{"id":"https://openalex.org/W7123335459","doi":"https://doi.org/10.1109/access.2026.3653450","title":"Stepwise Attention Control for Training-Free Image Editing","display_name":"Stepwise Attention Control for Training-Free Image Editing","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123335459","doi":"https://doi.org/10.1109/access.2026.3653450"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3653450","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3653450","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3653450","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122868125","display_name":"Geon-Chan Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Geon-Chan Choi","raw_affiliation_strings":["Department of Information and Communications Engineering, Sejong University, Gwangjin-gu, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Information and Communications Engineering, Sejong University, Gwangjin-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122865861","display_name":"Jong-Ki Han","orcid":null},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong-Ki Han","raw_affiliation_strings":["Department of AI Convergence Electronics Engineering, Sejong University, Gwangjin-gu, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of AI Convergence Electronics Engineering, Sejong University, Gwangjin-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5122868125"],"corresponding_institution_ids":["https://openalex.org/I28777354"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06880455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"8789","last_page":"8799"},"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":0.9453999996185303,"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":0.9453999996185303,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.005499999970197678,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.00279999990016222,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.7300999760627747},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6431999802589417},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.546500027179718},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5164999961853027},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48100000619888306},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.47699999809265137},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46630001068115234},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4580000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8895999789237976},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.7300999760627747},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6431999802589417},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.546500027179718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5404999852180481},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4832000136375427},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48100000619888306},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3504999876022339},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2680000066757202},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3653450","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3653450","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3653450","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3653450","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321287","display_name":"Sejong University","ror":"https://ror.org/00aft1q37"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2194775991","https://openalex.org/W2962785568","https://openalex.org/W4286611278","https://openalex.org/W4312872987","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4390872636","https://openalex.org/W4390873784","https://openalex.org/W4391769166","https://openalex.org/W4394597158","https://openalex.org/W4394597404","https://openalex.org/W4394625750","https://openalex.org/W4402715857","https://openalex.org/W4402727249","https://openalex.org/W4402775818","https://openalex.org/W4413146475"],"related_works":[],"abstract_inverted_index":{"Text-conditioned":[0],"image":[1,40,159],"editing":[2,81,135],"aims":[3],"to":[4,116,161],"modify":[5],"visual":[6],"content":[7],"based":[8,104],"on":[9,105],"natural":[10],"language":[11],"prompts":[12],"while":[13,149],"preserving":[14,64],"the":[15,19,65,71,75,98,106,127,134,141,153,157],"spatial":[16],"structure":[17,68],"of":[18,74,125,156],"input":[20,66],"image.":[21],"This":[22,119],"capability":[23],"plays":[24],"a":[25,51,89],"vital":[26],"role":[27],"in":[28,54,79],"applications":[29],"such":[30],"as":[31],"creative":[32],"media":[33],"design,":[34],"virtual":[35],"scene":[36],"generation,":[37],"and":[38,47,69,110,130],"interactive":[39],"manipulation.":[41],"However,":[42],"achieving":[43],"both":[44,126],"semantic":[45,72,131,147],"fidelity":[46,129],"structural":[48,128,154],"preservation":[49],"remains":[50],"major":[52],"challenge":[53],"diffusion-based":[55],"approaches.":[56],"Many":[57],"existing":[58,162],"methods":[59],"exhibit":[60],"an":[61],"imbalance":[62],"between":[63],"image\u2019s":[67],"reflecting":[70],"intent":[73],"prompt,":[76],"often":[77],"resulting":[78],"suboptimal":[80],"outcomes.":[82],"To":[83],"address":[84],"this":[85],"problem,":[86],"we":[87],"propose":[88],"training-free":[90],"method":[91,143],"called":[92],"Stepwise":[93],"Attention":[94],"Control,":[95],"which":[96],"divides":[97],"denoising":[99],"process":[100],"into":[101],"four":[102],"stages":[103],"diffusion":[107],"time":[108],"step":[109],"applies":[111],"tailored":[112],"attention":[113],"control":[114,124],"strategies":[115],"each":[117],"stage.":[118],"stage-wise":[120],"approach":[121],"enables":[122],"balanced":[123],"consistency":[132],"during":[133],"process.":[136],"Experimental":[137],"results":[138],"demonstrate":[139],"that":[140],"proposed":[142],"achieves":[144],"more":[145,150],"faithful":[146],"edits":[148],"effectively":[151],"retaining":[152],"features":[155],"original":[158],"compared":[160],"techniques.":[163]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}