{"id":"https://openalex.org/W4402979349","doi":"https://doi.org/10.1109/icme57554.2024.10687566","title":"Unified Diffusion-Based Rigid and Non-Rigid Editing with Text and Image Guidance","display_name":"Unified Diffusion-Based Rigid and Non-Rigid Editing with Text and Image Guidance","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979349","doi":"https://doi.org/10.1109/icme57554.2024.10687566"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5115694939","display_name":"Jiacheng Wang","orcid":"https://orcid.org/0009-0002-3109-3468"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiacheng Wang","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100646646","display_name":"Ping Liu","orcid":"https://orcid.org/0000-0002-1488-1668"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Liu","raw_affiliation_strings":["University of Nevada,Department of Computer Science and Engineering,Reno"],"affiliations":[{"raw_affiliation_string":"University of Nevada,Department of Computer Science and Engineering,Reno","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100738462","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0003-0816-6016"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115694939"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.7326,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7307973,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12162","display_name":"Cellular Automata and Applications","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13999","display_name":"Digital Rights Management and Security","score":0.9458000063896179,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.6096294522285461},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5306070446968079},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5215213894844055},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4808414876461029},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.48012733459472656},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4128369092941284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40411972999572754},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12496054172515869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6096294522285461},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5306070446968079},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5215213894844055},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4808414876461029},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.48012733459472656},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4128369092941284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40411972999572754},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12496054172515869},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2603777577","https://openalex.org/W3216352822","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4386057725","https://openalex.org/W4386075631","https://openalex.org/W4386113271","https://openalex.org/W4390873195","https://openalex.org/W4394596927","https://openalex.org/W4400582187"],"related_works":["https://openalex.org/W4311681673","https://openalex.org/W4319453795","https://openalex.org/W4205104112","https://openalex.org/W1974870326","https://openalex.org/W2770776392","https://openalex.org/W3176454756","https://openalex.org/W2772330423","https://openalex.org/W3163523050","https://openalex.org/W3006381446","https://openalex.org/W4386301887"],"abstract_inverted_index":{"Existing":[0],"text-to-image":[1],"editing":[2,12,46,73,135],"methods":[3],"tend":[4],"to":[5,70,99,104],"excel":[6],"either":[7,58],"in":[8,20,113,133],"rigid":[9,52,142],"or":[10,61,130],"non-rigid":[11,54,144],"but":[13],"encounter":[14],"challenges":[15],"when":[16],"combining":[17],"both,":[18],"resulting":[19],"misaligned":[21],"outputs":[22],"with":[23],"the":[24,123],"provided":[25],"text":[26],"prompts.":[27],"In":[28],"addition,":[29],"integrating":[30],"reference":[31,62],"images":[32],"for":[33,81],"control":[34],"remains":[35],"challenging.":[36],"To":[37,88],"address":[38],"these":[39],"issues,":[40],"we":[41,93],"present":[42],"a":[43,66,110],"versatile":[44,117],"image":[45,118],"framework":[47],"capable":[48],"of":[49,83,125],"executing":[50],"both":[51,141],"and":[53,75,85,116,136,143],"edits,":[55],"guided":[56],"by":[57],"textual":[59],"prompts":[60],"images.":[63],"We":[64],"leverage":[65],"dual-path":[67],"injection":[68],"scheme":[69],"handle":[71],"diverse":[72],"scenarios":[74],"introduce":[76],"an":[77],"integrated":[78],"self-attention":[79],"mechanism":[80],"fusion":[82,97],"appearance":[84,137],"structural":[86],"information.":[87],"mitigate":[89],"potential":[90],"visual":[91],"artifacts,":[92],"further":[94],"employ":[95],"latent":[96],"techniques":[98],"adjust":[100],"intermediate":[101],"latents.":[102],"Compared":[103],"previous":[105],"work,":[106],"our":[107,126],"approach":[108],"represents":[109],"significant":[111],"advance":[112],"achieving":[114],"precise":[115],"editing.":[119],"Comprehensive":[120],"experiments":[121],"validate":[122],"efficacy":[124],"method,":[127],"showcasing":[128],"competitive":[129],"superior":[131],"results":[132],"text-based":[134],"transfer":[138],"tasks,":[139],"encompassing":[140],"settings.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}
