{"id":"https://openalex.org/W4414934237","doi":"https://doi.org/10.1109/tip.2025.3614000","title":"Neural Scene Designer: Self-Styled Semantic Image Manipulation","display_name":"Neural Scene Designer: Self-Styled Semantic Image Manipulation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414934237","doi":"https://doi.org/10.1109/tip.2025.3614000","pmid":"https://pubmed.ncbi.nlm.nih.gov/41052154"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3614000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3614000","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5043395485","display_name":"Jianman Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianman Lin","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052027147","display_name":"Tianshui Chen","orcid":"https://orcid.org/0000-0002-5848-5624"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshui Chen","raw_affiliation_strings":["Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5848-5624","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103044807","display_name":"Chunmei Qing","orcid":"https://orcid.org/0000-0002-4733-306X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunmei Qing","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4733-306X","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064465418","display_name":"Zhijing Yang","orcid":"https://orcid.org/0000-0001-8336-5109"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijing Yang","raw_affiliation_strings":["Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8336-5109","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080512802","display_name":"Shuangping Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuangping Huang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5544-4544","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057904855","display_name":"Yuheng Ren","orcid":"https://orcid.org/0009-0002-9679-9947"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuheng Ren","raw_affiliation_strings":["Digital Industry College, Jimei University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Industry College, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412937","display_name":"Liang Lin","orcid":"https://orcid.org/0000-0003-2248-3755"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2248-3755","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36554746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"6577","last_page":"6588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.968500018119812,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.968500018119812,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9387999773025513,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9160000085830688,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6287999749183655},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5188999772071838},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46369999647140503},{"id":"https://openalex.org/keywords/premise","display_name":"Premise","score":0.45809999108314514},{"id":"https://openalex.org/keywords/cohesion","display_name":"Cohesion (chemistry)","score":0.429500013589859},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.421999990940094},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3492000102996826},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3465000092983246},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.3458000123500824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220000267028809},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5845000147819519},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C104054115","wikidata":"https://www.wikidata.org/wiki/Q216828","display_name":"Cohesion (chemistry)","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.421999990940094},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34549999237060547},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3271999955177307},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3172000050544739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31709998846054077},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3614000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3614000","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41052154","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41052154","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5071228584","display_name":null,"funder_award_id":"62202020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G558173643","display_name":null,"funder_award_id":"2025A1515010454","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6334643973","display_name":null,"funder_award_id":"2022YFB4500600","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G7242000173","display_name":null,"funder_award_id":"62206060","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8916583073","display_name":null,"funder_award_id":"2023A1515012568","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2105038642","https://openalex.org/W2475287302","https://openalex.org/W2963420272","https://openalex.org/W3035426499","https://openalex.org/W3035524453","https://openalex.org/W3043547428","https://openalex.org/W3118356434","https://openalex.org/W3157141280","https://openalex.org/W3175375202","https://openalex.org/W3199003182","https://openalex.org/W3214312641","https://openalex.org/W4225592316","https://openalex.org/W4281253515","https://openalex.org/W4312450015","https://openalex.org/W4312497550","https://openalex.org/W4312534259","https://openalex.org/W4312933868","https://openalex.org/W4313069043","https://openalex.org/W4385245566","https://openalex.org/W4385271281","https://openalex.org/W4385299582","https://openalex.org/W4385338916","https://openalex.org/W4386065395","https://openalex.org/W4386071604","https://openalex.org/W4386083151","https://openalex.org/W4387596111","https://openalex.org/W4390873054","https://openalex.org/W4393253100","https://openalex.org/W4394625844","https://openalex.org/W4400654953","https://openalex.org/W4402125712","https://openalex.org/W4402667886","https://openalex.org/W4402716273","https://openalex.org/W4402726964","https://openalex.org/W4403791673","https://openalex.org/W4404024902","https://openalex.org/W4404726022","https://openalex.org/W4407116492"],"related_works":[],"abstract_inverted_index":{"Maintaining":[0],"stylistic":[1,73],"consistency":[2,74],"is":[3,124],"crucial":[4],"for":[5,184],"the":[6,28,36,48,76,99,115,127,164,178,216,219],"cohesion":[7],"and":[8,20,72,94,105,200,203],"aesthetic":[9],"appeal":[10],"of":[11,31,39,60,102,180,218],"images,":[12],"a":[13,53,134,138,153,189],"fundamental":[14],"requirement":[15],"in":[16],"effective":[17],"image":[18,136,166],"editing":[19],"inpainting.":[21],"However,":[22],"existing":[23],"methods":[24],"primarily":[25],"focus":[26],"on":[27,126,212],"semantic":[29,67,103],"control":[30,104],"generated":[32],"content,":[33],"often":[34],"neglecting":[35],"critical":[37],"task":[38],"preserving":[40],"this":[41,44,185],"consistency.":[42,107],"In":[43],"work,":[45],"we":[46,113,187],"introduce":[47],"Neural":[49],"Scene":[50],"Designer":[51],"(NSD),":[52],"novel":[54],"framework":[55],"that":[56,90,130,157],"enables":[57],"photo-realistic":[58],"manipulation":[59],"user-specified":[61],"scene":[62],"regions":[63,132,142],"while":[64,167],"ensuring":[65],"both":[66],"alignment":[68],"with":[69,75],"user":[70],"intent":[71],"surrounding":[77],"environment.":[78],"NSD":[79],"leverages":[80],"an":[81],"advanced":[82],"diffusion":[83],"model,":[84],"incorporating":[85],"two":[86],"parallel":[87],"cross-attention":[88],"mechanisms":[89],"separately":[91],"process":[92],"text":[93],"style":[95,106,111,154],"information":[96],"to":[97,176,205],"achieve":[98],"dual":[100],"objectives":[101],"To":[108],"capture":[109],"fine-grained":[110],"representations,":[112],"propose":[114],"Progressive":[116],"Self-style":[117],"Representational":[118],"Learning":[119],"(PSRL)":[120],"module.":[121],"This":[122,192],"module":[123,151],"predicated":[125],"intuitive":[128],"premise":[129],"different":[131,144,173],"within":[133],"single":[135],"share":[137],"consistent":[139],"style,":[140],"whereas":[141],"from":[143,163,172],"images":[145],"exhibit":[146],"distinct":[147],"styles.":[148],"The":[149],"PSRL":[150],"employs":[152],"contrastive":[155],"loss":[156],"encourages":[158],"high":[159],"similarity":[160],"between":[161,170],"representations":[162],"same":[165],"enforcing":[168],"dissimilarity":[169],"those":[171],"images.":[174],"Furthermore,":[175],"address":[177],"lack":[179],"standardized":[181],"evaluation":[182],"protocols":[183],"task,":[186],"establish":[188],"comprehensive":[190],"benchmark.":[191],"benchmark":[193,214],"includes":[194],"competing":[195],"algorithms,":[196],"dedicated":[197],"style-related":[198],"metrics,":[199],"diverse":[201],"datasets":[202],"settings":[204],"facilitate":[206],"fair":[207],"comparisons.":[208],"Extensive":[209],"experiments":[210],"conducted":[211],"our":[213],"demonstrate":[215],"effectiveness":[217],"proposed":[220],"framework.":[221]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}