{"id":"https://openalex.org/W4417339515","doi":"https://doi.org/10.1109/ictai66417.2025.00120","title":"An Unified Stochastic Fusion of Dual Diffusion Paths for Faithful Architectural Image Synthesis","display_name":"An Unified Stochastic Fusion of Dual Diffusion Paths for Faithful Architectural Image Synthesis","publication_year":2025,"publication_date":"2025-11-03","ids":{"openalex":"https://openalex.org/W4417339515","doi":"https://doi.org/10.1109/ictai66417.2025.00120"},"language":null,"primary_location":{"id":"doi:10.1109/ictai66417.2025.00120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai66417.2025.00120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI)","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/A5102758835","display_name":"Guangzhe Zhao","orcid":"https://orcid.org/0000-0002-5596-3686"},"institutions":[{"id":"https://openalex.org/I62853816","display_name":"Beijing University of Civil Engineering and Architecture","ror":"https://ror.org/02yj0p855","country_code":"CN","type":"education","lineage":["https://openalex.org/I62853816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhe Zhao","raw_affiliation_strings":["School of Intelligence Science and Technology, Beijing University of Civil Engineering and Architecture,Beijing Key Laboratory of Super Intelligent Technology for Urban Architecture,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Beijing University of Civil Engineering and Architecture,Beijing Key Laboratory of Super Intelligent Technology for Urban Architecture,Beijing,China","institution_ids":["https://openalex.org/I62853816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024989060","display_name":"Shilong Yang","orcid":"https://orcid.org/0000-0002-5572-9435"},"institutions":[{"id":"https://openalex.org/I62853816","display_name":"Beijing University of Civil Engineering and Architecture","ror":"https://ror.org/02yj0p855","country_code":"CN","type":"education","lineage":["https://openalex.org/I62853816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilong Yang","raw_affiliation_strings":["School of Intelligence Science and Technology, Beijing University of Civil Engineering and Architecture,Beijing Key Laboratory of Super Intelligent Technology for Urban Architecture,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Beijing University of Civil Engineering and Architecture,Beijing Key Laboratory of Super Intelligent Technology for Urban Architecture,Beijing,China","institution_ids":["https://openalex.org/I62853816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066593508","display_name":"Feihu Yan","orcid":"https://orcid.org/0000-0003-4227-0757"},"institutions":[{"id":"https://openalex.org/I62853816","display_name":"Beijing University of Civil Engineering and Architecture","ror":"https://ror.org/02yj0p855","country_code":"CN","type":"education","lineage":["https://openalex.org/I62853816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feihu Yan","raw_affiliation_strings":["School of Intelligence Science and Technology, Beijing University of Civil Engineering and Architecture,Beijing Key Laboratory of Super Intelligent Technology for Urban Architecture,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Beijing University of Civil Engineering and Architecture,Beijing Key Laboratory of Super Intelligent Technology for Urban Architecture,Beijing,China","institution_ids":["https://openalex.org/I62853816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62853816"],"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":"826","last_page":"832"},"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":0.8310999870300293,"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":0.8310999870300293,"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/T13519","display_name":"Historical Architecture and Urbanism","score":0.018200000748038292,"subfield":{"id":"https://openalex.org/subfields/1202","display_name":"History"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01720000058412552,"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/modular-design","display_name":"Modular