{"id":"https://openalex.org/W7160332716","doi":"https://doi.org/10.48550/arxiv.2605.02152","title":"SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking","display_name":"SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7160332716","doi":"https://doi.org/10.48550/arxiv.2605.02152"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.02152","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02152","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.2605.02152","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135326894","display_name":"Zhengan Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Zhengan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044126187","display_name":"Shikang Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Shikang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101558909","display_name":"Haoran Qin","orcid":"https://orcid.org/0009-0008-4784-0943"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135311180","display_name":"Xiaobing Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Xiaobing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135316927","display_name":"Yinggui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yinggui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135309045","display_name":"Jiacheng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiacheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135380935","display_name":"Jiaxuan Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Jiaxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135338905","display_name":"Yuqi Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Yuqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135339646","display_name":"Peiliang Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Peiliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135375941","display_name":"Jinkui Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Jinkui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062995314","display_name":"Xiantao Zhang","orcid":"https://orcid.org/0000-0002-3795-3556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiantao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135285442","display_name":"Linfeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Linfeng","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":0.8008000254631042,"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":0.8008000254631042,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.0640999972820282,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.007499999832361937,"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/upsampling","display_name":"Upsampling","score":0.7441999912261963},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5824000239372253},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5670999884605408},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5580999851226807},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5428000092506409},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5284000039100647},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5040000081062317},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.47269999980926514},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4410000145435333},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4251999855041504}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8023999929428101},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7441999912261963},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5824000239372253},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5670999884605408},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5580999851226807},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44769999384880066},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4410000145435333},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4154999852180481},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39820000529289246},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3668999969959259},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C173642442","wikidata":"https://www.wikidata.org/wiki/Q1253346","display_name":"Decimation","level":3,"score":0.3528999984264374},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.26930001378059387},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.02152","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02152","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.2605.02152","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02152","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"image":[1,93],"editing":[2,52],"offers":[3],"strong":[4,144],"semantic":[5,69,106],"controllability,":[6],"but":[7],"remains":[8],"computationally":[9],"expensive":[10],"due":[11],"to":[12,57,114,137,149,158],"iterative":[13],"high-resolution":[14,77,119],"denoising":[15],"over":[16],"all":[17],"spatial":[18,61],"tokens.":[19],"Dynamic-resolution":[20],"sampling":[21],"reduces":[22],"this":[23],"cost":[24],"by":[25],"performing":[26],"early":[27],"steps":[28],"at":[29,126],"reduced":[30],"resolution.":[31,129],"However,":[32],"existing":[33,164],"approaches":[34],"prioritize":[35],"upsampling":[36],"using":[37],"low-level":[38],"heuristics":[39],"such":[40],"as":[41],"edge":[42],"detection":[43],"or":[44],"channel":[45],"variance,":[46],"which":[47,109],"are":[48,63,112],"weakly":[49],"aligned":[50],"with":[51,163],"semantics":[53],"and":[54,79,133,139,152,172],"may":[55],"lead":[56],"structural":[58],"inconsistency.":[59],"Moreover,":[60],"regions":[62],"often":[64],"upsampled":[65],"without":[66],"verifying":[67],"whether":[68],"modification":[70],"is":[71,147,168],"actually":[72],"required,":[73],"resulting":[74],"in":[75,169],"redundant":[76],"computation":[78],"accumulated":[80],"errors.":[81],"Therefore,":[82],"we":[83],"propose":[84],"SpecEdit,":[85],"a":[86,97,100,127],"training-free":[87],"dynamic-resolution":[88],"framework":[89],"tailored":[90],"for":[91,118],"diffusion-based":[92],"editing.":[94],"SpecEdit":[95,146],"follows":[96],"draft-and-verify":[98],"scheme:":[99],"low-resolution":[101],"draft":[102],"first":[103],"estimates":[104],"the":[105,122],"outcome,":[107],"after":[108],"token-level":[110],"discrepancies":[111],"used":[113],"identify":[115],"edit-relevant":[116],"tokens":[117,124],"denoising,":[120],"while":[121,142],"remaining":[123],"stay":[125],"coarse":[128],"Experiments":[130],"on":[131,176],"Qwen-Image-Edit":[132],"FLUX.1-Kontext-dev":[134],"demonstrate":[135],"up":[136,157],"10x":[138],"7x":[140],"acceleration,":[141],"maintaining":[143],"quality.":[145],"complementary":[148],"step":[150],"distillation":[151],"other":[153],"acceleration":[154],"techniques,":[155],"achieving":[156],"13x":[159],"speedup":[160],"when":[161],"combined":[162],"methods.":[165],"Our":[166],"code":[167],"supplementary":[170],"material":[171],"will":[173],"be":[174],"released":[175],"GitHub.":[177]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-06T00:00:00"}