{"id":"https://openalex.org/W7164821739","doi":"https://doi.org/10.1145/3805622.3810798","title":"FreSCo: Joint Frequency-Aware and Spatial Control for Image Zero-Shot Style Transfer","display_name":"FreSCo: Joint Frequency-Aware and Spatial Control for Image Zero-Shot Style Transfer","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164821739","doi":"https://doi.org/10.1145/3805622.3810798"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810798","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810798","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":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810798","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138670959","display_name":"Tingrun Chen","orcid":"https://orcid.org/0009-0005-7705-7587"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingrun Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0005-7705-7587","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023344529","display_name":"Xudong Ling","orcid":"https://orcid.org/0009-0009-1128-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Ling","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0009-1128-8322","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025767081","display_name":"Shicai Wei","orcid":"https://orcid.org/0000-0001-5744-2035"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shicai Wei","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0001-5744-2035","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081385896","display_name":"Guiduo Duan","orcid":"https://orcid.org/0000-0001-6857-7744"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiduo Duan","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0001-6857-7744","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100333748","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-7486-5264"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-7486-5264","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.9354796,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1812","last_page":"1821"},"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":0.9865999817848206,"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":0.9865999817848206,"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/T11019","display_name":"Image Enhancement Techniques","score":0.0020000000949949026,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0012000000569969416,"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/fidelity","display_name":"Fidelity","score":0.5638999938964844},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.531499981880188},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4490000009536743},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4052000045776367},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.40070000290870667},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.3792000114917755},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.37450000643730164},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.3547999858856201},{"id":"https://openalex.org/keywords/constructive","display_name":"Constructive","score":0.350600004196167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6672999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5940999984741211},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5638999938964844},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42809998989105225},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.40070000290870667},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.3792000114917755},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.350600004196167},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C106192678","wikidata":"https://www.wikidata.org/wiki/Q1419761","display_name":"Collinearity","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C2780423554","wikidata":"https://www.wikidata.org/wiki/Q766198","display_name":"Haar wavelet","level":5,"score":0.2599000036716461},{"id":"https://openalex.org/C104319648","wikidata":"https://www.wikidata.org/wiki/Q1412040","display_name":"Figure\u2013ground","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810798","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810798","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":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810798","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810798","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":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7520512342453003}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2103559027","https://openalex.org/W2114770744","https://openalex.org/W2133665775","https://openalex.org/W2331128040","https://openalex.org/W2475287302","https://openalex.org/W2603777577","https://openalex.org/W2962785568","https://openalex.org/W2962793481","https://openalex.org/W4214774769","https://openalex.org/W4312933868","https://openalex.org/W4366734343","https://openalex.org/W4385271281","https://openalex.org/W4386071613","https://openalex.org/W4386076136","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4393148714","https://openalex.org/W4393158423","https://openalex.org/W4399423212","https://openalex.org/W4400582187","https://openalex.org/W4402667886","https://openalex.org/W4402715897","https://openalex.org/W4402716004","https://openalex.org/W4402716307","https://openalex.org/W4402753498","https://openalex.org/W4402753850","https://openalex.org/W4402754248","https://openalex.org/W4409262782","https://openalex.org/W4411635654","https://openalex.org/W4414360166","https://openalex.org/W4415795194"],"related_works":[],"abstract_inverted_index":{"Latent":[0,83],"Diffusion":[1],"Models":[2],"(LDMs)":[3],"have":[4],"become":[5],"a":[6,21,65,132],"cornerstone":[7],"for":[8,126],"zero-shot":[9],"style":[10,56,74,96],"transfer":[11],"in":[12,35,44],"multimedia":[13,162],"content":[14,53,72,163],"creation,":[15],"but":[16],"they":[17],"frequently":[18],"struggle":[19],"with":[20,135],"critical":[22],"trade-off":[23],"between":[24],"artistic":[25,153],"stylization":[26],"fidelity":[27],"and":[28,55,73],"semantic":[29],"structural":[30,158],"preservation.":[31],"A":[32],"key":[33],"oversight":[34],"existing":[36,168],"methods":[37],"is":[38],"the":[39,80,111,120],"neglect":[40],"of":[41],"frequency-domain":[42],"distinctions":[43],"visual":[45],"signals,":[46],"which":[47],"leads":[48],"to":[49,106,139,167],"prevalent":[50],"issues":[51],"like":[52],"drift":[54],"leakage.":[57],"To":[58],"address":[59],"these":[60],"limitations,":[61],"we":[62],"propose":[63],"FreSCo,":[64],"novel":[66],"training-free":[67],"framework":[68],"that":[69,146],"explicitly":[70],"decouples":[71],"through":[75],"dual-domain":[76],"control":[77],"mechanisms.":[78],"First,":[79],"Dynamic":[81],"Wavelet":[82,92],"Fusion":[84],"(DWLF)":[85],"module":[86],"decomposes":[87],"latent":[88,121],"features":[89],"via":[90],"Discrete":[91],"Transform":[93],"(DWT),":[94],"injecting":[95],"exclusively":[97],"into":[98,119],"high-frequency":[99],"texture":[100],"sub-bands":[101],"while":[102,155],"boosting":[103],"spectral":[104],"energy":[105],"counteract":[107],"VAE-induced":[108],"smoothing.":[109],"Second,":[110],"VAE-Compressed":[112],"Masking":[113],"strategy":[114],"encodes":[115],"edge":[116],"maps":[117],"directly":[118],"space,":[122],"resolving":[123],"pixel-latent":[124],"misalignment":[125],"precise":[127],"spatial":[128],"control.":[129],"We":[130],"construct":[131],"comprehensive":[133],"benchmark":[134],"1,280":[136],"content-style":[137],"pairs":[138],"rigorously":[140],"evaluate":[141],"performance.":[142],"Extensive":[143],"experiments":[144],"demonstrate":[145],"FreSCo":[147],"achieves":[148],"state-of-the-art":[149],"results,":[150],"generating":[151],"high-fidelity":[152],"textures":[154],"maintaining":[156],"superior":[157],"consistency":[159],"across":[160],"diverse":[161],"creation":[164],"scenarios":[165],"compared":[166],"baselines.":[169]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}