{"id":"https://openalex.org/W4409262827","doi":"https://doi.org/10.1109/wacv61041.2025.00083","title":"Fine-Tuning Image-Conditional Diffusion Models is Easier than you Think","display_name":"Fine-Tuning Image-Conditional Diffusion Models is Easier than you Think","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4409262827","doi":"https://doi.org/10.1109/wacv61041.2025.00083"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61041.2025.00083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61041.2025.00083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.tue.nl/ws/files/357133114/Fine-Tuning_Image-Conditional_Diffusion_Models_is_Easier_than_you_Think_1_.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111868737","display_name":"Glenn Garcia","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Gonzalo Martin Garcia","raw_affiliation_strings":["RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044241033","display_name":"Karim Abou Zeid","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Karim Abou Zeid","raw_affiliation_strings":["RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103544331","display_name":"Christian Schmidt","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Schmidt","raw_affiliation_strings":["RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061463972","display_name":"Daan de Geus","orcid":"https://orcid.org/0000-0003-0559-5341"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daan De Geus","raw_affiliation_strings":["RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071563379","display_name":"Alexander Hermans","orcid":"https://orcid.org/0000-0003-2127-0782"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Hermans","raw_affiliation_strings":["RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071006649","display_name":"Bastian Leibe","orcid":"https://orcid.org/0000-0003-4225-0051"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bastian Leibe","raw_affiliation_strings":["RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5111868737"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":14.262,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.99078846,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"753","last_page":"762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.7268000245094299,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.7268000245094299,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6452233791351318},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5518471002578735},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5453336834907532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4256453514099121},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37631845474243164},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.34615635871887207},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08678919076919556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6452233791351318},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5518471002578735},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5453336834907532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4256453514099121},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37631845474243164},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.34615635871887207},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08678919076919556},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wacv61041.2025.00083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61041.2025.00083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/bf3fb415-6059-4e06-8351-31728a73ef35","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/bf3fb415-6059-4e06-8351-31728a73ef35","pdf_url":"https://pure.tue.nl/ws/files/357133114/Fine-Tuning_Image-Conditional_Diffusion_Models_is_Easier_than_you_Think_1_.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Martin Garcia, G, Abou Zeid, K, Schmidt, C, de Geus, D, Hermans, A & Leibe, B 2025, Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think. in 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025., 10943344, Institute of Electrical and Electronics Engineers, pp. 753-762, 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, United States, 26/02/25. https://doi.org/10.1109/WACV61041.2025.00083","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/bf3fb415-6059-4e06-8351-31728a73ef35","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/bf3fb415-6059-4e06-8351-31728a73ef35","pdf_url":"https://pure.tue.nl/ws/files/357133114/Fine-Tuning_Image-Conditional_Diffusion_Models_is_Easier_than_you_Think_1_.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Martin Garcia, G, Abou Zeid, K, Schmidt, C, de Geus, D, Hermans, A & Leibe, B 2025, Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think. in 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025., 10943344, Institute of Electrical and Electronics Engineers, pp. 753-762, 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, United States, 26/02/25. https://doi.org/10.1109/WACV61041.2025.00083","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320324232","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409262827.pdf","grobid_xml":"https://content.openalex.org/works/W4409262827.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1513100184","https://openalex.org/W1899309388","https://openalex.org/W2125310925","https://openalex.org/W2150066425","https://openalex.org/W2151996626","https://openalex.org/W2594519801","https://openalex.org/W2741885505","https://openalex.org/W2962809185","https://openalex.org/W2963760790","https://openalex.org/W3097660860","https://openalex.org/W3174458495","https://openalex.org/W3199238138","https://openalex.org/W3203887644","https://openalex.org/W4214520160","https://openalex.org/W4312388311","https://openalex.org/W4312933868","https://openalex.org/W4390871919","https://openalex.org/W4390873429","https://openalex.org/W4394625831","https://openalex.org/W4395481595","https://openalex.org/W4402727115","https://openalex.org/W4402727359","https://openalex.org/W4402733585","https://openalex.org/W4402753888","https://openalex.org/W4402753900","https://openalex.org/W4402754301","https://openalex.org/W4403947105","https://openalex.org/W6639633739","https://openalex.org/W6750474155","https://openalex.org/W6757817989","https://openalex.org/W6779823529","https://openalex.org/W6782298681","https://openalex.org/W6783713337","https://openalex.org/W6791436909","https://openalex.org/W6809884996","https://openalex.org/W6838452192","https://openalex.org/W6846539466","https://openalex.org/W6849845829","https://openalex.org/W6853818442","https://openalex.org/W6854302227","https://openalex.org/W6862238593"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"work":[1],"showed":[2],"that":[3,51,64,111,128],"large":[4],"diffusion":[5],"models":[6,120],"can":[7],"be":[8],"reused":[9],"as":[10,20],"highly":[11],"precise":[12],"monocular":[13],"depth":[14,18,116,146],"estimators":[15],"by":[16,57],"casting":[17],"estimation":[19,119,149],"an":[21],"image-conditional":[22],"image":[23],"generation":[24],"task.":[25],"While":[26],"the":[27,52,61,76,100,156],"proposed":[28],"model":[29,72,102,110],"achieved":[30],"state-of-the-art":[31,144],"results,":[32],"high":[33],"computational":[34],"demands":[35],"due":[36],"to":[37,75,142],"multi-step":[38],"inference":[39,62],"limited":[40],"its":[41],"use":[42],"in":[43,60],"many":[44],"scenarios.":[45],"In":[46],"this":[47,129],"paper,":[48],"we":[49,93],"show":[50],"perceived":[53],"inefficiency":[54],"was":[55],"caused":[56],"a":[58,108],"flaw":[59],"pipeline":[63],"has":[65],"so":[66],"far":[67],"gone":[68],"unnoticed.":[69],"The":[70],"fixed":[71],"performs":[73],"comparably":[74],"best":[77],"previously":[78],"reported":[79],"configuration":[80],"while":[81],"being":[82],"more":[83],"than":[84],"200x":[85],"faster.":[86],"To":[87],"optimize":[88],"for":[89],"downstream":[90],"task":[91],"performance,":[92],"perform":[94],"end-to-end":[95],"fine-tuning":[96,130],"on":[97,121,135],"top":[98],"of":[99,155],"single-step":[101],"with":[103],"task-specific":[104],"losses":[105],"and":[106,117,138,147],"get":[107],"deterministic":[109],"outperforms":[112],"all":[113],"other":[114],"diffusion-based":[115,145],"normal":[118,148],"common":[122],"zero-shot":[123],"benchmarks.":[124],"We":[125],"surprisingly":[126],"find":[127],"protocol":[131],"also":[132],"works":[133],"directly":[134],"Stable":[136],"Diffusion":[137],"achieves":[139],"comparable":[140],"performance":[141],"current":[143],"models,":[150],"calling":[151],"into":[152],"question":[153],"some":[154],"conclusions":[157],"drawn":[158],"from":[159],"prior":[160],"works.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}