{"id":"https://openalex.org/W7171999552","doi":"https://doi.org/10.1145/3774521.3774558","title":"Quality Aware Text-to-Image Synthesis with distortion maps as structural guides","display_name":"Quality Aware Text-to-Image Synthesis with distortion maps as structural guides","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7171999552","doi":"https://doi.org/10.1145/3774521.3774558"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774558","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774558","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774558","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119288400","display_name":"Kriti Khare","orcid":null},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kriti Khare","raw_affiliation_strings":["Indian Institute of Technology Mandi, Mandi, India"],"raw_orcid":"https://orcid.org/0009-0002-3789-4223","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Mandi, Mandi, India","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087871225","display_name":"Parimala Kancharla","orcid":null},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parimala Kancharla","raw_affiliation_strings":["Indian Institute of Technology, Mandi, Mandi, India"],"raw_orcid":"https://orcid.org/0009-0001-4113-1600","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Mandi, Mandi, India","institution_ids":["https://openalex.org/I9579091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9579091"],"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.7397000193595886},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6054999828338623},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5985999703407288},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5971999764442444},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.583899974822998},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5263000130653381},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5210000276565552},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.49059998989105225},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44670000672340393}],"concepts":[{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.7397000193595886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6629999876022339},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5985999703407288},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5437999963760376},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5267999768257141},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5263000130653381},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5210000276565552},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49059998989105225},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.3582000136375427},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C205372313","wikidata":"https://www.wikidata.org/wiki/Q355645","display_name":"Latent image","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C100279318","wikidata":"https://www.wikidata.org/wiki/Q467440","display_name":"Sample space","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C173413354","wikidata":"https://www.wikidata.org/wiki/Q7049470","display_name":"Nonlinear distortion","level":4,"score":0.25839999318122864},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774558","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774558","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774558","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774558","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1973207880","https://openalex.org/W2099474155","https://openalex.org/W2125848133","https://openalex.org/W2133665775","https://openalex.org/W2740667773","https://openalex.org/W2899684919","https://openalex.org/W2937719843","https://openalex.org/W2962770929","https://openalex.org/W2963470893","https://openalex.org/W3001347582","https://openalex.org/W3180355996","https://openalex.org/W4232050619","https://openalex.org/W4312933868","https://openalex.org/W4390873084"],"related_works":[],"abstract_inverted_index":{"Although":[0],"Stable":[1,180],"Diffusion":[2,9,181],"(SD),":[3],"a":[4,52,59],"popular":[5],"variant":[6,182],"of":[7,71,145],"Latent":[8],"Models":[10],"(LDMs),":[11],"has":[12],"been":[13],"the":[14,68,135,146,150,157,163,178],"state-of-the-art":[15,179],"for":[16,127],"various":[17],"generative":[18],"vision":[19],"tasks,":[20],"it":[21],"suffers":[22],"from":[23,74],"major":[24],"issues":[25],"during:":[26],"(i)":[27],"Training:":[28],"due":[29,41],"to":[30,42,63,82,89,98],"heavy":[31],"compute":[32],"requirement,":[33],"and":[34,38,92,119],"prolonged":[35],"training":[36,136],"duration;":[37],"(ii)":[39],"Inference:":[40],"structurally-deformed":[43],"sample":[44,158,174],"generation.":[45],"To":[46],"address":[47],"these":[48,84],"issues,":[49],"we":[50,56,108],"propose":[51],"two-fold":[53],"solution.":[54],"First,":[55],"introduce":[57],"DistFormer,":[58],"transformer-based":[60],"model":[61],"designed":[62],"generate":[64],"distortion":[65,120],"maps":[66],"in":[67,149,173],"latent":[69,76],"space":[70],"LDMs":[72],"directly":[73],"input":[75],"embeddings.":[77],"DistFormer":[78],"is":[79],"trained":[80],"offline":[81],"produce":[83],"maps,":[85,91,103],"which":[86,112],"are":[87],"analogous":[88],"SSIM":[90,102],"further":[93],"refined":[94],"using":[95],"reinforcement":[96],"learning":[97],"align":[99],"with":[100],"ground-truth":[101],"enhancing":[104],"generation":[105,159,175],"accuracy.":[106],"Second,":[107],"present":[109],"QualityAwareStableDiffusion":[110],"(QASD),":[111],"employs":[113],"both":[114],"textual":[115],"embeddings":[116,121],"(from":[117,122],"CLIP)":[118],"DistFormer)":[123],"as":[124],"joint":[125],"guidance":[126],"LDMs.":[128],"Our":[129],"proposed":[130],"QASD":[131,167],"not":[132],"only":[133],"accelerates":[134],"process":[137],"while":[138],"maintaining":[139],"stability":[140],"(by":[141],"promoting":[142],"faster":[143],"convergence":[144],"U-Net":[147],"loss":[148],"reverse":[151],"diffusion":[152],"process),":[153],"but":[154],"also":[155],"enhances":[156],"quality":[160,176],"structurally":[161],"at":[162],"inference":[164],"stage.":[165],"Specifically,":[166],"demonstrates":[168],"around":[169],"\u223c":[170],"17%":[171],"improvement":[172],"over":[177],"SDXL-Turbo.":[183]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}