,":[39],"novel":[41],"hierarchical":[42,74,96],"framework":[43],"that":[44,87,104,130,153],"bridges":[45],"the":[46,148],"gap":[47],"between":[48,136],"2D":[49,107],"image":[50],"delivers":[57],"high-fidelity":[58],"scenes":[59,72],"with":[60,106,175],"compositional":[61,111],"identities":[62],"aesthetic":[64],"scene":[65],"content.":[66],"Our":[67],"key":[68],"insight":[69],"is":[70],"treating":[71],"''objects''":[75],"under":[76],"isometric":[77],"views,":[78],"where":[79],"room":[81],"functions":[82],"complex":[85],"can":[88],"be":[89],"further":[90],"decomposed":[91,121],"into":[92],"manipulatable":[93],"items.":[94],"This":[95],"approach":[97],"enables":[98],"us":[99],"to":[100,143],"generate":[101],"content":[103],"aligns":[105],"representations":[108],"while":[109,169],"maintaining":[110,170],"structure.":[112],"To":[113],"ensure":[114,144],"completeness":[115],"spatial":[117,145],"alignment":[118,174],"of":[119],"each":[120],"instance,":[122],"develop":[124],"video-diffusion-based":[126],"amodal":[127],"completion":[128],"technique":[129],"effectively":[131],"handles":[132],"occlusions":[133],"shadows":[135],"objects,":[137],"introduce":[139],"shape":[140],"prior":[141],"injection":[142],"coherence":[146],"within":[147],"scene.":[149],"Experimental":[150],"results":[151],"demonstrate":[152],"our":[154],"method":[155],"produces":[156],"more":[157],"natural":[158],"arrangements":[160],"complete":[162],"instances":[164],"suitable":[165],"applications,":[168],"physical":[171],"plausibility":[172],"user":[176],"inputs.":[177]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}
