{"id":"https://openalex.org/W7166533486","doi":"https://doi.org/10.1145/3807895.3807932","title":"Scene2Scene: LLM-driven 3D Spatial Blockout for Guided AI Video Synthesis","display_name":"Scene2Scene: LLM-driven 3D Spatial Blockout for Guided AI Video Synthesis","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7166533486","doi":"https://doi.org/10.1145/3807895.3807932"},"language":null,"primary_location":{"id":"doi:10.1145/3807895.3807932","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807895.3807932","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the Symposium on Interactive 3D Graphics and Games","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3807895.3807932","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139587270","display_name":"Yutong Alison Mei","orcid":"https://orcid.org/0009-0008-2433-7448"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yutong Alison Mei","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0009-0008-2433-7448","affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139586629","display_name":"Wei Cai","orcid":"https://orcid.org/0009-0007-6737-4831"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Cai","raw_affiliation_strings":["Columbia University, New York, New York, USA"],"raw_orcid":"https://orcid.org/0009-0007-6737-4831","affiliations":[{"raw_affiliation_string":"Columbia University, New York, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78018962,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.3255000114440918,"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"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.3255000114440918,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08229999989271164,"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/T10648","display_name":"Virtual Reality Applications and Impacts","score":0.07739999890327454,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6934999823570251},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5404999852180481},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.41830000281333923},{"id":"https://openalex.org/keywords/interactive-video","display_name":"Interactive video","score":0.37790000438690186},{"id":"https://openalex.org/keywords/video-production","display_name":"Video production","score":0.3718999922275543},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3671000003814697},{"id":"https://openalex.org/keywords/spatial-relationship","display_name":"Spatial relationship","score":0.32179999351501465},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.31299999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853000164031982},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6934999823570251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5472000241279602},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5170000195503235},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4239000082015991},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C2776566319","wikidata":"https://www.wikidata.org/wiki/Q3495514","display_name":"Interactive video","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C166142869","wikidata":"https://www.wikidata.org/wiki/Q60061622","display_name":"Video production","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C2986522900","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relationship","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C2983864324","wikidata":"https://www.wikidata.org/wiki/Q16872183","display_name":"Line drawings","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C2988327813","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Time line","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3807895.3807932","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807895.3807932","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the Symposium on Interactive 3D Graphics and Games","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3807895.3807932","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807895.3807932","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the Symposium on Interactive 3D Graphics and Games","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W4310695675","https://openalex.org/W4393967358","https://openalex.org/W4403791020","https://openalex.org/W7133190492"],"related_works":[],"abstract_inverted_index":{"Scene2Scene":[0,40],"is":[1],"an":[2,53],"interactive":[3,86],"system":[4],"that":[5,85],"bridges":[6],"natural":[7],"language":[8],"prompts":[9,46],"and":[10,28,37,63,71],"AI":[11],"video":[12],"generation":[13],"through":[14],"3D":[15,61,87],"spatial":[16,26,50,88,92],"blockout":[17],"editing.":[18],"Existing":[19],"text-to-video":[20],"approaches":[21],"provide":[22],"limited":[23],"control":[24],"over":[25],"layout":[27],"camera":[29,72],"composition,":[30],"leaving":[31],"a":[32,48,59,76],"gap":[33],"between":[34],"creators\u2019":[35],"intentions":[36],"generated":[38],"results.":[39],"addresses":[41],"this":[42],"by":[43],"parsing":[44],"narrative":[45],"into":[47],"structured":[49],"schema":[51],"via":[52],"LLM,":[54],"instantiating":[55],"the":[56],"scene":[57],"as":[58],"lightweight":[60],"blockout,":[62],"enabling":[64],"users":[65],"to":[66],"refine":[67],"character":[68],"placement,":[69],"orientation,":[70],"position":[73],"before":[74],"generating":[75],"video.":[77],"A":[78],"user":[79],"study":[80],"with":[81,97],"10":[82],"participants":[83,100],"suggests":[84],"editing":[89],"better":[90],"conveys":[91],"intent":[93],"than":[94],"text-only":[95],"description,":[96],"80%":[98],"of":[99,108],"preferring":[101],"our":[102],"approach":[103],"for":[104],"its":[105],"improved":[106],"sense":[107],"control.":[109]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-30T00:00:00"}
