{"id":"https://openalex.org/W7125961203","doi":"https://doi.org/10.1109/smc58881.2025.11342753","title":"Enhancing Visual Aesthetics in Stable Diffusion: A Reinforcement Learning Approach","display_name":"Enhancing Visual Aesthetics in Stable Diffusion: A Reinforcement Learning Approach","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125961203","doi":"https://doi.org/10.1109/smc58881.2025.11342753"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5052816488","display_name":"Junyong You","orcid":"https://orcid.org/0000-0002-4288-5244"},"institutions":[{"id":"https://openalex.org/I4210107808","display_name":"NORCE Research AS","ror":"https://ror.org/02gagpf75","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210107808"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Junyong You","raw_affiliation_strings":["Norwegian Research Centre (NORCE),Bergen,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian Research Centre (NORCE),Bergen,Norway","institution_ids":["https://openalex.org/I4210107808"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028506258","display_name":"Yuan Lin","orcid":"https://orcid.org/0000-0002-6753-570X"},"institutions":[{"id":"https://openalex.org/I2800207870","display_name":"H\u00f8yskolen Kristiania","ror":"https://ror.org/03gss5916","country_code":"NO","type":"education","lineage":["https://openalex.org/I2800207870"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Yuan Lin","raw_affiliation_strings":["Kristiania University of Applied Science,Oslo,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kristiania University of Applied Science,Oslo,Norway","institution_ids":["https://openalex.org/I2800207870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124060839","display_name":"Bin Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I47449453","display_name":"Kean University","ror":"https://ror.org/04wzzqn13","country_code":"US","type":"education","lineage":["https://openalex.org/I47449453"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Hu","raw_affiliation_strings":["Kean University,New Jersey,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kean University,New Jersey,USA","institution_ids":["https://openalex.org/I47449453"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":"2833","last_page":"2839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.8393999934196472,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.8393999934196472,"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":0.11309999972581863,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.01119999960064888,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6611999869346619},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5200999975204468},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.511900007724762},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5113000273704529},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.46209999918937683},{"id":"https://openalex.org/keywords/cognitive-reframing","display_name":"Cognitive reframing","score":0.45989999175071716},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42289999127388}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6611999869346619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6323999762535095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6050000190734863},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.46209999918937683},{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4083999991416931},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39719998836517334},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3495999872684479},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.265500009059906},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C126057942","wikidata":"https://www.wikidata.org/wiki/Q35158","display_name":"Stereoscopy","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6658290028572083}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1896080482","https://openalex.org/W1990647098","https://openalex.org/W2009678853","https://openalex.org/W2038292797","https://openalex.org/W2078807908","https://openalex.org/W2117117414","https://openalex.org/W2325937025","https://openalex.org/W2529088810","https://openalex.org/W2754213847","https://openalex.org/W2963165596","https://openalex.org/W3003957020","https://openalex.org/W3098267758","https://openalex.org/W3138028713","https://openalex.org/W3171472210","https://openalex.org/W3173777717","https://openalex.org/W4285606417","https://openalex.org/W4312933868","https://openalex.org/W4386065622","https://openalex.org/W4390873054","https://openalex.org/W4404545718"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"models":[1],"such":[2,29],"as":[3,30,103,121,133],"stable":[4,63,118,163],"diffusion":[5,64,119,164],"have":[6],"recently":[7],"achieved":[8],"significant":[9],"success":[10],"in":[11,81,107,135,150,161],"producing":[12],"high-quality":[13],"images":[14,60,191],"conditioned":[15],"on":[16,88],"textual":[17],"inputs.":[18],"It":[19],"is":[20],"difficult":[21],"to":[22,54,154,167,198],"control":[23],"the":[24,56,104,108,113,117,126,151,156,162,169,179,185,189],"quality":[25,187],"of":[26,59,78,99,116,188],"generated":[27,190],"images,":[28],"aesthetic":[31,57,67,97,171,186],"quality,":[32],"after":[33],"an":[34,96,100],"image":[35,79,101],"generative":[36],"model":[37,69,94,120],"has":[38,70],"been":[39,71],"trained.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,176],"pro-pose":[45],"a":[46,82,122,136],"novel":[47],"method":[48,181],"that":[49,178],"leverages":[50],"reinforcement":[51],"learning":[52],"(RL)":[53],"enhance":[55],"appeal":[58],"produced":[61],"by":[62,74],"models.":[65],"An":[66],"assessment":[68,93],"first":[72],"developed":[73],"modelling":[75],"influence":[76],"factors":[77],"aesthetics":[80],"deep":[83],"network":[84,157],"and":[85,196],"then":[86],"trained":[87],"publicly":[89],"available":[90],"datasets.":[91],"The":[92,141],"produces":[95],"score":[98],"serving":[102],"reward":[105],"function":[106],"RL":[109,152],"framework.":[110],"By":[111],"reframing":[112],"denoising":[114,128],"process":[115,139],"sequential":[123],"decision-making":[124],"problem,":[125],"intermediate":[127],"steps":[129],"can":[130,147,182],"be":[131,148],"formulated":[132],"actions":[134],"Markov":[137],"decision":[138],"(MDP).":[140],"proximal":[142],"policy":[143],"optimization":[144],"(PPO)":[145],"algorithm":[146],"applied":[149],"framework":[153],"optimize":[155],"parameters":[158],"(i.e.,":[159],"U-Net)":[160],"model,":[165],"aiming":[166],"maximize":[168],"expected":[170],"reward.":[172],"Through":[173],"extensive":[174],"experiments,":[175],"demonstrate":[177],"proposed":[180],"significantly":[183],"improve":[184],"while":[192],"maintaining":[193],"their":[194],"diversity":[195],"adherence":[197],"input":[199],"prompts.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-29T00:00:00"}