{"id":"https://openalex.org/W4392902883","doi":"https://doi.org/10.1109/icassp48485.2024.10446603","title":"Wavelet-Guided Acceleration of Text Inversion in Diffusion-Based Image Editing","display_name":"Wavelet-Guided Acceleration of Text Inversion in Diffusion-Based Image Editing","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902883","doi":"https://doi.org/10.1109/icassp48485.2024.10446603"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093047686","display_name":"Gwanhyeong Koo","orcid":"https://orcid.org/0009-0005-6455-3223"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Gwanhyeong Koo","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea","Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058873046","display_name":"Sunjae Yoon","orcid":"https://orcid.org/0000-0001-7458-5273"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunjae Yoon","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea","Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea","Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093047686"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.963,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74417555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4380","last_page":"4384"},"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":0.9944000244140625,"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":0.9944000244140625,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9746000170707703,"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/computer-science","display_name":"Computer science","score":0.7442817091941833},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6750891208648682},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5954718589782715},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5769419074058533},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5024006366729736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4922579824924469},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.45799049735069275},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.448574423789978},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4437675476074219},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3963485658168793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15201586484909058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442817091941833},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6750891208648682},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5954718589782715},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5769419074058533},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5024006366729736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4922579824924469},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.45799049735069275},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.448574423789978},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4437675476074219},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3963485658168793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15201586484909058},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4494872504","display_name":null,"funder_award_id":"2021-0-01381","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4805667441","display_name":null,"funder_award_id":"UD230017TD","funder_id":"https://openalex.org/F4320334874","funder_display_name":"Defense Acquisition Program Administration"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320334874","display_name":"Defense Acquisition Program Administration","ror":"https://ror.org/04bjg9m96"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2765811365","https://openalex.org/W2952716587","https://openalex.org/W2964024144","https://openalex.org/W3036167779","https://openalex.org/W3121370741","https://openalex.org/W3162926177","https://openalex.org/W4224035735","https://openalex.org/W4226125322","https://openalex.org/W4281485151","https://openalex.org/W4289785045","https://openalex.org/W4298289240","https://openalex.org/W4312933868","https://openalex.org/W4318203092","https://openalex.org/W4361230700","https://openalex.org/W4378760015","https://openalex.org/W4386057725","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4390873195","https://openalex.org/W6637568146","https://openalex.org/W6755312952","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6795288823","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6841366371","https://openalex.org/W6848774630","https://openalex.org/W6850576684","https://openalex.org/W6852963699"],"related_works":["https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W4311681673","https://openalex.org/W4285230481","https://openalex.org/W4385769873","https://openalex.org/W2382174632","https://openalex.org/W4281634296","https://openalex.org/W4319161863","https://openalex.org/W2129959498","https://openalex.org/W2371687270"],"abstract_inverted_index":{"In":[0],"the":[1,14,17,25,30,52,55,59,65,69,83,96,102,111,116,131,140],"field":[2],"of":[3,16,54],"image":[4,19,60,113,152],"editing,":[5],"Null-text":[6],"Inversion":[7,104],"(NTI)":[8],"enables":[9],"fine-grained":[10],"editing":[11,61,133,153],"while":[12,57,129],"preserving":[13],"structure":[15],"original":[18,112],"by":[20,135],"optimizing":[21],"null":[22],"embeddings":[23],"during":[24,95],"DDIM":[26,97],"sampling":[27,98],"process.":[28,62,99],"However,":[29],"NTI":[31,56,128,141],"process":[32],"is":[33],"time-consuming,":[34],"taking":[35],"more":[36],"than":[37],"two":[38],"minutes":[39],"per":[40],"image.":[41],"To":[42],"address":[43],"this,":[44],"we":[45,87],"introduce":[46],"an":[47],"innovative":[48],"method":[49,144],"that":[50],"maintains":[51,124],"principles":[53],"accelerating":[58],"We":[63],"propose":[64],"WaveOpt-Estimator,":[66],"which":[67],"determines":[68],"text":[70,90,118],"optimization":[71,91],"endpoint":[72],"based":[73,154],"on":[74,155],"frequency":[75,85],"characteristics.":[76],"Utilizing":[77],"wavelet":[78],"transform":[79],"analysis":[80],"to":[81,92,127,139],"identify":[82],"image\u2019s":[84],"characteristics,":[86],"can":[88],"limit":[89],"specific":[93],"timesteps":[94],"By":[100],"adopting":[101],"Negative-Prompt":[103],"(NPI)":[105],"concept,":[106],"a":[107,146],"target":[108],"prompt":[109],"representing":[110],"serves":[114],"as":[115],"initial":[117],"value":[119],"for":[120,149],"optimization.":[121],"This":[122],"approach":[123,148],"performance":[125],"comparable":[126],"reducing":[130],"average":[132],"time":[134],"over":[136],"80%":[137],"compared":[138],"method.":[142],"Our":[143],"presents":[145],"promising":[147],"efficient,":[150],"high-quality":[151],"diffusion":[156],"models.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}