{"id":"https://openalex.org/W4416514194","doi":"https://doi.org/10.1109/iccv51701.2025.01410","title":"CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation","display_name":"CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416514194","doi":"https://doi.org/10.1109/iccv51701.2025.01410"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.23347","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100718639","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0002-2683-1262"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["School of Artificial Intelligence, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031396623","display_name":"Shengqian Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengqian Li","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064575558","display_name":"Zuzeng Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuzeng Lin","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431127","display_name":"Feng Wang","orcid":"https://orcid.org/0000-0001-6975-4335"},"institutions":[{"id":"https://openalex.org/I4210146168","display_name":"CREATe Centre","ror":"https://ror.org/04e30s833","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210146168"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Feng Wang","raw_affiliation_strings":["CreateAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CreateAI","institution_ids":["https://openalex.org/I4210146168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070239285","display_name":"Sifeng Liu","orcid":"https://orcid.org/0000-0002-5872-9457"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["School of Artificial Intelligence, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.38864181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15194","last_page":"15204"},"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":0.9663000106811523,"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":0.9663000106811523,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.007300000172108412,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.00570000009611249,"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/autoencoder","display_name":"Autoencoder","score":0.6266000270843506},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5799999833106995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4618000090122223},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.4595000147819519},{"id":"https://openalex.org/keywords/image-translation","display_name":"Image translation","score":0.45809999108314514},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4399000108242035},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.43959999084472656},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4138000011444092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991000175476074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6486999988555908},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6266000270843506},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4618000090122223},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.4595000147819519},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.45809999108314514},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4399000108242035},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3741999864578247},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35120001435279846},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2676999866962433},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.23347","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23347","pdf_url":"https://arxiv.org/pdf/2506.23347","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.23347","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.23347","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.23347","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23347","pdf_url":"https://arxiv.org/pdf/2506.23347","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6616382615","display_name":null,"funder_award_id":"2461160308,U23B2010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8986216942","display_name":null,"funder_award_id":"2022ZD0115502","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/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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"current":[1],"conditional":[2],"autoregressive":[3,109],"image":[4,21,63,115,135,199],"generation":[5,110,151,168],"methods":[6],"have":[7],"shown":[8],"promising":[9],"results,":[10],"yet":[11],"their":[12],"potential":[13],"remains":[14],"largely":[15],"unexplored":[16],"in":[17,39,62,124,156,183],"the":[18,35,49,133,165,179],"practical":[19],"unsupervised":[20,184,198],"translation":[22,105,172,200],"domain,":[23],"which":[24,44,102],"operates":[25],"without":[26],"explicit":[27],"cross-domain":[28],"correspondences.":[29],"A":[30],"critical":[31],"limitation":[32],"stems":[33],"from":[34],"discrete":[36],"quantization":[37],"inherent":[38],"traditional":[40],"Vector":[41],"Quantization-based":[42],"frameworks,":[43],"disrupts":[45],"gradient":[46,92],"flow":[47],"between":[48],"Variational":[50],"Autoencoder":[51],"decoder":[52],"and":[53,147,189],"causal":[54],"Transformer,":[55],"impeding":[56],"end-to-end":[57],"optimization":[58],"during":[59],"adversarial":[60],"training":[61],"space.":[64],"To":[65],"tackle":[66],"this":[67,96],"issue,":[68],"we":[69,99],"propose":[70],"using":[71],"Softmax":[72],"Relaxed":[73],"Quantization,":[74],"a":[75,83,157],"novel":[76],"approach":[77],"that":[78,164,193],"reformulates":[79,103],"codebook":[80],"selection":[81],"as":[82,106,117],"continuous":[84],"probability":[85],"mixing":[86],"process":[87],"via":[88],"Softmax,":[89],"thereby":[90],"preserving":[91],"propagation.":[93],"Building":[94],"upon":[95],"differentiable":[97],"foundation,":[98],"introduce":[100],"CycleVAR,":[101],"image-to-image":[104],"image-conditional":[107],"visual":[108],"by":[111],"injecting":[112],"multi-scale":[113],"source":[114],"tokens":[116],"contextual":[118],"prompts,":[119],"analogous":[120],"to":[121,131],"prefix-based":[122],"conditioning":[123],"language":[125],"models.":[126],"CycleVAR":[127,194],"exploits":[128],"two":[129],"modes":[130],"generate":[132],"target":[134],"tokens,":[136],"including":[137],"(1)":[138],"serial":[139,180],"multi-step":[140,181],"generation,":[141],"enabling":[142],"iterative":[143],"refinement":[144],"across":[145],"scales,":[146],"(2)":[148],"parallel":[149,166],"one-step":[150,167],"synthesizing":[152],"all":[153],"resolution":[154],"outputs":[155],"single":[158],"forward":[159],"pass.":[160],"Experimental":[161],"findings":[162],"indicate":[163,192],"mode":[169,182],"attains":[170],"superior":[171],"quality":[173],"with":[174],"quicker":[175],"inference":[176],"speed":[177],"than":[178],"scenarios.":[185],"Furthermore,":[186],"both":[187],"quantitative":[188],"qualitative":[190],"results":[191],"surpasses":[195],"previous":[196],"state-of-the-art":[197],"models,":[201],"\\textit{e}.\\textit{g}.,":[202],"CycleGAN-Turbo.":[203]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}