{"id":"https://openalex.org/W7164047529","doi":"https://doi.org/10.1145/3748522.3779967","title":"Analyzing Coarse-to-fine Generation of Diffusion Models through Image Editing Perspectives","display_name":"Analyzing Coarse-to-fine Generation of Diffusion Models through Image Editing Perspectives","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7164047529","doi":"https://doi.org/10.1145/3748522.3779967"},"language":null,"primary_location":{"id":"doi:10.1145/3748522.3779967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779967","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3748522.3779967","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103156774","display_name":"Seonggyeom Kim","orcid":"https://orcid.org/0009-0006-8506-969X"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seonggyeom Kim","raw_affiliation_strings":["Hanyang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0006-8506-969X","affiliations":[{"raw_affiliation_string":"Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017852846","display_name":"M Kyoo Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minju Kim","raw_affiliation_strings":["Hanyang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0009-6832-5921","affiliations":[{"raw_affiliation_string":"Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111023367","display_name":"Minju Bang","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minju Bang","raw_affiliation_strings":["Hanyang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-7334-2485","affiliations":[{"raw_affiliation_string":"Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036440250","display_name":"Dong\u2010Kyu Chae","orcid":"https://orcid.org/0000-0002-5410-6391"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Kyu Chae","raw_affiliation_strings":["Computer Science, Hanyang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-5410-6391","affiliations":[{"raw_affiliation_string":"Computer Science, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103156774"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.96125796,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1020","last_page":"1028"},"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":0.9395999908447266,"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":0.9395999908447266,"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":0.013100000098347664,"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":0.00419999985024333,"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/focus","display_name":"Focus (optics)","score":0.659600019454956},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.656000018119812},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5583000183105469},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5529999732971191},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5340999960899353},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49869999289512634},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4374000132083893},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43160000443458557},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4043000042438507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336999773979187},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.659600019454956},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.656000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5638999938964844},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5583000183105469},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5529999732971191},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5340999960899353},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49869999289512634},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42899999022483826},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4043000042438507},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3675000071525574},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34389999508857727},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.3276999890804291},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32690000534057617},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3748522.3779967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779967","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3748522.3779967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779967","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W1849277567","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2963749936","https://openalex.org/W3034600949","https://openalex.org/W3096831136","https://openalex.org/W3102061158","https://openalex.org/W3176913662","https://openalex.org/W3191805365","https://openalex.org/W3216352822","https://openalex.org/W3217030260","https://openalex.org/W4214827287","https://openalex.org/W4230421069","https://openalex.org/W4312824283","https://openalex.org/W4312933868","https://openalex.org/W4385527149","https://openalex.org/W4386083151","https://openalex.org/W4390874580","https://openalex.org/W7133185348","https://openalex.org/W7133218093","https://openalex.org/W7133226442"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"models":[1,153],"involve":[2],"a":[3,8,75,89,134],"forward":[4],"noising":[5],"process":[6,15],"and":[7,30,80,105,122],"reverse":[9],"denoising":[10],"process.":[11],"Their":[12],"diffusion-like":[13],"sampling":[14],"have":[16],"an":[17,54,166],"intrinsic":[18],"nature":[19],"of":[20,48,74,77,120,149,196],"coarse-to-fine":[21,63],"generation":[22],"(i.e.,":[23],"the":[24,31,60,71,84,94,114,127,142,183,194],"initial":[25],"stages":[26,33],"build":[27],"coarse-grained":[28],"outlines":[29],"latter":[32],"focus":[34],"on":[35,93,118,147,170,189],"fine":[36],"details),":[37],"which":[38,177],"has":[39],"been":[40],"implicitly":[41],"demonstrated":[42],"in":[43],"prior":[44,85],"works.":[45],"The":[46],"goal":[47],"this":[49],"work":[50],"is":[51,178,201],"to":[52],"present":[53],"analysis":[55,86,110,138],"method":[56,139],"that":[57,69,87],"explicitly":[58],"reveals":[59],"diffusion":[61,152],"models'":[62],"behavior,":[64],"through":[65],"conducting":[66],"image":[67,143,185],"editing":[68,144,186],"mixes":[70],"latent":[72,124],"features":[73,125],"pair":[76],"samples":[78],"(source":[79],"reference).":[81],"Different":[82],"from":[83],"defined":[88],"specific":[90],"stage":[91],"based":[92,117,169],"step":[95],"number":[96],"T":[97],"(e.g.,":[98],"fine:":[99],"[0,":[100],"333],":[101],"medium:":[102],"[333,":[103],"666],":[104],"coarse:":[106],"[666,":[107],"999]),":[108],"our":[109,137,197],"more":[111,179],"carefully":[112],"partitions":[113],"generative":[115],"sequence":[116],"variation":[119],"noise":[121],"U-Net":[123],"during":[126],"sequence.":[128],"We":[129],"then":[130],"show":[131,193],"that,":[132],"with":[133],"few":[135],"modifications,":[136],"can":[140],"perform":[141],"task":[145],"working":[146],"top":[148],"existing":[150],"pre-trained":[151],"while":[154],"allowing":[155],"controllability,":[156],"without":[157],"any":[158],"additional":[159],"training":[160],"or":[161],"fine-tuning.":[162],"Finally,":[163],"we":[164],"propose":[165],"extended":[167],"metric":[168],"LPIPS":[171],"(Learned":[172],"Perceptual":[173],"Image":[174],"Patch":[175],"Similarity),":[176],"suitable":[180],"for":[181],"evaluating":[182],"controllable":[184],"task.":[187],"Experiments":[188],"several":[190],"widely-used":[191],"benchmarks":[192],"effectiveness":[195],"method.":[198],"Our":[199],"code":[200],"available":[202],"at:":[203],"https://github.com/gyeomo/Coarse-to-fine_Generation_of_Diffusion":[204]},"counts_by_year":[],"updated_date":"2026-06-10T14:10:52.464848","created_date":"2026-06-10T00:00:00"}