{"id":"https://openalex.org/W7166124598","doi":"https://doi.org/10.48550/arxiv.2606.26930","title":"PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation","display_name":"PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166124598","doi":"https://doi.org/10.48550/arxiv.2606.26930"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.26930","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26930","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.26930","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139461038","display_name":"Xiaomin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaomin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139407584","display_name":"Qian Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139412629","display_name":"Yinan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yinan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139430880","display_name":"Ying Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139393051","display_name":"Chen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139416537","display_name":"Jing Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029653356","display_name":"H\u00fcseyin Ozan \u04aairkino\u011flu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Huchuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139390141","display_name":"Xu Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.8867999911308289,"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":0.8867999911308289,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.026799999177455902,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.019200000911951065,"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/generative-grammar","display_name":"Generative grammar","score":0.5080000162124634},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4702000021934509},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3905999958515167},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3846000134944916},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.35839998722076416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6172000169754028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5618000030517578},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4458000063896179},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3905999958515167},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.35839998722076416},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.32600000500679016},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.26930","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26930","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.26930","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26930","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":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.41087374091148376}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"like":[2,27,73],"Group":[3],"Relative":[4],"Policy":[5],"Optimization":[6],"(GRPO)":[7],"has":[8],"significantly":[9,159],"advanced":[10],"text-to-image":[11],"post-training.":[12],"However,":[13],"current":[14],"methods":[15],"often":[16],"favor":[17],"superficial":[18],"aesthetics,":[19],"such":[20],"as":[21],"over-saturated":[22],"colors,":[23],"leaving":[24],"critical":[25],"flaws":[26],"AI":[28,79,165],"artifacts":[29,72,166],"and":[30,77,121,141,167],"biological":[31],"implausibilities":[32],"unresolved.":[33],"We":[34],"attribute":[35],"these":[36],"limitations":[37],"to":[38,53,58,116,124],"two":[39],"primary":[40],"factors:":[41],"(1)":[42],"The":[43],"absence":[44],"of":[45],"real":[46,104],"images":[47,105],"during":[48],"post-training":[49],"confines":[50],"GRPO":[51,108],"sampling":[52,109],"the":[54,64,107,127],"original":[55],"distribution,":[56],"failing":[57],"break":[59,97],"inherent":[60,98],"generative":[61,99],"boundaries;":[62],"(2)":[63],"optimization":[65],"process":[66],"lacks":[67],"specific":[68],"rewards":[69],"targeting":[70],"fine-grained":[71],"overly":[74],"oily":[75],"skin":[76],"other":[78],"artifacts.":[80],"To":[81],"address":[82],"this,":[83],"we":[84,96,131,147],"propose":[85],"PortraitGen,":[86],"a":[87,133,150],"novel":[88],"framework":[89],"tailored":[90],"for":[91,138,143],"photorealistic":[92],"portrait":[93],"generation.":[94],"First,":[95],"boundaries":[100],"by":[101],"directly":[102],"introducing":[103],"into":[106],"groups,":[110],"where":[111],"image":[112],"inversion":[113],"is":[114],"employed":[115],"obtain":[117],"their":[118],"transition":[119],"probabilities":[120],"latents.":[122],"Second,":[123],"explicitly":[125],"steer":[126],"model":[128],"toward":[129],"photorealism,":[130],"introduce":[132],"complementary":[134],"dual-reward":[135],"mechanism:":[136],"OmniReward":[137],"general":[139],"quality":[140],"AI-Portrait":[142],"human-centric":[144],"fidelity.":[145],"Furthermore,":[146],"curate":[148],"PortraitBench,":[149],"comprehensive":[151],"portrait-centric":[152],"benchmark.":[153],"Extensive":[154],"experiments":[155],"demonstrate":[156],"that":[157],"PortraitGen":[158],"outperforms":[160],"existing":[161],"baselines,":[162],"effectively":[163],"suppressing":[164],"achieving":[168],"unprecedented":[169],"photorealism.":[170]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-27T00:00:00"}