{"id":"https://openalex.org/W4403780721","doi":"https://doi.org/10.1145/3664647.3681466","title":"DiffHarmony++: Enhancing Image Harmonization with Harmony-VAE and Inverse Harmonization Model","display_name":"DiffHarmony++: Enhancing Image Harmonization with Harmony-VAE and Inverse Harmonization Model","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780721","doi":"https://doi.org/10.1145/3664647.3681466"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681466","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5002352323","display_name":"Pengfei Zhou","orcid":"https://orcid.org/0009-0008-8469-1123"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengfei Zhou","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013283012","display_name":"Fangxiang Feng","orcid":"https://orcid.org/0000-0002-4798-4233"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangxiang Feng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101545733","display_name":"Guang Liu","orcid":"https://orcid.org/0000-0002-5259-7094"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Liu","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068728736","display_name":"Ruifan Li","orcid":"https://orcid.org/0000-0002-3543-6272"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifan Li","raw_affiliation_strings":["Beijing University of Post and Telecommunication, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Post and Telecommunication, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112115197","display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0003-2015-0674"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Wang","raw_affiliation_strings":["Beijing University of Post and Telecommunication, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Post and Telecommunication, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002352323"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.5263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67024987,"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":"10592","last_page":"10601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9997000098228455,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9997000098228455,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/harmonization","display_name":"Harmonization","score":0.9408371448516846},{"id":"https://openalex.org/keywords/harmony","display_name":"Harmony (color)","score":0.7537958025932312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.557120680809021},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4468225836753845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4013023376464844},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3511802554130554},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1776764690876007},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.06884658336639404}],"concepts":[{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.9408371448516846},{"id":"https://openalex.org/C2776453491","wikidata":"https://www.wikidata.org/wiki/Q5659234","display_name":"Harmony (color)","level":2,"score":0.7537958025932312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.557120680809021},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4468225836753845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4013023376464844},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3511802554130554},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1776764690876007},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06884658336639404},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681466","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":41,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1997488488","https://openalex.org/W2083366168","https://openalex.org/W2194775991","https://openalex.org/W2960974111","https://openalex.org/W2962737447","https://openalex.org/W2995278328","https://openalex.org/W3008540959","https://openalex.org/W3034684802","https://openalex.org/W3036167779","https://openalex.org/W3097266704","https://openalex.org/W3127395526","https://openalex.org/W3169823210","https://openalex.org/W3171358896","https://openalex.org/W3171714858","https://openalex.org/W4214738329","https://openalex.org/W4225322336","https://openalex.org/W4248413939","https://openalex.org/W4255437396","https://openalex.org/W4281969232","https://openalex.org/W4287062130","https://openalex.org/W4295903508","https://openalex.org/W4304098227","https://openalex.org/W4312497550","https://openalex.org/W4312502952","https://openalex.org/W4312698476","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4312966374","https://openalex.org/W4382240897","https://openalex.org/W4385271281","https://openalex.org/W4385644314","https://openalex.org/W4385800876","https://openalex.org/W4387968695","https://openalex.org/W4390872583","https://openalex.org/W4390873054","https://openalex.org/W4390873462","https://openalex.org/W4393159139","https://openalex.org/W4399418400","https://openalex.org/W6779823529","https://openalex.org/W6843236409"],"related_works":["https://openalex.org/W2376204837","https://openalex.org/W2386707344","https://openalex.org/W2361191023","https://openalex.org/W3122413929","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068"],"abstract_inverted_index":{"Latent":[0],"diffusion":[1,27,110,137],"model":[2,28,138],"has":[3,15],"demonstrated":[4],"impressive":[5],"efficacy":[6],"in":[7,101],"image":[8,21,36,44,49,83,118],"generation":[9],"and":[10,97,129,148,168,173],"editing":[11],"tasks.":[12],"Recently,":[13],"it":[14,113],"also":[16],"promoted":[17],"the":[18,34,40,65,68,74,85,93,105,162],"advancement":[19],"of":[20,67,76,109,146,164],"harmonization.":[22],"However,":[23],"methods":[24],"involving":[25,81],"latent":[26],"all":[29],"face":[30],"a":[31,47,150],"common":[32],"challenge:":[33],"severe":[35],"distortion":[37],"introduced":[38],"by":[39],"VAE":[41],"component,":[42],"while":[43],"harmonization":[45,69,136,153,170],"is":[46],"low-level":[48],"processing":[50],"task":[51,70],"that":[52],"relies":[53],"on":[54,126,143],"pixel-level":[55],"evaluation":[56],"metrics.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"propose":[62],"Harmony-VAE,":[63],"leveraging":[64],"input":[66,80],"itself":[71],"to":[72,116,139],"enhance":[73],"quality":[75],"decoded":[77],"images.":[78],"The":[79],"composite":[82,123],"contains":[84],"precise":[86],"pixel":[87],"level":[88],"information,":[89],"which":[90],"can":[91],"complement":[92],"correct":[94],"foreground":[95,130,157],"appearance":[96],"color":[98],"information":[99],"contained":[100],"denoised":[102],"latents.":[103],"Meanwhile,":[104],"inherent":[106],"generative":[107],"nature":[108],"models":[111,175],"makes":[112],"naturally":[114],"adapt":[115],"inverse":[117,135,169],"harmonization,":[119],"i.e.":[120],"generating":[121],"synthetic":[122],"images":[124,128],"based":[125],"real":[127],"masks.":[131],"We":[132],"train":[133],"an":[134],"perform":[140],"data":[141],"augmentation":[142],"two":[144],"subsets":[145],"iHarmony4":[147],"construct":[149],"new":[151],"human":[152],"dataset":[154],"with":[155],"prominent":[156],"objects.":[158],"Extensive":[159],"experiments":[160],"demonstrate":[161],"effectiveness":[163],"our":[165],"proposed":[166],"Harmony-VAE":[167],"model.":[171],"Code":[172],"pretrained":[174],"are":[176],"available":[177],"at":[178],"https://github.com/nicecv/DiffHarmony.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}