{"id":"https://openalex.org/W7119539934","doi":"https://doi.org/10.48550/arxiv.2601.03391","title":"Edit2Restore:Few-Shot Image Restoration via Parameter-Efficient Adaptation of Pre-trained Editing Models","display_name":"Edit2Restore:Few-Shot Image Restoration via Parameter-Efficient Adaptation of Pre-trained Editing Models","publication_year":2026,"publication_date":"2026-01-06","ids":{"openalex":"https://openalex.org/W7119539934","doi":"https://doi.org/10.48550/arxiv.2601.03391"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.03391","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03391","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":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.2601.03391","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122335117","display_name":"M. Ak\u0131n Y\u0131lmaz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Y\u0131lmaz, M. Ak\u0131n","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093939655","display_name":"Ahmet Bilican","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bilican, Ahmet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108319827","display_name":"Burak Can Biner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biner, Burak Can","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122358229","display_name":"A. Murat Tekalp","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tekalp, A. Murat","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":0.6437000036239624,"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":0.6437000036239624,"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":0.15629999339580536,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.12700000405311584,"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/image-restoration","display_name":"Image restoration","score":0.6969000101089478},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5644000172615051},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5284000039100647},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4438000023365021},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4214000105857849},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3935999870300293},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.38199999928474426},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.36000001430511475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354000210762024},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.6969000101089478},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5644000172615051},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5151000022888184},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3952000141143799},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3553999960422516},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3370000123977661},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.03391","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03391","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":"doi:10.48550/arxiv.2601.03391","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03391","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.7303762435913086,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"restoration":[1,35,77,85,148,202],"has":[2],"traditionally":[3],"required":[4],"training":[5,144],"specialized":[6,84],"models":[7,28],"on":[8,49,121,147],"thousands":[9,90],"of":[10,91,143,161],"paired":[11,65],"examples":[12],"per":[13,67],"degradation":[14],"type.":[15],"We":[16],"challenge":[17],"this":[18],"paradigm":[19],"by":[20,70],"demonstrating":[21],"that":[22,74,82,185],"powerful":[23],"pre-trained":[24,103,186],"text-conditioned":[25],"image":[26,187,201,210],"editing":[27,104,188],"can":[29],"be":[30],"efficiently":[31],"adapted":[32],"for":[33,59,207],"multiple":[34,127],"tasks":[36],"through":[37],"parameter-efficient":[38],"fine-tuning":[39],"with":[40,89],"remarkably":[41],"few":[42],"examples.":[43],"Our":[44],"approach":[45],"fine-tunes":[46],"LoRA":[47,118],"adapters":[48],"FLUX.1":[50],"Kontext,":[51],"a":[52,194],"state-of-the-art":[53],"12B":[54],"parameter":[55],"flow":[56],"matching":[57],"model":[58],"image-to-image":[60],"translation,":[61],"using":[62],"only":[63],"16-128":[64],"images":[66],"task,":[68],"guided":[69],"simple":[71],"text":[72,123,162],"prompts":[73],"specify":[75],"the":[76,95,141,159],"operation.":[78],"Unlike":[79],"existing":[80],"methods":[81],"train":[83],"networks":[86],"from":[87],"scratch":[88],"samples,":[92],"we":[93,138],"leverage":[94],"rich":[96],"visual":[97],"priors":[98],"already":[99],"encoded":[100],"in":[101],"large-scale":[102],"models,":[105,189],"dramatically":[106],"reducing":[107],"data":[108],"requirements":[109],"while":[110],"maintaining":[111],"high":[112],"perceptual":[113,174],"quality.":[114],"A":[115],"single":[116],"unified":[117,155],"adapter,":[119],"conditioned":[120],"task-specific":[122,153],"prompts,":[124],"effectively":[125],"handles":[126],"degradations":[128],"including":[129],"denoising,":[130],"deraining,":[131],"and":[132,165,196],"dehazing.":[133],"Through":[134],"comprehensive":[135],"ablation":[136],"studies,":[137],"analyze:":[139],"(i)":[140],"impact":[142],"set":[145],"size":[146],"quality,":[149],"(ii)":[150],"trade-offs":[151],"between":[152],"versus":[154],"multi-task":[156],"adapters,":[157],"(iii)":[158],"role":[160],"encoder":[163],"fine-tuning,":[164],"(iv)":[166],"zero-shot":[167],"baseline":[168],"performance.":[169],"While":[170],"our":[171,182,216],"method":[172],"prioritizes":[173],"quality":[175],"over":[176],"pixel-perfect":[177],"reconstruction":[178],"metrics":[179],"like":[180],"PSNR/SSIM,":[181],"results":[183,217],"demonstrate":[184],"when":[190],"properly":[191],"adapted,":[192],"offer":[193],"compelling":[195],"data-efficient":[197],"alternative":[198],"to":[199,214],"traditional":[200],"approaches,":[203],"opening":[204],"new":[205],"avenues":[206],"few-shot,":[208],"prompt-guided":[209],"enhancement.":[211],"The":[212],"code":[213],"reproduce":[215],"are":[218],"available":[219],"at:":[220],"https://github.com/makinyilmaz/Edit2Restore":[221]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-01-09T00:00:00"}