{"id":"https://openalex.org/W7138212888","doi":"https://doi.org/10.1609/aaai.v40i11.37859","title":"Free-Form Scene Editor: Enabling Multi-Round Object Manipulation Like in a 3D Engine","display_name":"Free-Form Scene Editor: Enabling Multi-Round Object Manipulation Like in a 3D Engine","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138212888","doi":"https://doi.org/10.1609/aaai.v40i11.37859"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i11.37859","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37859","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i11.37859","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002734020","display_name":"Xincheng Shuai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xincheng Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129699736","display_name":"Zhenyuan Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenyuan Qin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129679877","display_name":"Henghui Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henghui Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129750783","display_name":"Dacheng Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"9033","last_page":"9041"},"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":0.7232999801635742,"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":0.7232999801635742,"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":0.09290000051259995,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.07050000131130219,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.7731999754905701},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7139000296592712},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.515500009059906},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5134999752044678},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4083000123500824},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3887999951839447},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3702999949455261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046000003814697},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.7731999754905701},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7139000296592712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6513000130653381},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5813000202178955},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3887999951839447},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.34929999709129333},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.30640000104904175},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26589998602867126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i11.37859","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37859","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37859","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i11.37859","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37859","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3671822789","display_name":null,"funder_award_id":"62472104","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,18,50,142],"text-to-image":[3],"(T2I)":[4],"diffusion":[5],"models":[6,61],"have":[7],"significantly":[8,138],"improved":[9],"semantic":[10],"image":[11,51],"editing,":[12],"yet":[13],"most":[14],"methods":[15,141],"fall":[16],"short":[17],"performing":[19],"3D-aware":[20,30,104,147],"object":[21,38,105],"manipulation.":[22],"In":[23],"this":[24],"work,":[25],"we":[26,107],"present":[27],"FFSE,":[28],"a":[29,64,110],"autoregressive":[31],"framework":[32],"designed":[33],"to":[34,72],"enable":[35],"intuitive,":[36],"physically-consistent":[37],"editing":[39,62,97,116,148],"directly":[40],"on":[41],"real-world":[42],"images.":[43],"Unlike":[44],"previous":[45],"approaches":[46],"that":[47,134],"either":[48],"operate":[49],"space":[52],"or":[53],"require":[54],"slow":[55],"and":[56,80,90,121,128,145],"error-prone":[57],"3D":[58,68],"reconstruction,":[59],"FFSE":[60,137],"as":[63,77],"sequence":[65],"of":[66,102],"learned":[67],"transformations,":[69],"allowing":[70],"users":[71],"perform":[73],"arbitrary":[74],"manipulations,":[75],"such":[76],"translation,":[78],"scaling,":[79],"rotation,":[81],"while":[82],"preserving":[83],"realistic":[84],"background":[85],"effects":[86],"(e.g.,":[87],"shadows,":[88],"reflections)":[89],"maintaining":[91],"global":[92],"scene":[93],"consistency":[94],"across":[95,118],"multiple":[96],"rounds.":[98],"To":[99],"support":[100],"learning":[101],"multi-round":[103,127,146],"manipulation,":[106],"introduce":[108],"3DObjectEditor,":[109],"hybrid":[111],"dataset":[112],"constructed":[113],"from":[114],"simulated":[115],"sequences":[117],"diverse":[119],"objects":[120],"scenes,":[122],"enabling":[123],"effective":[124],"training":[125],"under":[126],"dynamic":[129],"conditions.":[130],"Extensive":[131],"experiments":[132],"show":[133],"the":[135],"proposed":[136],"outperforms":[139],"existing":[140],"both":[143],"single-round":[144],"scenarios.":[149]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}