design","score":0.7186999917030334},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5006999969482422},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.43810001015663147},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.42719998955726624},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3625999987125397},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.3546000123023987},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.34389999508857727},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.34150001406669617},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.3395000100135803}],"concepts":[{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7186999917030334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7028999924659729},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.43810001015663147},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41909998655319214},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40939998626708984},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3546000123023987},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.34389999508857727},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3402000069618225},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.3059999942779541},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C158436829","wikidata":"https://www.wikidata.org/wiki/Q4787054","display_name":"Architectural geometry","level":5,"score":0.27309998869895935},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictai66417.2025.00120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai66417.2025.00120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G219251005","display_name":null,"funder_award_id":"62176018","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":29,"referenced_works":["https://openalex.org/W1982471090","https://openalex.org/W2102166818","https://openalex.org/W2754213847","https://openalex.org/W2760432156","https://openalex.org/W2806774428","https://openalex.org/W2970662959","https://openalex.org/W3005996645","https://openalex.org/W3044628801","https://openalex.org/W3122251558","https://openalex.org/W4206254810","https://openalex.org/W4229041301","https://openalex.org/W4303613698","https://openalex.org/W4312534581","https://openalex.org/W4312933868","https://openalex.org/W4379882640","https://openalex.org/W4385270415","https://openalex.org/W4386814972","https://openalex.org/W4389523490","https://openalex.org/W4390343450","https://openalex.org/W4394977914","https://openalex.org/W4396956600","https://openalex.org/W4399532573","https://openalex.org/W4399775969","https://openalex.org/W4402716152","https://openalex.org/W4402727507","https://openalex.org/W4404198594","https://openalex.org/W4404643622","https://openalex.org/W4409262649","https://openalex.org/W4411297688"],"related_works":[],"abstract_inverted_index":{"Architectural":[0],"image":[1,89,169],"generation":[2,85],"aims":[3],"to":[4,60],"automate":[5],"the":[6,92],"creation":[7],"of":[8],"visually":[9],"and":[10,42,57,67,107,115,125,130,146,166],"semantically":[11],"coherent":[12,105],"architectural":[13,68,168],"visuals":[14],"based":[15],"on":[16],"inputs":[17],"such":[18],"as":[19],"text":[20],"prompts":[21],"or":[22,47,75],"sketches.":[23],"While":[24],"diffusion":[25,62],"models":[26],"have":[27],"recently":[28],"achieved":[29],"remarkable":[30],"success":[31],"in":[32,97],"this":[33,51],"domain,":[34],"they":[35],"still":[36],"struggle":[37],"with":[38,117,140],"preserving":[39],"structural":[40,144],"distortions":[41],"semantic":[43,109,142],"misalignment":[44],"under":[45,100],"complex":[46],"multi-modal":[48],"prompts.":[49],"In":[50],"paper,":[52],"we":[53],"propose":[54],"a":[55,82,161],"lightweight":[56],"modular":[58,151],"enhancement":[59],"existing":[61,158],"pipelines":[63],"that":[64,134],"improves":[65],"consistency":[66],"plausibility":[69],"without":[70],"requiring":[71],"external":[72],"conditioning":[73],"modules":[74],"fixed":[76],"fine-tuning":[77],"strategies.":[78],"Our":[79],"method":[80,136],"introduces":[81],"text-image-image":[83],"conditional":[84],"framework,":[86],"where":[87],"two":[88],"generated":[90],"from":[91],"same":[93],"prompt":[94],"are":[95],"fused":[96],"latent":[98],"space":[99],"unified":[101],"stochastic":[102],"control,":[103],"enabling":[104],"sampling":[106],"minimizing":[108],"degradation.":[110],"This":[111],"approach":[112],"is":[113],"model-agnostic":[114],"compatible":[116],"optional":[118],"adaptation":[119],"modules,":[120],"making":[121],"it":[122],"highly":[123],"extensible":[124],"adaptable":[126],"across":[127],"different":[128],"architectures":[129],"tasks.":[131],"Experiments":[132],"demonstrate":[133],"our":[135],"consistently":[137],"produces":[138],"images":[139],"improved":[141],"fidelity,":[143],"consistency,":[145],"stylistic":[147],"harmony.":[148],"Furthermore,":[149],"its":[150],"design":[152],"allows":[153],"for":[154,164],"efficient":[155],"integration":[156],"into":[157],"workflows,":[159],"offers":[160],"promising":[162],"foundation":[163],"controllable":[165],"reliable":[167],"synthesis.":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-15T00:00:00"}