{"id":"https://openalex.org/W3193457413","doi":"https://doi.org/10.1145/3474085.3475206","title":"Towards Controllable and Photorealistic Region-wise Image Manipulation","display_name":"Towards Controllable and Photorealistic Region-wise Image Manipulation","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3193457413","doi":"https://doi.org/10.1145/3474085.3475206","mag":"3193457413"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.08674","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ansheng You","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ansheng You","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenglin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglin Zhou","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qixuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixuan Zhang","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan Xu","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"535","last_page":"543"},"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":0.9983000159263611,"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":0.9983000159263611,"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":0.9890999794006348,"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":0.9815999865531921,"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/flexibility","display_name":"Flexibility (engineering)","score":0.6991999745368958},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6283000111579895},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6179999709129333},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6105999946594238},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.588100016117096},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4731999933719635},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4578999876976013},{"id":"https://openalex.org/keywords/image-manipulation","display_name":"Image manipulation","score":0.4530999958515167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085000276565552},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6991999745368958},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6283000111579895},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6179999709129333},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6105999946594238},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.588100016117096},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4593999981880188},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4578999876976013},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.4530999958515167},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41499999165534973},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4058000147342682},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3475206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.08674","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.08674","pdf_url":"https://arxiv.org/pdf/2108.08674","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:2108.08674","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.08674","pdf_url":"https://arxiv.org/pdf/2108.08674","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W1901129140","https://openalex.org/W2331128040","https://openalex.org/W2339754110","https://openalex.org/W2475287302","https://openalex.org/W2604721644","https://openalex.org/W2771305881","https://openalex.org/W2798365772","https://openalex.org/W2801495938","https://openalex.org/W2961363059","https://openalex.org/W2962770929","https://openalex.org/W2963201933","https://openalex.org/W2963767194","https://openalex.org/W2963890275","https://openalex.org/W2965128575","https://openalex.org/W2969810168","https://openalex.org/W2982041717","https://openalex.org/W2985068832","https://openalex.org/W3009014607","https://openalex.org/W3034214199","https://openalex.org/W3034431451","https://openalex.org/W3034600949","https://openalex.org/W3035574324","https://openalex.org/W3035757124","https://openalex.org/W3109547540","https://openalex.org/W3159890710"],"related_works":[],"abstract_inverted_index":{"Adaptive":[0],"and":[1,41,48,58,121],"flexible":[2],"image":[3],"editing":[4,75],"is":[5,63],"a":[6,18,30,67,82],"desirable":[7],"function":[8],"of":[9,50,117,125],"modern":[10],"generative":[11,19],"models.":[12],"In":[13],"this":[14],"work,":[15],"we":[16],"present":[17],"model":[20,62,92,100,128],"with":[21,54],"auto-encoder":[22],"architecture":[23],"for":[24,110,129],"per-region":[25],"style":[26,42,49,59,96,134,140],"manipulation.":[27],"We":[28],"apply":[29],"code":[31],"consistency":[32],"loss":[33,70],"to":[34,71],"enforce":[35],"an":[36],"explicit":[37],"disentanglement":[38],"between":[39],"content":[40,47,57,68],"latent":[43,136],"representations,":[44],"making":[45],"the":[46,73,115,118,123,126],"generated":[51],"samples":[52],"consistent":[53],"their":[55],"corresponding":[56],"references.":[60],"The":[61],"also":[64],"constrained":[65],"by":[66,89],"alignment":[69],"ensure":[72],"foreground":[74,94],"will":[76],"not":[77],"interfere":[78],"background":[79],"contents.":[80],"As":[81],"result,":[83],"given":[84],"interested":[85],"region":[86],"masks":[87],"provided":[88],"users,":[90],"our":[91,99],"supports":[93],"region-wise":[95,133],"transfer.":[97,141],"Specially,":[98],"receives":[101],"no":[102],"extra":[103],"annotations":[104],"such":[105],"as":[106],"semantic":[107],"labels":[108],"except":[109],"self-supervision.":[111],"Extensive":[112],"experiments":[113],"show":[114],"effectiveness":[116],"proposed":[119,127],"method":[120],"exhibit":[122],"flexibility":[124],"various":[130],"applications,":[131],"including":[132],"editing,":[135],"space":[137],"interpolation,":[138],"cross-domain":[139]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-08-30T00:00:00"}