{"id":"https://openalex.org/W4417220102","doi":"https://doi.org/10.48550/arxiv.2510.20093","title":"StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback","display_name":"StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback","publication_year":2025,"publication_date":"2025-10-23","ids":{"openalex":"https://openalex.org/W4417220102","doi":"https://doi.org/10.48550/arxiv.2510.20093"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.20093","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.20093","pdf_url":"https://arxiv.org/pdf/2510.20093","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.20093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058108589","display_name":"Jiho Park","orcid":"https://orcid.org/0000-0002-1048-3881","observed_orcids":["https://orcid.org/0000-0002-1048-3881"]},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Park, Jiho","raw_affiliation_strings":["Dongguk University Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguk University Seoul , South Korea","institution_ids":["https://openalex.org/I205490536"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Choi, Sieun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Choi, Sieun","raw_affiliation_strings":["Dongguk University Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguk University Seoul , South Korea","institution_ids":["https://openalex.org/I205490536"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Seo, Jaeyoon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seo, Jaeyoon","raw_affiliation_strings":["Dongguk University Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguk University Seoul , South Korea","institution_ids":["https://openalex.org/I205490536"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080664764","display_name":"Jihie Kim","orcid":"https://orcid.org/0000-0003-2358-4021","observed_orcids":["https://orcid.org/0000-0003-2358-4021"]},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Jihie","raw_affiliation_strings":["Dongguk University Seoul , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguk University Seoul , South Korea","institution_ids":["https://openalex.org/I205490536"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205490536"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":1.0,"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":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.0,"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/sketch-generation","display_name":"sketch generation","score":0.7720000147819519},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8069999814033508},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.7889999747276306},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5080000162124634},{"id":"https://openalex.org/keywords/reward-function","display_name":"reward function","score":0.6079999804496765},{"id":"https://openalex.org/keywords/image-text-alignment","display_name":"image-text alignment","score":0.8640000224113464},{"id":"https://openalex.org/keywords/abstract-expression","display_name":"abstract expression","score":0.531000018119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288999795913696},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.7372000217437744},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6499000191688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6189000010490417},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49149999022483826},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43650001287460327},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26460000872612}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.20093","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.20093","pdf_url":"https://arxiv.org/pdf/2510.20093","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2510.20093","doi":"https://doi.org/10.48550/arxiv.2510.20093","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.20093","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.20093","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.20093","pdf_url":"https://arxiv.org/pdf/2510.20093","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2094304639","display_name":null,"funder_award_id":"IITP-2025-RS-2023-00254592","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3626246151","display_name":null,"funder_award_id":"IITP-2025-RS-2023-00254592","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G3812690899","display_name":null,"funder_award_id":"RS-2023","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320321213","display_name":"Dongguk University","ror":"https://ror.org/057q6n778"},{"id":"https://openalex.org/F4320322105","display_name":"Korea Institute of Science and Technology Information","ror":"https://ror.org/01k4yrm29"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417220102.pdf","grobid_xml":"https://content.openalex.org/works/W4417220102.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W1959608418","https://openalex.org/W2936695845","https://openalex.org/W3020908159","https://openalex.org/W3212616005","https://openalex.org/W4281485151","https://openalex.org/W4321855132","https://openalex.org/W4378464471","https://openalex.org/W4378945165","https://openalex.org/W4384918448","https://openalex.org/W4385574358","https://openalex.org/W4402426725","https://openalex.org/W4402904177","https://openalex.org/W4403444272","https://openalex.org/W4404330874","https://openalex.org/W4416024151"],"related_works":["https://openalex.org/W4402036111","https://openalex.org/W4390784146","https://openalex.org/W4415538262","https://openalex.org/W7133224108","https://openalex.org/W4402667897","https://openalex.org/W4378945165","https://openalex.org/W7168370063","https://openalex.org/W7128923514","https://openalex.org/W7223627054","https://openalex.org/W7125158387"],"abstract_inverted_index":{"Although":[0],"recent":[1],"advancements":[2],"in":[3,16],"diffusion":[4,39],"models":[5,40],"have":[6],"significantly":[7],"enriched":[8],"the":[9,54,66,111,120,125,139],"quality":[10],"of":[11,24,68,122,141],"generated":[12],"images,":[13],"challenges":[14],"remain":[15],"synthesizing":[17],"pixel-based":[18],"human-drawn":[19],"sketches,":[20],"a":[21,34,74],"representative":[22],"example":[23],"abstract":[25],"expression.":[26],"To":[27],"combat":[28],"these":[29],"challenges,":[30],"we":[31,52,72,116],"propose":[32],"StableSketcher,":[33],"novel":[35],"framework":[36],"that":[37,96,144],"empowers":[38],"to":[41,57,63,110,119],"generate":[42],"hand-drawn":[43],"sketches":[44,99,130],"with":[45,100,107,132],"high":[46],"prompt":[47],"fidelity.":[48],"Within":[49],"this":[50],"framework,":[51],"fine-tune":[53],"variational":[55],"autoencoder":[56],"optimize":[58],"latent":[59],"decoding,":[60],"enabling":[61],"it":[62],"better":[64,105],"capture":[65],"characteristics":[67],"sketches.":[69],"In":[70],"parallel,":[71],"integrate":[73],"new":[75],"reward":[76],"function":[77],"for":[78],"reinforcement":[79],"learning":[80],"based":[81],"on":[82,146],"visual":[83],"question":[84],"answering,":[85],"which":[86],"improves":[87],"text-image":[88],"alignment":[89,106],"and":[90,134,151],"semantic":[91],"consistency.":[92],"Extensive":[93],"experiments":[94],"demonstrate":[95],"StableSketcher":[97],"generates":[98],"improved":[101],"stylistic":[102],"fidelity,":[103],"achieving":[104],"prompts":[108],"compared":[109],"Stable":[112],"Diffusion":[113],"baseline.":[114],"Additionally,":[115],"introduce":[117],"SketchDUO,":[118],"best":[121],"our":[123],"knowledge,":[124],"first":[126],"dataset":[127,152],"comprising":[128],"instance-level":[129],"paired":[131],"captions":[133],"question-answer":[135],"pairs,":[136],"thereby":[137],"addressing":[138],"limitations":[140],"existing":[142],"datasets":[143],"rely":[145],"image-label":[147],"pairs.":[148],"Our":[149],"code":[150],"will":[153],"be":[154],"made":[155],"publicly":[156],"available":[157],"upon":[158],"acceptance.":[159],"Project":[160],"page:":[161],"https://zihos.github.io/StableSketcher":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-25T00:00:00"}