{"id":"https://openalex.org/W4416251877","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227757","title":"Multi-view Geometry-Aware Diffusion Transformer for Novel View Synthesis of Indoor Scenes","display_name":"Multi-view Geometry-Aware Diffusion Transformer for Novel View Synthesis of Indoor Scenes","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251877","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227757"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5089529572","display_name":"Xueyang Kang","orcid":"https://orcid.org/0000-0001-7159-676X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xueyang Kang","raw_affiliation_strings":["University of Melbourne, KU Leuven,Parkville,VIC,Australia,3052"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne, KU Leuven,Parkville,VIC,Australia,3052","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113750451","display_name":"Zhengkang Xiang","orcid":"https://orcid.org/0009-0005-8322-8696"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhengkang Xiang","raw_affiliation_strings":["University of Melbourne,Parkville,VIC,Australia,3052"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne,Parkville,VIC,Australia,3052","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083880559","display_name":"Zezheng Zhang","orcid":"https://orcid.org/0000-0002-2853-7729"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zezheng Zhang","raw_affiliation_strings":["University of Melbourne,Parkville,VIC,Australia,3052"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne,Parkville,VIC,Australia,3052","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003580485","display_name":"Kourosh Khoshelham","orcid":"https://orcid.org/0000-0001-6639-1727"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kourosh Khoshelham","raw_affiliation_strings":["University of Melbourne,Parkville,VIC,Australia,3052"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne,Parkville,VIC,Australia,3052","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.621399998664856,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.621399998664856,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.15800000727176666,"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":0.07569999992847443,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.6920999884605408},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6582000255584717},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.6402999758720398},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5437999963760376},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4041000008583069},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.37369999289512634},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3601999878883362},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2964000105857849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7197999954223633},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.6920999884605408},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6582000255584717},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6071000099182129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5666000247001648},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2124386111","https://openalex.org/W2133665775","https://openalex.org/W2594519801","https://openalex.org/W2962785568","https://openalex.org/W2963557767","https://openalex.org/W3034971010","https://openalex.org/W3109585842","https://openalex.org/W4214610961","https://openalex.org/W4225793068","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4319300158","https://openalex.org/W4382468817","https://openalex.org/W4385270985","https://openalex.org/W4386057725","https://openalex.org/W4386075980","https://openalex.org/W4386076215","https://openalex.org/W4386076653","https://openalex.org/W4386113271","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4390874211","https://openalex.org/W4390874694","https://openalex.org/W4402727736","https://openalex.org/W4402727792","https://openalex.org/W4402753875","https://openalex.org/W4402754024","https://openalex.org/W4413559374","https://openalex.org/W4415796936"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,128,178],"novel":[3,119,174],"view":[4,79,90,95,150,175],"synthesis":[5],"of":[6,57,87,100,117,147,160],"indoor":[7,138],"scenes":[8],"using":[9,143],"diffusion":[10,52,75],"models":[11],"has":[12],"attracted":[13],"significant":[14],"attention,":[15],"particularly":[16],"for":[17,114,149,169],"generating":[18],"desired":[19],"poses":[20],"from":[21],"a":[22,49,72,97,129,144],"source":[23,102],"image.":[24],"Existing":[25],"methods":[26],"can":[27],"produce":[28],"plausible":[29],"views":[30,41],"near":[31],"the":[32,44,88,92,115,158],"input":[33,45,89],"view,":[34],"but":[35],"they":[36],"often":[37],"fail":[38],"to":[39,64],"extrapolate":[40],"far":[42],"beyond":[43],"perspective.":[46],"Additionally,":[47],"achieving":[48],"multiview":[50],"consistent":[51,118,173],"model":[53,76,133],"typically":[54],"requires":[55],"training":[56],"computationally":[58],"intensive":[59],"3D":[60],"priors,":[61],"limiting":[62],"scalability":[63],"long-range":[65,126],"generation.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"present":[71],"transformer-based":[73],"latent":[74],"that":[77],"leverages":[78],"geometry":[80],"constraints,":[81],"including":[82],"explicitly":[83],"warped":[84],"feature":[85,104],"maps":[86],"as":[91],"denoised":[93],"target":[94],"and":[96,108,123,141,152,171],"conditioning":[98],"combination":[99],"epipolar-weighted":[101],"image":[103],"map,":[105],"Pl\u00fccker":[106],"raymap,":[107],"camera":[109],"poses.":[110],"This":[111],"approach":[112,162],"allows":[113],"extrapolation":[116],"views,":[120],"both":[121],"semantically":[122,170],"geometrically,":[124],"over":[125,163],"trajectories":[127],"single-shot":[130],"manner.":[131],"Our":[132],"is":[134],"evaluated":[135],"on":[136],"two":[137],"datasets,":[139],"ScanNet":[140],"RealEstate10K,":[142],"diverse":[145],"set":[146],"metrics":[148],"quality":[151],"consistency":[153],"evaluation.":[154],"Experimental":[155],"results":[156],"demonstrate":[157],"superiority":[159],"our":[161],"existing":[164],"models,":[165],"showcasing":[166],"its":[167],"potential":[168],"geometrically":[172],"synthesis,":[176],"scalable":[177],"video":[179],"generation":[180],"applications.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}