{"id":"https://openalex.org/W7139964995","doi":"https://doi.org/10.48550/arxiv.2603.19206","title":"RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing","display_name":"RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7139964995","doi":"https://doi.org/10.48550/arxiv.2603.19206"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.19206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19206","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.19206","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103048066","display_name":"Yue Gong","orcid":"https://orcid.org/0009-0004-4356-7696"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gong, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130218264","display_name":"Hongyu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hongyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130236593","display_name":"Shanyuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shanyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130252060","display_name":"Bo Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Bo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054182752","display_name":"Yan Ma","orcid":"https://orcid.org/0000-0002-9492-3492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Yuhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047587238","display_name":"Lifang Wu","orcid":"https://orcid.org/0000-0003-3334-2923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Liebucha","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130222209","display_name":"Xiaoyu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xiaoyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130219434","display_name":"Manyuan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Manyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130217074","display_name":"Dawei Leng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leng, Dawei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100605634","display_name":"Yuhui Yin","orcid":"https://orcid.org/0000-0002-2151-4583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Yuhui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130248339","display_name":"Lijun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lijun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5103048066"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.8575000166893005,"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":0.8575000166893005,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.016899999231100082,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.012600000016391277,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7526000142097473},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6930999755859375},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.623199999332428},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6205999851226807},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5507000088691711},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5462999939918518},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41850000619888306},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39570000767707825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965999841690063},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7526000142097473},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6930999755859375},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.623199999332428},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6205999851226807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6105999946594238},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5507000088691711},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4260999858379364},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.37059998512268066},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.31209999322891235},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.19206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19206","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.19206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19206","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"models":[1,15,34],"have":[2],"become":[3],"the":[4,124,128,200],"dominant":[5],"paradigm":[6],"for":[7,23,120,145],"image":[8,196],"generation":[9,58,102,194],"and":[10,25,103,161,176,195],"editing,":[11,197],"with":[12,179],"latent":[13,21,139],"diffusion":[14,40,85,147,181],"shifting":[16],"denoising":[17],"to":[18,29,42,68,117],"a":[19,96,109,114,134,142,168],"compact":[20,143],"space":[22,140],"efficiency":[24],"scalability.":[26],"Recent":[27],"attempts":[28],"leverage":[30],"pretrained":[31,129],"visual":[32,190],"representation":[33,43,48,130],"as":[35,50,77,79],"tokenizer":[36,98,169],"priors":[37],"either":[38],"align":[39],"features":[41,44],"or":[45],"directly":[46],"reuse":[47],"encoders":[49],"frozen":[51,69],"tokenizers.":[52,206],"Although":[53],"such":[54],"approaches":[55],"can":[56],"improve":[57],"metrics,":[59],"they":[60],"often":[61],"suffer":[62],"from":[63],"limited":[64],"reconstruction":[65,121,202],"fidelity":[66,203],"due":[67],"encoders,":[70],"which":[71,137],"in":[72],"turn":[73],"degrades":[74],"editing":[75],"quality,":[76],"well":[78],"overly":[80],"high-dimensional":[81],"latents":[82,178],"that":[83,99,112,156,170,186],"make":[84],"modeling":[86,182],"difficult.":[87],"To":[88],"address":[89],"these":[90,165],"limitations,":[91],"We":[92,105,149],"propose":[93],"Representation-Pivoted":[94],"AutoEncoder,":[95],"representation-based":[97,205],"improves":[100],"both":[101],"editing.":[104],"introduce":[106],"Representation-Pivot":[107],"Regularization,":[108],"training":[110,154],"strategy":[111,155],"enables":[113],"representation-initialized":[115],"encoder":[116],"be":[118],"fine-tuned":[119],"while":[122,198],"preserving":[123],"semantic":[125],"structure":[126],"of":[127],"space,":[131],"followed":[132],"by":[133],"variational":[135],"bridge":[136],"compress":[138],"into":[141],"one":[144],"better":[146],"modeling.":[148],"adopt":[150],"an":[151],"objective-decoupled":[152],"stage-wise":[153],"sequentially":[157],"optimizes":[158],"generative":[159],"tractability":[160],"reconstruction-fidelity":[162],"objectives.":[163],"Together,":[164],"components":[166],"yield":[167],"preserves":[171],"strong":[172],"semantics,":[173],"reconstructs":[174],"faithfully,":[175],"produces":[177],"reduced":[180],"complexity.":[183],"Experiments":[184],"demonstrate":[185],"RPiAE":[187],"outperforms":[188],"other":[189],"tokenizers":[191],"on":[192],"text-to-image":[193],"delivering":[199],"best":[201],"among":[204]},"counts_by_year":[],"updated_date":"2026-03-21T06:36:02.116451","created_date":"2026-03-21T00:00:00"}