{"id":"https://openalex.org/W7164800866","doi":"https://doi.org/10.1145/3805622.3810596","title":"SA-Edit: Accelerating Editing Models via Test-time Spatial Acceleration","display_name":"SA-Edit: Accelerating Editing Models via Test-time Spatial Acceleration","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164800866","doi":"https://doi.org/10.1145/3805622.3810596"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810596","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810596","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020435071","display_name":"Yihao Song","orcid":"https://orcid.org/0000-0002-8946-878X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihao Song","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-2743-1401","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325900","display_name":"Teng Hu","orcid":"https://orcid.org/0009-0008-1247-5931"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Hu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-1247-5931","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054879013","display_name":"Ran Yi","orcid":"https://orcid.org/0000-0003-1858-3358"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Yi","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1858-3358","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059708315","display_name":"Xiaoning Lei","orcid":"https://orcid.org/0009-0002-0518-7903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoning Lei","raw_affiliation_strings":["Contemporary Amperex Technology Co. Limited, Ningde, China"],"raw_orcid":"https://orcid.org/0009-0002-0518-7903","affiliations":[{"raw_affiliation_string":"Contemporary Amperex Technology Co. Limited, Ningde, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009598072","display_name":"Bin Sheng","orcid":"https://orcid.org/0000-0001-8678-2784"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Sheng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8678-2784","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.93296385,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1672","last_page":"1681"},"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":0.920199990272522,"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":0.920199990272522,"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":0.018400000408291817,"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/T11019","display_name":"Image Enhancement Techniques","score":0.005900000222027302,"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/acceleration","display_name":"Acceleration","score":0.7473999857902527},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6960999965667725},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5873000025749207},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5845000147819519},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5343999862670898},{"id":"https://openalex.org/keywords/aliasing","display_name":"Aliasing","score":0.5315999984741211},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5188999772071838},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5034999847412109},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.5027999877929688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950000166893005},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.7473999857902527},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6960999965667725},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5873000025749207},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5845000147819519},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5343999862670898},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.5315999984741211},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.5027999877929688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4921000003814697},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46650001406669617},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4348999857902527},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3296000063419342},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C534633266","wikidata":"https://www.wikidata.org/wiki/Q4774317","display_name":"Anti-aliasing","level":5,"score":0.2565999925136566},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810596","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810596","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W4312933868","https://openalex.org/W4386057725","https://openalex.org/W4386076215","https://openalex.org/W4390872297","https://openalex.org/W4390873195","https://openalex.org/W4404965485","https://openalex.org/W4409368325","https://openalex.org/W4413145077","https://openalex.org/W4413157724","https://openalex.org/W4415796735","https://openalex.org/W4415797645","https://openalex.org/W7110015622","https://openalex.org/W7133185348","https://openalex.org/W7160134147","https://openalex.org/W7160201328"],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"image":[1,60,108],"editing":[2,61,109],"models":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"for":[8,54,107],"generating":[9],"high-quality":[10],"results.":[11],"However,":[12],"the":[13,55,134],"iterative":[14],"inference":[15,106],"process":[16],"poses":[17],"a":[18,66,86],"significant":[19],"challenge":[20],"in":[21],"achieving":[22],"real-time":[23],"generation.":[24],"Previously":[25],"proposed":[26,140],"methods,":[27],"such":[28],"as":[29],"feature":[30],"caching":[31],"or":[32],"model":[33],"distillation,":[34],"often":[35],"require":[36],"model-specific":[37],"designs":[38],"and":[39,51,75,81,89,136],"lack":[40],"flexibility.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,64,84],"introduce":[46,85],"SA-Edit,":[47],"an":[48],"efficient,":[49],"training-free,":[50],"plug-and-play":[52],"algorithm":[53],"universal":[56],"acceleration":[57,124],"of":[58,138],"diffusion-based":[59],"models.":[62],"Specifically,":[63],"propose":[65],"spatial":[67],"scaling":[68],"strategy":[69],"to":[70,126],"reduce":[71],"redundant":[72],"latent":[73],"tokens":[74],"enhance":[76],"efficiency.":[77],"To":[78],"address":[79],"aliasing":[80],"blurring":[82],"artifacts,":[83],"score-based":[87],"filter":[88],"adaptively":[90],"refine":[91],"high-score":[92],"regions":[93],"after":[94],"each":[95],"upsampling":[96],"operation.":[97],"Our":[98],"method":[99],"achieves":[100],"at":[101],"least":[102],"4.2":[103],"\u00d7":[104],"faster":[105],"while":[110],"maintaining":[111],"high":[112],"output":[113],"quality.":[114],"Furthermore,":[115],"our":[116,139],"approach":[117],"can":[118],"be":[119],"seamlessly":[120],"integrated":[121],"with":[122],"existing":[123],"techniques":[125],"achieve":[127],"even":[128],"greater":[129],"speedups.":[130],"Extensive":[131],"experiments":[132],"demonstrate":[133],"effectiveness":[135],"efficiency":[137],"method.":[141],"The":[142],"code":[143],"is":[144],"released":[145],"at:":[146],"https://github.com/ouroboros-phy/SA-Edit":[147]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}