{"id":"https://openalex.org/W7163200387","doi":"https://doi.org/10.48550/arxiv.2606.00954","title":"COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation","display_name":"COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation","publication_year":2026,"publication_date":"2026-05-31","ids":{"openalex":"https://openalex.org/W7163200387","doi":"https://doi.org/10.48550/arxiv.2606.00954"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00954","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00954","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.00954","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137679306","display_name":"Xinlong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xinlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137636160","display_name":"Jia Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137627532","display_name":"Xiaoyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137639563","display_name":"Teng Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Teng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137636459","display_name":"Chengyu Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Chengyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137672228","display_name":"Yongchuan Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yongchuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"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":0.7408999800682068,"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":0.7408999800682068,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07699999958276749,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.043699998408555984,"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/feature","display_name":"Feature (linguistics)","score":0.5996000170707703},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5184999704360962},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46219998598098755},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44130000472068787},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4169999957084656},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.36419999599456787},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.3612000048160553},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3582000136375427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724399983882904},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5996000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5882999897003174},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5184999704360962},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3422999978065491},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3215999901294708},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00954","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00954","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"doi:10.48550/arxiv.2606.00954","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00954","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Achieving":[0],"high-fidelity":[1],"object-level":[2,23,61,83,137],"control":[3,37],"in":[4],"Diffusion":[5],"Transformers":[6],"remains":[7],"a":[8,55,103,110,130],"significant":[9],"challenge":[10],"despite":[11],"the":[12,64,71,96,117,125,142,154],"introduction":[13],"of":[14],"structural":[15],"priors":[16],"like":[17],"depth":[18],"and":[19,32,156,172],"Canny":[20],"maps.":[21],"Current":[22],"conditional":[24],"generation":[25,144],"methods":[26,166],"frequently":[27],"suffer":[28],"from":[29],"visual":[30],"artifacts":[31],"struggle":[33],"to":[34,77,114],"maintain":[35],"precise":[36],"over":[38],"objects":[39],"within":[40],"small":[41],"localized":[42],"regions.":[43],"To":[44,91],"address":[45,78],"these":[46,94],"limitations,":[47],"we":[48,69],"propose":[49,70],"Cascaded":[50],"Object-Level":[51],"Latent":[52],"Refinement":[53],"(COLLAR),":[54],"training-free":[56],"framework":[57],"that":[58,136,160],"progressively":[59],"optimizes":[60],"features":[62,84,138],"via":[63,88],"Field-of-View":[65],"(FoV)":[66],"expansion.":[67],"First,":[68],"Cross-Scale":[72],"Semantic":[73],"Alignment":[74],"(CSSA)":[75],"module":[76,101],"spatial-semantic":[79],"gaps":[80],"by":[81],"injecting":[82],"into":[85,141],"extended-FoV":[86,126],"branches":[87],"attention":[89],"mechanisms.":[90],"further":[92],"optimize":[93],"features,":[95],"Cyclic":[97],"Feature":[98],"Injection":[99],"(CFI)":[100],"introduces":[102],"reciprocal":[104],"background":[105],"feedback":[106],"mechanism.":[107],"It":[108],"leverages":[109],"frequency-based":[111],"adaptive":[112],"strategy":[113],"selectively":[115],"update":[116],"global":[118,143],"backbone":[119],"with":[120],"context-aligned":[121],"local":[122],"information.":[123],"Finally,":[124],"branch":[127],"serves":[128],"as":[129],"hub":[131],"for":[132],"feature":[133],"optimization,":[134],"ensuring":[135],"are":[139],"integrated":[140],"process":[145],"without":[146],"compromising":[147],"final":[148],"image":[149,170],"quality.":[150],"Extensive":[151],"experiments":[152],"on":[153],"COCO-MIG":[155],"COCO-POS":[157],"benchmarks":[158],"demonstrate":[159],"our":[161],"approach":[162],"consistently":[163],"outperforms":[164],"state-of-the-art":[165],"across":[167],"semantic":[168],"alignment,":[169],"quality,":[171],"spatial":[173],"fidelity.":[174]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}