{"id":"https://openalex.org/W4385644314","doi":"https://doi.org/10.1145/3581783.3612451","title":"Painterly Image Harmonization using Diffusion Model","display_name":"Painterly Image Harmonization using Diffusion Model","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385644314","doi":"https://doi.org/10.1145/3581783.3612451"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612451","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.02228","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101529009","display_name":"Lingxiao Lu","orcid":"https://orcid.org/0009-0007-6975-9620"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lingxiao Lu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-6975-9620","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047636121","display_name":"Jiangtong Li","orcid":"https://orcid.org/0000-0003-3873-4053"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangtong Li","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3873-4053","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101643442","display_name":"Junyan Cao","orcid":"https://orcid.org/0009-0003-0301-1549"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyan Cao","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-0301-1549","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032618817","display_name":"Li Niu","orcid":"https://orcid.org/0000-0003-1970-8634"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Niu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1970-8634","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741568","display_name":"Liqing Zhang","orcid":"https://orcid.org/0000-0001-7597-8503"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqing Zhang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7597-8503","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101529009"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.2372,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90042024,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"233","last_page":"241"},"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":0.9994999766349792,"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":0.9994999766349792,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9991000294685364,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9955999851226807,"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":0.7922073602676392},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6020417213439941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5095980167388916},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4446898102760315},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4335331320762634},{"id":"https://openalex.org/keywords/harmonization","display_name":"Harmonization","score":0.4305707514286041},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3535175919532776},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13701888918876648}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922073602676392},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6020417213439941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5095980167388916},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4446898102760315},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4335331320762634},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.4305707514286041},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3535175919532776},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13701888918876648},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612451","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.02228","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.02228","pdf_url":"https://arxiv.org/pdf/2308.02228","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.02228","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.02228","pdf_url":"https://arxiv.org/pdf/2308.02228","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G5660070723","display_name":null,"funder_award_id":"62076162","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385644314.pdf","grobid_xml":"https://content.openalex.org/works/W4385644314.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2331128040","https://openalex.org/W2339754110","https://openalex.org/W2465552163","https://openalex.org/W2475287302","https://openalex.org/W2476548250","https://openalex.org/W2583638424","https://openalex.org/W2603777577","https://openalex.org/W2604130399","https://openalex.org/W2617602381","https://openalex.org/W2763110165","https://openalex.org/W2944279536","https://openalex.org/W2960974111","https://openalex.org/W2963245902","https://openalex.org/W2969803502","https://openalex.org/W2969810168","https://openalex.org/W2982014123","https://openalex.org/W2982695696","https://openalex.org/W3008540959","https://openalex.org/W3009134234","https://openalex.org/W3022021927","https://openalex.org/W3024169794","https://openalex.org/W3034684802","https://openalex.org/W3036167779","https://openalex.org/W3094502228","https://openalex.org/W3096831136","https://openalex.org/W3121370741","https://openalex.org/W3127395526","https://openalex.org/W3166396011","https://openalex.org/W3169823210","https://openalex.org/W3171358896","https://openalex.org/W3171714858","https://openalex.org/W3173657020","https://openalex.org/W3193917007","https://openalex.org/W3202767484","https://openalex.org/W3212516020","https://openalex.org/W3213331968","https://openalex.org/W4214738329","https://openalex.org/W4214897085","https://openalex.org/W4225322336","https://openalex.org/W4226125322","https://openalex.org/W4226148126","https://openalex.org/W4287029626","https://openalex.org/W4287163461","https://openalex.org/W4287250395","https://openalex.org/W4294375521","https://openalex.org/W4300979859","https://openalex.org/W4304098227","https://openalex.org/W4309957652","https://openalex.org/W4312365264","https://openalex.org/W4312497550","https://openalex.org/W4312698476","https://openalex.org/W4312926745","https://openalex.org/W4312933868","https://openalex.org/W4312966374","https://openalex.org/W4313029666","https://openalex.org/W4320831569","https://openalex.org/W4321277285","https://openalex.org/W4321473512","https://openalex.org/W4323892956","https://openalex.org/W4361194528","https://openalex.org/W4382240897","https://openalex.org/W4385245566","https://openalex.org/W6600195515"],"related_works":["https://openalex.org/W2006073222","https://openalex.org/W2488916264","https://openalex.org/W2323573032","https://openalex.org/W198625436","https://openalex.org/W1908077024","https://openalex.org/W2095388346","https://openalex.org/W2379751185","https://openalex.org/W2379404183","https://openalex.org/W2004509987","https://openalex.org/W1992842611"],"abstract_inverted_index":{"Painterly":[0,58],"image":[1],"harmonization":[2,105],"aims":[3],"to":[4,102,134],"insert":[5],"photographic":[6],"objects":[7,44],"into":[8],"paintings":[9],"and":[10,47,70,81,121,129,141,160,167],"obtain":[11],"artistically":[12],"coherent":[13],"composite":[14],"images.":[15],"Previous":[16],"methods":[17],"for":[18],"this":[19],"task":[20],"mainly":[21],"rely":[22],"on":[23],"inference":[24],"optimization":[25],"or":[26,36],"generative":[27],"adversarial":[28],"network,":[29],"but":[30],"they":[31],"are":[32,100,169],"either":[33],"very":[34],"time-consuming":[35],"struggling":[37],"at":[38,171],"fine":[39],"control":[40],"of":[41],"the":[42,78,82,93,104,110,136,146,156],"foreground":[43,87,95,157],"(e.g.,":[45],"texture":[46],"content":[48,119,142],"details).":[49],"To":[50],"address":[51],"these":[52],"issues,":[53],"we":[54,116],"propose":[55],"a":[56,66,71],"novel":[57],"Harmonization":[59],"stable":[60],"Diffusion":[61],"model":[62,168],"(PHDiffusion),":[63],"which":[64],"includes":[65],"lightweight":[67],"adaptive":[68,79],"encoder":[69,80],"Dual":[72],"Encoder":[73],"Fusion":[74],"(DEF)":[75],"module.":[76],"Specifically,":[77],"DEF":[83],"module":[84],"first":[85],"stylize":[86,155],"features":[88,96],"within":[89],"each":[90],"encoder.":[91],"Then,":[92],"stylized":[94],"from":[97,149],"both":[98],"encoders":[99],"combined":[101],"guide":[103],"process.":[106],"During":[107],"training,":[108],"besides":[109],"noise":[111],"loss":[112,120,128],"in":[113],"diffusion":[114],"model,":[115],"additionally":[117],"employ":[118],"two":[122],"style":[123,127,131,139],"losses,":[124],"i.e.,":[125],"AdaIN":[126],"contrastive":[130],"loss,":[132],"aiming":[133],"balance":[135],"trade-off":[137],"between":[138],"migration":[140],"preservation.":[143],"Compared":[144],"with":[145],"state-of-the-art":[147],"models":[148],"related":[150],"fields,":[151],"our":[152],"PHDiffusion":[153],"can":[154],"more":[158],"sufficiently":[159],"simultaneously":[161],"retain":[162],"finer":[163],"content.":[164],"Our":[165],"code":[166],"available":[170],"https://github.com/bcmi/PHDiffusion-Painterly-Image-Harmonization":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}